Distributed named navigation pedestrian and vehicle warning method, system and device

Abstract

The application discloses a kind of distributed naming navigation pedestrian and vehicle early warning method, system and device, comprising: the classification zoning segmentation of road, the classification fragmentation of real estate, the correlation of road and surrounding real estate is established, map and knowledge base are constructed;Establish distributed naming navigation pedestrian and vehicle early warning system;The classification type of pedestrian and vehicle is respectively enveloped, and the pedestrian and vehicle entering each road section is respectively coded and named;Pedestrian and vehicle on each road section establish trajectory correlation and establish correlation degree parameter and index;Distributed naming navigation pedestrian and vehicle early warning system real-time calculation and navigation and or early warning.The application constructs "naming-connection structure-correlation map-navigation and early warning visualization" and "data space-time multidimensional multimodal deep perception cognitive flow space" associated mapping matching collaborative computing model, automatically carries out risk prediction, early warning and event evaluation to pedestrian and vehicle, enhances the accuracy, real-time performance and safety and reliability of navigation, tracking and early warning.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent safe navigation, in particular to a distributed named navigation pedestrian and vehicle early warning method, system and device. BACKGROUND

[0002] At present, the distributed named navigation pedestrian and vehicle early warning technology is widely used in automatic driving, intelligent transportation, military exercises, intelligent operation, industrial production, terrain exploration, astronomical observation, emergency rescue and the like.

[0003] However, in the prior art, most of the technologies are concentrated in GPS, Beidou, image segmentation technology and the like, and there are few literatures on intelligent safe navigation and early warning technology in dynamic, complex and uncertain environments, and the technology is still very lacking.

[0004] Using the prior art, accurate and real-time early warning of pedestrians and vehicles cannot be achieved. SUMMARY

[0005] The present application provides a distributed named navigation pedestrian and vehicle early warning method, system and device to overcome the defects of the prior art.

[0006] In the present application, the distributed named navigation is an intelligent navigation mode that can navigate the movement or flight of people, machines and objects by combining the spatio-temporal geographical position and environment with semantic information through intelligent association and collaborative computing of cameras, sensors, radars, servers and the like. A plurality of service nodes are used to process navigation requests and provide navigation results. This can improve the accuracy and efficiency of navigation, effectively reduce system and or network energy consumption, and also ensure the reliability and scalability of the service.

[0007] In the present application, the pedestrian and vehicle early warning is combined with the distributed named navigation to form a distributed named navigation pedestrian and vehicle early warning system. In the urban traffic environment, the movement trajectory and associated conditions of surrounding pedestrians and vehicles can be monitored in real time, and early warning signals can be sent in time. The system can also be applied to other scenarios of movement or flight of people, machines and objects.

[0008] In order to achieve the above application purposes, the technical solutions adopted by the present application are as follows:

[0009] A distributed named navigation pedestrian and vehicle early warning method comprises the following steps:

[0010] S1, classifying, partitioning and segmenting roads, classifying and fragmenting real estate, establishing an association between roads and surrounding real estate, and constructing a map and a knowledge base;

[0011] S2, establishing a distributed named navigation pedestrian and vehicle early warning system;

[0012] S3, the classification of pedestrian and vehicle is enveloped respectively, and the pedestrian and vehicle entering each road section is coded and named respectively;

[0013] S4, the trajectory correlation between the pedestrian and vehicle on each road section is established, and the correlation measurement parameters and indexes are established;

[0014] S5, the distributed named navigation pedestrian and vehicle warning system is calculated, navigated and warned in real time.

[0015] Further, in S1, the real estate is classified and fragmented, the road is correlated with the surrounding real estate, and the map and knowledge base are constructed, including:

[0016] S11, the classification of roads is coded and named, and the real estate is classified and fragmented, and is digitized by image, video stream and text description;

[0017] S12, the correlation between each road section and its surrounding real estate is established, and the correlation measurement parameters and indexes are established;

[0018] The correlation is established by using geographical geometric figures or text language description;

[0019] The correlation measurement parameters and indexes include distance, direction, pedestrian and vehicle space-time flow, pedestrian and vehicle travel frequency, and various space-time attribute characteristics of pedestrian and vehicle and pedestrian and vehicle cluster;

[0020] S13, the correlation between each road section and each road section connected thereto is established, and the correlation measurement parameters and indexes are established;

[0021] The correlation is established by using geographical geometric figures or text language description;

[0022] The correlation measurement parameters and indexes include: connection direction, distance, pedestrian and vehicle space-time flow, pedestrian and vehicle transfer probability, pedestrian and vehicle travel frequency, and various space-time attribute characteristics of pedestrian and vehicle and pedestrian and vehicle cluster;

[0023] S14, the map is constructed and updated according to the correlation relationship between each road section and real estate, the space-time change update state and the prediction calculation of the traffic tool;

[0024] The construction of the map and the knowledge base also includes that each road section and its connected road, and the surrounding real estate and environment, and all people, machines and objects existing therein are mutual reference objects, and the map and path planning are constructed and planned according to the mutual correlation and or reference;

[0025] S15, the coding and or naming and feature information of the road and real estate are encrypted and decrypted;

[0026] S16, visualizing or simulating the road and real estate and their spatio-temporal changes, and establishing a road and real estate knowledge database or cloud.

[0027] Further, the distributed named navigation pedestrian and vehicle warning system established in S2 comprises:

[0028] The distributed named navigation pedestrian and vehicle warning system is established by using servers, base stations, gateways, routers, switches, sensors, cameras, and radars.

[0029] According to the classification and segmentation of roads, the distributed named navigation pedestrian and vehicle warning system is blockchained.

[0030] According to the classification and segmentation of roads, the distributed named navigation pedestrian and vehicle warning system adopts a gateway cluster architecture to establish collaboration, and can also adopt a named data network security architecture combining naming and addressing.

[0031] Further, the distributed named navigation pedestrian and vehicle warning system in S2 comprises:

[0032] The input module, output module, secure computing processing module, navigation warning control module, navigation warning event management module, storage module, map module, environmental and meteorological module, road environment module, pedestrian module, vehicle module, trajectory module, correlation module, visualization module, hardware management module, software management module, language and image knowledge base module, navigation language translation NaviT module, network connection control module, road and real estate correlation knowledge database or cloud module, and Web interactive operating system module.

[0033] The above-mentioned modules are interconnected, and the modules can be divided into multiple different processing units. The modules and units can be distributed in different servers or clouds of a network through physical isolation and / or virtual isolation. The modules and units can be integrated in the same device. Each module and unit is provided with a cache area according to efficiency and data conditions. The input module, input unit, output module, and output unit can be embedded and integrated into other modules, or can be interconnected with other modules.

[0034] The functions of each module of the distributed named navigation pedestrian and vehicle warning system are as follows:

[0035] The input module is responsible for collecting information for navigation and warning, including various sensors, radars, cameras, network interfaces, and intelligent devices.

[0036] The output module is responsible for transmitting processed navigation and warning information to corresponding users, terminals, devices, and interfaces.

[0037] Security computing processing module: responsible for trajectory comparison calculation according to various intelligent learning and or intelligent computing processing technology, road environment obstacle avoidance and risk avoidance calculation, weather prediction calculation, path planning calculation, event space-time change rule logic calculation, correlation learning calculation, video stream compression encoding calculation, network transmission processing, various interconnection security protocol design, various information and data security processing and decryption calculation;

[0038] Navigation warning control module: responsible for mutual communication between modules, and forms navigation information instructions and warning information instructions according to interactive information, rule specification standards, calculation results, and evaluates classification and grading, and issues navigation instructions and or warning instructions to pedestrians and or vehicles;

[0039] Navigation warning event management module: responsible for evaluating, classifying and grading specific navigation events and warning events, establishing event data logic model and related flow space, forming event mapping database and calculating statistics, etc. for various learning calculations;

[0040] Storage module: responsible for storing module data, rules, algorithms, models, strategies, and storing them in hierarchical, block and object form, and setting effective period and refreshing invalid data in time according to usage and importance;

[0041] Map module: responsible for calculating and generating and updating maps, routes, and road sign information, and responsible for calculating and reasoning to generate real-time dynamic path planning information and navigation route scheduling information for each pedestrian and each vehicle, including various levels of electronic maps, virtual reality maps and mixed reality maps, and associated matching mapping data information;

[0042] Environmental meteorological module: responsible for collecting, detecting, identifying, classifying and standardizing environmental meteorological real-time information data, and predicting and calculating environmental meteorological information;

[0043] Road environment module: responsible for collecting, detecting, identifying, classifying and standardizing road environment real-time information data, road classification, segmentation and zoning, and predicting and planning mobile routes;

[0044] Pedestrian module: responsible for pedestrian identification, classification, labeling, pedestrian coding and decoding, naming and eliminating naming, pedestrian statistical calculation, pedestrian space-time flow change rule calculation, registration, identity authentication, and interaction between users and the system. The pedestrian identification, classification and labeling includes identification and classification according to pedestrian coding, naming, clothing, appearance, age, shape, and action characteristics, identification and classification according to pedestrian cluster structure, density, number of people, behavior, clothing, age, and cluster group activity type, and identification and classification according to human, machine, and object interaction characteristics;

[0045] Vehicle module: responsible for vehicle identification classification labeling, vehicle coding and decoding, naming and eliminating naming, vehicle statistical calculation, vehicle space-time flow change law calculation and registration, vehicle authentication, user interaction with the system, wherein the vehicle identification classification labeling includes identification classification labeling according to the characteristics of vehicle coding, naming, color, brand, license plate number, shape, moving or flying speed, and also includes identification classification labeling according to the characteristics of vehicle cluster structure, density, number of vehicles, moving or flying speed and cluster group activity type, and also includes identification classification labeling according to the characteristics of human, machine and object interaction, and the vehicle authentication includes vehicle identity authentication, vehicle owner authentication and vehicle user authentication, as well as the association of various authentication data information with the vehicle;

[0046] Trajectory module: responsible for collecting real-time movement trajectories of pedestrians and vehicles, and forming pedestrian and vehicle trajectory maps;

[0047] Correlation module: responsible for establishing correlations between roads, weather, environment, maps, pedestrians, vehicles and trajectories, performing correlation calculations according to correlation measurement parameters and indicators as well as traffic rules, navigation rules and early warning rules, obtaining real-time correlation data results, and establishing data deep perception and cognitive correlation flow processes and knowledge graphs, storing and updating correlation data, correlation logic and correlation model information;

[0048] Visualization module: responsible for visualizing and displaying map, road conditions, weather, trajectory, pedestrian, vehicle and correlation status on various screens or in real air, and matching mapping virtual and real;

[0049] Hardware management module: responsible for adjusting, checking, repairing and intelligently calculating safety warnings for each hardware of the navigation and early warning system;

[0050] Software management module: responsible for adjusting, checking, repairing and intelligently calculating safety warnings for each software of the navigation and early warning system;

[0051] Language image knowledge base module: responsible for storing various languages, voices, texts, images, symbols, curves, structures and logic knowledge of navigation and early warning information data and their associated information data through classification and scaling, and matching and mapping between languages, voices, texts, images, symbols, curves, structures and logic;

[0052] Navigation language translation NaviT module: according to the language image knowledge base, combining Transformer model and or CNN model and or cross-learning and or reinforcement learning and or statistical learning and or contrast learning intelligent technology method, responsible for language mutual translation and mutual conversion of multi-modal navigation information data, responsible for generating navigation instructions, early warning instructions, map information, path planning information, labeling information and parameter information;

[0053] Network connection control module: responsible for the network connection of each module and each unit, interface management, network detection, network condition calculation, connection protocol design, network information encryption and decryption calculation, security warning;

[0054] Road and real estate association knowledge database or cloud module: responsible for digitizing, visualizing or simulating road and real estate and their spatio-temporal change conditions, and representing the association relationship, association measurement parameters and indexes of the calculated road and real estate, forming the spatio-temporal association logic paradigm and model of each road segment and its connected road segments and surrounding real estate, and calculating and constructing and updating various scale maps;

[0055] Web interactive operating system module: mainly responsible for the safe information interaction between pedestrians and vehicles and each module of the system, such as publishing navigation or warning requirements, and responsible for the safe information interaction between pedestrians and vehicles, and responsible for the safe information interaction between pedestrians and vehicles on each road segment, also including the interaction between various types of users such as people, machines and objects, and the interaction between various types of users and the distributed named navigation pedestrian and vehicle warning system.

[0056] Further, the distributed named navigation pedestrian and vehicle warning system modules in S2 form a spatio-temporal neural network learning mechanism small model according to the association historical data information of each module, and each module is connected to form a spatio-temporal navigation NaviGPT or navigation intelligent agent and various types of navigation warning API.

[0057] According to the corresponding neural network model of each module, a corresponding programmable and or software-defined chip and or processor is designed and developed.

[0058] Further, the sub-steps of S3 include:

[0059] The pedestrians and vehicles are real-time collected by the camera sensing devices of the corresponding road segments and transmitted to the demand modules of the distributed named navigation pedestrian and vehicle warning system, and or the pedestrians and vehicles each have a camera sensing mobile phone or tablet device to real-time collect and transmit to the demand modules of the distributed named navigation pedestrian and vehicle warning system, and or some third-party observation or observation device to real-time collect and transmit to the demand modules of the distributed named navigation pedestrian and vehicle warning system, and or the pedestrians and vehicles each register on the display page such as web page or APP of the distributed named navigation pedestrian and vehicle warning system;

[0060] Pedestrian and vehicle enveloping is to envelop pedestrians and vehicles respectively by using geometric shape images according to the shape and volume characteristics of pedestrians and vehicles, and the appearance shape and volume size of the enveloped geometric image are generally not less than the overall actual shape and volume size of pedestrians and vehicles;

[0061] According to the road segment conditions, the road segment includes the basis for separating the road segment mechanism in the road environment module in the special split line or the special road sign or the distributed naming navigation pedestrian and vehicle early warning system;

[0062] The pedestrians and vehicles entering each road segment are immediately classified, coded, and / or named. The coding and / or naming are uniformly used on the road segment. When the pedestrians and vehicles move out of the road segment, the coding and / or naming automatically become invalid and are cleared. When the pedestrians and vehicles enter another road segment, they are re-coded and / or renamed. When the pedestrians and vehicles move out of the road segment, the coding and / or naming again automatically become invalid and are cleared.

[0063] As a preferred embodiment, one name and / or one or more codes are used for each pedestrian and vehicle on multiple consecutive road segments in S3, or multiple names and / or multiple codes are used.

[0064] As a preferred embodiment, the coding and / or naming in S3 are pre-coded a certain period of time before the pedestrians and vehicles enter a road segment, that is, the coding and / or naming on the road segment and the coding and / or naming on the next road segment exist simultaneously for a certain period of time. The coding and / or naming includes coding and / or naming according to an ordered coding rule, coding and / or naming according to an unordered coding rule, and coding and / or naming according to an encryption and decryption coding rule.

[0065] As a preferred embodiment, the same coding and / or naming mechanism is used for each road segment in S3, or different coding and / or naming mechanisms are used. Multiple sets of coding and / or naming mechanisms are set according to different entrances and moving directions on the same road segment.

[0066] As a preferred embodiment, the coding and / or naming in S3 are automatically completed by the distributed naming navigation pedestrian and vehicle early warning system in real time according to the real-time information of the pedestrians and vehicles. The pedestrians and vehicles cannot modify or adjust the coding and / or naming.

[0067] As a preferred embodiment, the distributed naming navigation pedestrian and vehicle early warning system in S3 associates and matches the coding and / or naming of the pedestrians and vehicles on each road segment with the registration information and / or historical association information of the pedestrians and vehicles.

[0068] As a preferred embodiment, the distributed naming navigation pedestrian and vehicle early warning system in S3 identifies the pedestrians and vehicles through pedestrian and vehicle feature detection and identifies the pedestrians and vehicles through the interconnection and sharing of pedestrian and vehicle information between road segments. The association and matching mapping of each pedestrian and vehicle with each road segment and the coding and / or naming are established.

[0069] As a preferred embodiment, each coding and / or naming on each road segment in S3 includes part or all of the people, machines, and objects in the road space.

[0070] The coding and / or naming of people, machines and objects in each section of the road and its space is periodically recoded and / or renamed with a time period, or periodically recoded and / or renamed with different rules and different mechanisms of coding and / or naming of people, machines and objects in the corresponding road space;

[0071] The length of the time period of coding and / or naming in each section of the road and its space is adjusted and updated according to the road environment, road traffic conditions and time;

[0072] By learning and calculating the road environment, road traffic conditions, road uncertainty factors for a long time, the logical paradigm and model of the space-time variation law of each section of the road environment, the logical paradigm and model of the space-time variation law of each section of the road traffic, the logical paradigm and model of the space-time variation law of the occurrence of each section of the road uncertainty factor, the logical paradigm and model of the space-time variation law of the coding and / or naming of people, machines and objects in each section of the road space, and the updating paradigm and model of the management rules, specifications and standards of traffic, navigation and early warning of each section of the road space are formed;

[0073] According to the space-time variation law of the coding and / or naming of people, machines and objects in each section of the road space, the coding and / or naming of people, machines and objects in each section of the road space is carried out;

[0074] The space-time tracking identification and identity authentication of the people, machines and objects are combined with the space-time variation law of the coding and / or naming of people, machines and objects in each section of the road space and other characteristic attributes of the people, machines and objects, and the tracking identification, classification, flow statistics, space-time tracking identification, identity authentication and relationship identification and authentication of each pedestrian, each vehicle and each object are carried out in the complex scene of the people, machines and objects cluster in each section of the road space;

[0075] The space-time variation law of the coding and / or naming of people, machines and objects in each section of the road space, the space-time variation law of the coding and / or naming of people, machines and objects in each section of the road space, the space-time variation law of the coding and / or naming of people, machines and objects in each section of the road space, and the updating paradigm and model of the management rules, specifications and standards of traffic, navigation and early warning of each section of the road space all belong to the event space-time variation law logical paradigm and model;

[0076] The real-time navigation and early warning correlation information is stored, and the expired and invalid storage information is deleted.

[0077] Further, S4 establishes trajectory association and establishes correlation measurement parameters and indexes between pedestrians and vehicles on each section of the road.

[0078] Establish the association of the pedestrian and vehicle information and or its assigned code and or naming and its moving trajectory on each road section, form the pedestrian and vehicle trajectory mapping database;

[0079] The pedestrian and vehicle trajectory is collected by the camera sensing device of the corresponding road section and or uploaded by the camera sensing mobile phone and tablet device of the pedestrian and vehicle, and the distributed named navigation pedestrian and vehicle early warning system;

[0080] The distributed named navigation pedestrian and vehicle early warning system includes using GPS navigation positioning, Beidou navigation positioning, base station positioning, network signal positioning, visual positioning, sensor positioning to obtain the moving trajectory and real-time positioning information of the pedestrian and vehicle on the corresponding road section;

[0081] The moving trajectory obtained by each pedestrian and vehicle in multiple ways is distinguished and represented;

[0082] On each road section, the assigned code and or naming of each pedestrian and vehicle, and its envelope, and the moving trajectory are associated to form the pedestrian and vehicle trajectory matching mapping database;

[0083] The pedestrian and vehicle correlation degree measurement parameters and indexes include but are not limited to trajectory time and place, trajectory line length, trajectory line change speed, trajectory line change acceleration, relative distance between multiple trajectory lines, relative speed between multiple trajectory lines, relative acceleration between multiple trajectory lines, multi-trajectory space correlation number, multi-trajectory space correlation connection structure, multi-trajectory space correlation connection structure density, multi-trajectory space correlation road connection structure density, multi-trajectory space correlation connection structure change trend, multi-trajectory space correlation connection structure change speed, multi-trajectory space correlation connection structure change acceleration;

[0084] The association method and association structure of the data association adopts the decision tree method, matrix method, knowledge graph method, manifold association, and flow space association.

[0085] Further, in S4, all pedestrians and vehicles entering each road section are associated, and the envelopes of each pedestrian and vehicle are connected by connection lines, each pedestrian and vehicle connects all pedestrians and vehicles on the road section, or only connects the surrounding other pedestrians and vehicles;

[0086] The connection line is lengthened or shortened according to the moving status of the pedestrian and vehicle, the length of the connection line forms the relative distance quantitative measurement value between the pedestrian and vehicle or between the pedestrian and vehicle trajectories, and the length of the connection line and its change are directly determined according to the length of the connection line on the environmental video stream image, or calculated and predicted according to the relative motion speed, relative acceleration, relative position and relative moving trajectory of the associated pedestrian and vehicle;

[0087] As preferred, the length of the connection line in S4 represents the real-time relative distance of the spatiotemporal trajectory, the speed and acceleration of the length of the connection line represents the relative speed and relative acceleration between the associated two parties, and the length of the connection line and its changes are determined directly according to the length of the connection line on the image of the environmental video stream or calculated and predicted according to the actual relative speed, relative acceleration, relative position and relative moving trajectory of the associated two parties;

[0088] As preferred, the distributed named navigation pedestrian and vehicle early warning system in S4 automatically establishes the metric connection line for the pedestrian and vehicle, and the user can also adjust and select the metric connection line with the surrounding vehicles and pedestrians according to the surrounding environment, and the number of connection lines of each pedestrian or each vehicle is the connection degree of the pedestrian or the vehicle;

[0089] As preferred, the pedestrian and vehicle user in S4 interacts with the distributed named navigation pedestrian and vehicle early warning system in real time to achieve the best personalized early warning needs;

[0090] As preferred, the connection line in S4 exists or exists implicitly;

[0091] As preferred, the ratio of the total number of the pedestrian or the vehicle and all the other pedestrians or vehicles connected to it to the area or space volume of the road occupied by the closed loop connection of the most peripheral pedestrian or vehicle in the pedestrian or vehicle and all the other pedestrians or vehicles connected to it is the connection structure density of the pedestrian or the vehicle;

[0092] The correlation metric parameters and indexes include but are not limited to the length of the connection line, the change speed of the connection line, the change acceleration of the connection line, the relative distance, the relative speed, the relative acceleration, the connection degree, the connection structure, the connection structure density, the road connection structure density, the structure change trend, the structure change speed, and the structure change acceleration;

[0093] As preferred, the ratio of the total number of all pedestrians and vehicles on a certain section of road to the area or space volume of the road, or the ratio of the area or space volume of the road occupied by the closed loop connection of the most peripheral pedestrian or vehicle on the road to the area or space volume of the road is the road connection structure density of the road;

[0094] Real-time generation of correlation metric parameters and index values of each pedestrian and each vehicle on each road section and part or all of the road section connection structure density values of pedestrians and vehicles.

[0095] Further, S4 also includes:

[0096] According to the spatio-temporal correlation connection structure diagram between the pedestrians and vehicles, the structure spatio-temporal change trend, the structure spatio-temporal change speed, the structure spatio-temporal change acceleration and other spatio-temporal change correlation measurement parameters and index values, and according to the navigation rules, specifications, standards and / or early warning rules, specifications, standards, the spatio-temporal dynamic map is calculated and generated, the spatio-temporal relative positioning and navigation route of each pedestrian and each vehicle is calculated and generated, the navigation instruction, early warning instruction and event representation, classification and description of each pedestrian and each vehicle are calculated and generated, the spatio-temporal navigation logic paradigm or graph paradigm and the spatio-temporal early warning logic paradigm or graph paradigm of the pedestrians and vehicles are calculated and generated;

[0097] As preferred, in S4, part or all of the people, machines, objects and / or some risk points in the road space are connected and associated by connection lines each time;

[0098] As preferred, the association of people, machines, objects and / or risk points in S4 can be associated across road segments or across road space;

[0099] As preferred, the connection points of the connection lines in S4 are the key points on the surface of the people, machines, objects and / or some risk points, or the key points on the surface of the envelope of the people, machines, objects and / or some risk points, and each connection line connects single or multiple key points on the surface of each person, machine, object and / or some risk point and / or envelope;

[0100] Multiple people, machines and objects are enveloped as a whole and associated with other people, machines, objects and / or other multiple people, machines and objects, and according to the needs, the multiple people, machines and objects are also associated within the whole;

[0101] As preferred, in S4, the distributed named navigation pedestrian and vehicle early warning system automatically associates certain people, machines and objects, and forms a certain dynamic or static geometric shape or shape according to the association, and real-time navigation or early warning of the associated people, machines and objects moving and / or flying according to the moving speed, moving navigation route, moving acceleration and other parameters specified by the distributed named navigation pedestrian and vehicle early warning system, so that the association between the associated people, machines and objects changes according to the predetermined and / or real-time generated dynamic geometric shape or shape changes according to the needs;

[0102] The people, machines and objects can be distributed on different road segments, or on the same road segment, or on different real estate locations, and the people, machines and objects include dynamic and static objects, and the people, machines and objects can be adjacent or not adjacent, and the associated navigation and early warning method is applied in multiple scenarios of navigation, early warning or tracking;

[0103] Further, the distributed naming navigation pedestrian and vehicle early warning system in S4 calculates the road environment condition, the road traffic condition, the road uncertainty factor occurrence condition and the road human, machine and object connection structure change condition through long time learning, forms the logic paradigm and model of the space-time change rule of each section of road environment condition, forms the logic paradigm and model of the space-time change rule of each section of road traffic condition, forms the logic paradigm and model of the space-time change rule of each section of road uncertainty factor occurrence condition, forms the logic paradigm and model of the space-time change rule of each section of road space coding and naming for human, machine and object, forms the updating paradigm and model of the management rule, specification and standard of each section of road space traffic, navigation and early warning, and forms the logic paradigm and model of the space-time change rule of each section of road space connection structure for human, machine and object;

[0104] According to the space-time change rule logic paradigm and model of the connection structure of human, machine and object in each section of road space, the human, machine and object in the corresponding road space are connected and calculated;

[0105] The space-time change rule logic paradigm and model of each section of road traffic condition, the space-time change rule logic paradigm and model of each section of road uncertainty factor occurrence condition, the space-time change rule logic paradigm and model of each section of road space coding and naming for human, machine and object, the updating paradigm and model of the management rule, specification and standard of each section of road space traffic, navigation and early warning, and the space-time change rule logic paradigm and model of the connection structure of human, machine and object in each section of road space all belong to the event space-time change rule logic paradigm and model;

[0106] The real-time navigation early warning association information is stored, and the expired invalid storage information is deleted.

[0107] Further, S4 further includes:

[0108] The road environment space-time contrast measurement parameters and indexes are established according to the road dynamic and static environment space-time data;

[0109] The road meteorological environment space-time contrast measurement parameters and indexes are established according to the road meteorological environment space-time data;

[0110] The human group structure contrast measurement parameters and indexes are established according to the human group structure data;

[0111] The vehicle group structure contrast measurement parameters and indexes are established according to the vehicle group structure data;

[0112] The road connection structure contrast measurement parameters and indexes are established according to the road connection structure data of each section of road;

[0113] The human, machine and object connection structure contrast measurement parameters and indexes are established according to the human, machine and object connection structure data;

[0114] According to the spatiotemporal trajectory data of human, machine, and object clusters, the cluster trajectory data contrast measurement parameters and indicators are established;

[0115] According to the road environment, meteorological environment, and the associated connection structure data of corresponding pedestrian vehicles or independent movement or cluster movement of human, machine, and object, the scene contrast measurement parameters and indicators of the associated spatiotemporal scene of the road environment, meteorological environment, and corresponding pedestrian vehicles or human, machine, and object are established;

[0116] According to the actual trajectory data, the trajectory data contrast measurement parameters and indicators are established, the trajectory contrast measurement parameter and indicator values are inferred by real-time calculation, and the navigation rules, specifications, standards, and / or early warning rules, specifications, standards are calculated to generate spatiotemporal dynamic maps, to cooperatively calculate and generate spatiotemporal relative positioning and navigation routes for each pedestrian and each vehicle, to calculate and generate navigation instructions, early warning instructions, and event representation, classification, and description for each pedestrian and each vehicle, and to calculate and generate spatiotemporal navigation logic paradigms or graph paradigms and spatiotemporal early warning logic paradigms or graph paradigms for pedestrians and vehicles;

[0117] Real-time navigation and early warning associated information is stored, and expired and invalid storage information is deleted.

[0118] Further, the distributed named navigation pedestrian and vehicle early warning system in S5 calculates and navigates and / or warns in real time, including but not limited to:

[0119] Learning, calculating, and cooperatively inferring and predicting generate and update the spatiotemporal change rules, logic paradigms, and models of pedestrian and vehicle navigation and early warning event occurrence;

[0120] Learning, calculating, and cooperatively inferring and predicting generate and update the correlation mode, correlation measurement parameters and indicators, and correlation measurement parameter and indicator calculation logic paradigms and correlation measurement parameter and indicator values between pedestrians and vehicles;

[0121] Learning, calculating, and cooperatively inferring and predicting generate and update the environmental and meteorological conditions;

[0122] Learning, calculating, and cooperatively inferring and predicting generate and update the road environment dynamic conditions;

[0123] Learning, calculating, and cooperatively inferring and predicting generate and update the planning maps for each pedestrian and each vehicle, and real-time update the maps;

[0124] Learning, calculating, and cooperatively inferring and predicting generate and update the relative positioning, navigation paradigms, and navigation routes for each pedestrian and each vehicle;

[0125] Learning, calculating, and cooperatively inferring and predicting generate and update the early warning paradigms and early warning levels for each pedestrian and each vehicle;

[0126] Learning, calculating, and cooperatively inferring and predicting generate and update the early warning event categories, intensities, and evaluation methods;

[0127] Learning computing and reasoning prediction generate and update navigation rules, norms, standards, etc. and early warning rules, norms, standards, etc.

[0128] Learning computing and reasoning prediction generate and update navigation instructions and early warning instructions.

[0129] Learning computing and reasoning prediction system and inter-system security failure points and security weak points, generate and update real-time collaborative security computing paradigm.

[0130] Further, the learning computing and reasoning prediction generation and update technology in S5 includes various intelligent learning computing technologies, including mapping learning, traversal learning, reinforcement learning, statistical learning, contrast learning, inductive learning, adversarial learning, deep neural network learning, federated learning, distributed learning, Transformer model, probability learning, evolutionary learning, instruction learning, association learning, event spatio-temporal model learning.

[0131] Further, according to the results of learning computing and reasoning prediction generation in S5, compare navigation rules, norms, standards and or early warning rules, norms, standards, and determine decision to generate map, update map, relative positioning, navigation route, navigation instruction, early warning level, early warning instruction, event representation classification and description information.

[0132] Further, the event spatio-temporal model learning refers to learning the spatio-temporal variation law of events, which can calculate and infer the model, logical paradigm, state curve, geometric structure, dynamic characteristics, diffusion efficiency transfer metric paradigm, knowledge language semantic atlas, etc. of the spatio-temporal variation of the associated events, and on this basis, further intelligent association learning can deduce and generate higher-level event spatio-temporal variation law model of intelligent science and technology;

[0133] The instruction learning refers to learning and understanding the instruction language, which can infer the semantics, logic and execution process of the instruction, and can generate new reliable and available instructions based on the decision of the intelligent science and technology. Instruction language includes text language, voice language, symbol language, image language, video stream language, multi-modal language, etc.

[0134] The association learning includes according to the knowledge resource library, through the semantic understanding of data, according to the association relationship between semantic concepts and semantic connotations, the data is represented and processed in space and time, the data automatic classification, standardization and standardization process is executed, the data association network flow space is automatically constructed, the intelligent navigation data mapping knowledge graph and resource library is formed, and according to the data association relationship and data association degree measurement method, the data spatio-temporal variation logic paradigm or graph paradigm and the data association event spatio-temporal variation logic paradigm or graph paradigm are automatically generated.

[0135] The application also discloses a distributed named navigation pedestrian and vehicle warning device, which comprises one module or two module combination integrations or multiple module combination integrations or all module combination integrations of input modules, output modules, safety calculation processing modules, navigation warning control modules, navigation warning event management modules, storage modules, map modules, environment and meteorological modules, road environment modules, pedestrian modules, vehicle modules, trajectory modules, correlation modules, visualization modules, hardware management modules, software management modules, language and image knowledge base modules, navigation language translation NaviT modules, network connection control modules, road and real estate correlation knowledge database or cloud modules and Web interactive operating system modules in the distributed named navigation pedestrian and vehicle warning system.

[0136] Each device can be used alone or interconnected to form a new device.

[0137] The device can be embedded in the distributed named navigation pedestrian and vehicle warning system or embedded in the Internet.

[0138] Further, the distributed named navigation pedestrian and vehicle warning device comprises at least one processor and a memory.

[0139] The memory stores computer execution instructions.

[0140] The at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the above-mentioned distributed named navigation pedestrian and vehicle warning method.

[0141] The application also discloses a distributed named navigation pedestrian and vehicle warning chip, which comprises various types of chips designed according to the data collection, calculation, transmission, control and correlation processing methods of each module of input modules, output modules, safety calculation processing modules, navigation warning control modules, navigation warning event management modules, storage modules, map modules, environment and meteorological modules, road environment modules, pedestrian modules, vehicle modules, trajectory modules, correlation modules, visualization modules, hardware management modules, software management modules, language and image knowledge base modules, navigation language translation NaviT modules, network connection control modules, road and real estate correlation knowledge database or cloud modules and Web interactive operating system modules in the distributed named navigation pedestrian and vehicle warning system.

[0142] The application also discloses a distributed naming navigation pedestrian and vehicle early warning correlation chip, a correlation processor or a correlation device, which comprises all correlation chips, correlation processors or correlation devices integrated with multiple units or all units, including an input unit, an output unit, a correlation control unit, a correlation calculation unit, a correlation learning unit, a correlation metric parameter and index unit, a correlation topology structure unit, a correlation storage unit, a correlation decision generation unit and a network connection control unit.

[0143] The input unit is responsible for inputting known correlation data of events for which the correlation chip, the correlation processor or the correlation device is responsible for reasoning calculation and or generation, and a safe processing method, such as pedestrian and vehicle video streams, graphical images, pedestrian and vehicle trajectory data, road environment data, environmental meteorological data, pedestrian and vehicle navigation or early warning requirements in each road space;

[0144] The output unit is responsible for outputting correlation data of events for which the correlation chip, the correlation processor or the correlation device is responsible for reasoning calculation and or generation, and a safe processing decision for navigation and or early warning;

[0145] The correlation control unit is responsible for rules, specifications and or standards of events for which reasoning calculation and or generation is required, and a safe processing method, controls and adjusts the interconnection and intercommunication of each unit of the correlation chip, the correlation processor or the correlation device, and the safe processing method of each unit;

[0146] The correlation calculation unit is responsible for correlation logic operation and result data of events for which reasoning calculation and or generation is required according to navigation and or early warning rules and standards, including fusion, evaluation and encryption and decryption of various safe calculations;

[0147] The correlation learning unit is responsible for learning and prediction calculation of the space-time variation law of correlation events, such as traffic conditions, road environment conditions, environmental meteorological conditions, connection structure conditions, map construction conditions, path planning conditions, relative positioning conditions, navigation route conditions, early warning event conditions and safe calculation methods in each time period of each road space;

[0148] The correlation metric parameter and index unit is responsible for selection, generation and update of metric parameters and indexes of events for which reasoning calculation and or generation is required;

[0149] The association topology unit is responsible for the generation, ordering, comparison and inference calculation and security processing of the association topology of the calculated events, such as the connection topology of pedestrians and vehicles, the connection topology of people, machines and objects on the road, the connection topology of each section of road and the road connected thereto and the surrounding real estate, the map collaborative construction topology, the matching mapping topology of the code and or naming of pedestrians and vehicles and the trajectory and envelope of pedestrians and vehicles, the input module corresponding interface and or device connection topology of the distributed named navigation pedestrian and vehicle warning system, the output module corresponding interface and or device connection topology of the distributed named navigation pedestrian and vehicle warning system, and the network transmission routing topology.

[0150] The association storage unit is responsible for storing the association data, association computing power and association model information of each unit of the association chip, the association processor or the association device.

[0151] The association generation decision unit is responsible for generating navigation and or warning and association event decision information and or decision instructions according to the calculation results and navigation and or warning rules and standards. The decision information can be relative positioning information, navigation route information, map construction and update, warning category, level and instruction, event evaluation method, rule, standard and result, and new navigation and or warning rule, standard, mode and method.

[0152] The network connection control unit is responsible for connection with various types of networks, information interaction with the Internet, connection control of various API interfaces, network status calculation, connection protocol design and security processing of information network transmission.

[0153] The distributed named navigation pedestrian and vehicle warning association chip, the association processor or the association device can perform spatio-temporal multi-dimensional multi-modal data parallel collaborative calculation and output, or single-dimensional single-modal data independent calculation and output.

[0154] The application also discloses an association collaborative computing model of a distributed named navigation pedestrian and vehicle warning system, which comprises:

[0155] Through the collaborative calculation of meteorological environment, pedestrian and vehicle, road environment data of each road section, the road connection structure, path planning and real-time map information data are inferred, and through the collaborative calculation of road connection structure, path planning and real-time map data, the relative positioning of people, machines and objects, and the associated map of connection structure and real-time map information data are inferred, and through the collaborative calculation of relative positioning of people, machines and objects, and the associated map of connection structure and real-time map data, the information data of early warning decision evaluation, associated event management, pedestrian and vehicle trajectory and navigation route are inferred, which are fed back to each step of collaborative calculation in real time to help infer the data results after each step of collaborative calculation, forming a navigation and early warning associated data deep perception cognitive closed-loop flow space.

[0156] The early warning decision evaluation includes early warning decision information and evaluation information of the early warning decision information.

[0157] The associated event management includes associated event information and management information of the event, and the associated event includes various types of determined events and uncertain events on each road section, including navigation events and early warning events, including the distributed named navigation pedestrian and vehicle early warning system or network security event.

[0158] The associated collaborative calculation model is realized by chip cluster collaborative calculation, or by processor cluster collaborative calculation, or by chip and processor joint cluster collaborative calculation.

[0159] The association data of the association collaborative computing model comprises current meteorological environment of each road section, time and space variation law of meteorological environment of each road section, time and space logic paradigm and graph paradigm of meteorological environment of each road section, current static environment of each road section, time and space variation law of static environment of each road section, time and space logic paradigm and graph paradigm of static environment of each road section, current dynamic environment of each road section, time and space variation law of dynamic environment of each road section, time and space logic paradigm and graph paradigm of dynamic environment of each road section, current pedestrian and vehicle of each road section, time and space variation law of pedestrian and vehicle of each road section, time and space logic paradigm and graph paradigm of pedestrian and vehicle of each road section, current connection structure of each road section, time and space variation law of connection structure of each road section, time and space logic paradigm and graph paradigm of connection structure of each road section, current path planning and real-time map of each road section, time and space variation law of path planning and real-time map of each road section, time and space logic paradigm and graph paradigm of path planning and real-time map of each road section, current relative positioning of pedestrian and vehicle of each road section, time and space variation law of relative positioning of pedestrian and vehicle of each road section, time and space logic paradigm and graph paradigm of relative positioning of pedestrian and vehicle of each road section, current association map of connection structure and real-time map, time and space variation law of association map of connection structure and real-time map, time and space logic paradigm and graph paradigm of association map of connection structure and real-time map, current early warning decision evaluation of each road section, time and space variation law of early warning decision evaluation of each road section, time and space logic paradigm and graph paradigm of early warning decision evaluation of each road section, current pedestrian and vehicle trajectory of each road section, time and space variation law of pedestrian and vehicle trajectory of each road section, time and space logic paradigm and graph paradigm of pedestrian and vehicle trajectory of each road section, current association event management of each road section, time and space variation law of association event management of each road section, time and space logic paradigm and graph paradigm of association event management of each road section, current navigation route of each road section, time and space variation law of navigation route of each road section, time and space logic paradigm and graph paradigm of navigation route of each road section.

[0160] Compared with the prior art, the application has the advantages that:

[0161] The risk early warning analysis and prediction of the pedestrian and vehicle can be automatically performed, the event situation that may cause a safety hidden danger is timely evaluated and warned, the probability of accidents of the pedestrian and vehicle is greatly reduced, the traffic safety and the legal rights and interests of the user are protected, the efficiency of data transmission processing is improved, the transmission data amount is reduced, the system and / or network energy consumption is effectively reduced, and the precision, real-time performance and safety and reliability of the navigation, tracking and early warning and the like are enhanced. BRIEF DESCRIPTION OF DRAWINGS

[0162] Figure 1 A flowchart of a distributed naming navigation pedestrian and vehicle early warning method provided by the embodiment of the application is shown in the figure.

[0163] Figure 2The schematic diagram of road and real estate classification, partition and segmentation for the distributed named navigation pedestrian and vehicle early warning method provided by the embodiment of the present application Figure 1 ;

[0164] Figure 3 The schematic diagram of road and real estate classification, partition and segmentation for the distributed named navigation pedestrian and vehicle early warning method provided by the embodiment of the present application Figure 2 ;

[0165] Figure 4 The schematic diagram of the distributed named navigation pedestrian and vehicle early warning system provided by the embodiment of the present application

[0166] Figure 5 The schematic diagram of the distributed named navigation pedestrian and vehicle early warning cluster coordination system provided by the embodiment of the present application

[0167] Figure 6 The schematic diagram of pedestrian and vehicle envelope, respectively, coding and naming for the distributed named navigation pedestrian and vehicle early warning method provided by the embodiment of the present application

[0168] Figure 7 The schematic diagram of pedestrian and vehicle association and association measurement parameter and index for the distributed named navigation pedestrian and vehicle early warning method provided by the embodiment of the present application Figure 1 ;

[0169] Figure 8 The schematic diagram of pedestrian and vehicle association and association measurement parameter and index for the distributed named navigation pedestrian and vehicle early warning method provided by the embodiment of the present application Figure 2 ;

[0170] Figure 9 The schematic diagram of pedestrian and vehicle association and association measurement parameter and index for the distributed named navigation pedestrian and vehicle early warning system provided by the embodiment of the present application Figure 3 ;

[0171] Figure 10 The schematic diagram of the distributed named navigation pedestrian and vehicle early warning system association and collaborative calculation model provided by the embodiment of the present application

[0172] Figure 11 The schematic diagram of the distributed named navigation pedestrian and vehicle early warning system data deep perception cognitive association flow space provided by the embodiment of the present application

[0173] Figure 12 The schematic diagram of the distributed named navigation pedestrian and vehicle early warning association chip structure provided by the embodiment of the present application Figure 1 ;

[0174] Figure 13 The schematic diagram of the distributed named navigation pedestrian and vehicle early warning association chip structure provided by the embodiment of the present application Figure 2 ;

[0175] Figure 14 The distributed named navigation pedestrian vehicle warning correlation chip structure diagram provided for the embodiment of the present application Figure 3 ;

[0176] Figure 15 The aerial robot correlation warning diagram of the distributed named navigation pedestrian vehicle warning system provided for the embodiment of the present application

[0177] Figure 16 The pedestrian tracking and identification diagram according to the naming of the distributed named navigation pedestrian vehicle warning system provided for the embodiment of the present application

[0178] Figure 17 The hardware structure diagram of the distributed named navigation pedestrian vehicle warning device provided for the embodiment of the present application DETAILED DESCRIPTION

[0179] In order to make the purpose, technical scheme and advantages of the present application more clear and explicit, the present application is further described in detail below according to the drawings and examples.

[0180] As shown in Figure 1 , a distributed named navigation pedestrian vehicle warning method comprises the following steps:

[0181] S1, classify, zone and segment the road, classify and fragment the real estate, associate the road with the surrounding real estate, and construct a map and a knowledge base;

[0182] As shown in Figure 2 , it is only an embodiment of the classification, zoning and segmentation of one kind of road and real estate, and the present application is not limited to this embodiment. A suitable and reasonable classification, zoning and segmentation method can be selected according to the actual situation;

[0183] S11, encode and / or name the classification, zoning and segmentation of the road, and digitize it with images, video streams, text descriptions, etc.;

[0184] S12, encode and / or name the classification and fragmentation of the real estate, and digitize it with images, video streams, text descriptions, etc.;

[0185] S13, associate each segment of the road with its surrounding real estate, and establish correlation measurement parameters and indexes;

[0186] The association of each segment of the road with its surrounding real estate can be established by connecting with geographical geometric figures, or by describing with words and languages. The correlation measurement parameters and indexes can include distance, direction, pedestrian and vehicle space-time flow, pedestrian and vehicle travel frequency, various space-time attribute characteristics of pedestrian and vehicle and pedestrian and vehicle clusters, etc.

[0187] S14, associate each section of road with each section of road connected thereto and establish association measurement parameters and indexes;

[0188] The association of each section of road with each section of road connected thereto can be established by geographical geometric connection or by language description, and the association measurement parameters and indexes can include connection direction, distance, pedestrian and vehicle space-time flow, pedestrian and vehicle transfer probability, pedestrian and vehicle travel frequency, and various space-time attribute characteristics of pedestrian and vehicle clusters;

[0189] S15, update the map according to the association relationship between each section of road and real estate and its space-time change and the prediction and calculation of the vehicle;

[0190] Associating roads with surrounding real estate to build a map and a knowledge base also includes each section of road and its connected roads, as well as all people, machines, and objects in the surrounding real estate and environment, which can be mutually referenced. According to the mutual association and / or reference, a map and path planning can be constructed by multiple parties;

[0191] For example, Figure 3 According to the association between each section of road and the association between each section of road and real estate, and its space-time change and the traffic flow of vehicles, pedestrians and vehicles, a plurality of paths and / or routes of real estate A1 can be calculated by reasoning, and the best route can be selected by decision-making planning;

[0192] Encrypt and decrypt the coding and / or naming and feature information of roads and real estate;

[0193] Visualize or simulate the roads and real estate and their space-time change conditions, and establish a road and real estate knowledge database or cloud.

[0194] S2, establish a distributed named navigation pedestrian and vehicle early warning system;

[0195] Use servers, base stations, gateways, routers, switches, sensors, cameras, radars, etc. to establish a distributed named navigation pedestrian and vehicle early warning network system;

[0196] According to the classification and segmentation of roads, the distributed early warning network system is blockchained;

[0197] According to the classification and segmentation of roads, the distributed named navigation pedestrian and vehicle early warning network system adopts a gateway cluster architecture to establish collaboration, and can also adopt a named data network security architecture that combines naming and addressing;

[0198] ​The distributed naming navigation pedestrian and vehicle early warning network system can be a 4G network system, a 5G network system, a space-air-ground integrated satellite network system, a quantum network system, a new generation of Internet network system, and the like, and the present application is not limited thereto.

[0199] As shown in Figure 4 The establishment of the distributed naming navigation pedestrian and vehicle early warning system further comprises:

[0200] The early warning system comprises an input module, an output module, a safety calculation processing module, a navigation early warning control module, a navigation early warning event management module, a storage module, a map module, an environmental and meteorological module, a road environment module, a pedestrian module, a vehicle module, a trajectory module, a correlation module, a visualization module, a hardware management module, a software management module, a language and image knowledge base module, a navigation language translation NaviT module, a network connection control module, a road and real estate correlation knowledge database or cloud module, and a Web interactive operating system module.

[0201] The modules are interconnected, and the modules can be divided into multiple different processing units, which can be physically isolated and / or virtually isolated. The modules and units can be distributed in different servers or clouds of a network, or integrated in the same device. Each module and unit can have a cache area according to efficiency and data conditions. The input module and input unit, and the output module and output unit can be embedded and integrated into other modules, or interconnected with other modules.

[0202] The establishment of the distributed naming navigation pedestrian and vehicle early warning system further comprises:

[0203] The input module is mainly responsible for collecting information for navigation and early warning, including various sensors, radars, cameras, network interfaces, intelligent devices, and the like.

[0204] The output module is mainly responsible for transmitting various navigation and early warning information after processing to corresponding users, terminals, devices, interfaces, and the like.

[0205] The safety calculation processing module is mainly responsible for trajectory comparison calculation, road environment obstacle avoidance and risk avoidance calculation, meteorological prediction calculation, path planning calculation, event space-time change rule logic calculation, correlation learning calculation, video stream compression and encoding calculation, network transmission processing, various information and data security processing and encryption and decryption calculation, and the like, according to various intelligent learning and / or intelligent calculation processing technologies.

[0206] The navigation early warning control module is mainly responsible for mutual communication between modules, and forms navigation information instructions and early warning information instructions according to interactive information, rule specification standards, calculation results, and the like, and evaluates, classifies, and grades, and issues navigation instructions and / or early warning instructions to pedestrians and / or vehicles.

[0207] Navigation early warning event management module: mainly responsible for evaluating and classifying specific navigation events and early warning events, establishing event data logical model, etc. to form event mapping database and calculate statistics, etc. for various learning calculations;

[0208] Storage module: mainly responsible for storing data, rules, algorithms, models, strategies, etc. of various modules, and storing them in a hierarchical, block and object manner, and setting effective period and refreshing and clearing invalid data in time according to usage, importance, etc.;

[0209] Map module: mainly responsible for calculating and generating and updating map, route, road sign, etc. information, responsible for calculating and generating real-time dynamic path planning information, navigation route scheduling information, etc. of each pedestrian and each vehicle, including various levels of electronic map, virtual reality map and mixed reality map and associated matching mapping data information;

[0210] Environmental meteorological module: mainly responsible for collecting, detecting, identifying, classifying, standardizing and processing real-time environmental meteorological information data, and predicting and calculating environmental meteorological information, etc.;

[0211] Road environment module: mainly responsible for collecting, detecting, identifying, classifying, standardizing and processing real-time road environment information data, road classification, segmentation and zoning, and predicting and planning mobile route, etc.;

[0212] Pedestrian module: mainly responsible for pedestrian identification classification labeling, pedestrian coding and decoding, naming and eliminating naming, pedestrian statistical calculation, pedestrian space-time flow change law calculation, and registration, identity authentication, user and system interaction, such as publishing navigation or early warning requirements, etc. The pedestrian identification classification labeling includes identification classification labeling according to pedestrian coding, naming, clothing, appearance, age, shape, action, etc. characteristic attribute, also includes identification classification labeling according to pedestrian cluster structure, density, number of people, behavior, clothing, age and cluster team activity type, etc. crowd characteristic attribute, also includes pedestrian identification classification labeling according to human, machine and object interaction relationship characteristic attribute;

[0213] Vehicle module: mainly responsible for vehicle identification classification labeling, vehicle coding and decoding, naming and eliminating naming, vehicle statistical calculation, vehicle space-time flow change law calculation, and registration, vehicle authentication, user and system interaction, such as publishing navigation or early warning requirements, etc. The vehicle identification classification labeling includes identification classification labeling according to vehicle coding, naming, color, brand, license plate number, shape, moving or flying speed, etc. characteristic attribute, also includes identification classification labeling according to vehicle cluster structure, density, number of vehicles, moving or flying speed and cluster team activity type, etc. vehicle team characteristic attribute, also includes vehicle identification classification labeling according to human, machine and object interaction relationship characteristic attribute, and the vehicle authentication includes vehicle identity authentication, vehicle owner authentication and vehicle user authentication, and association of various authentication data information and vehicle;

[0214] The trajectory module is mainly responsible for collecting the real-time movement trajectories of pedestrians and vehicles, and forming a pedestrian and vehicle trajectory map.

[0215] The association module is mainly responsible for establishing associations between roads, weather, environment, maps, pedestrians, vehicles, trajectories, etc. It performs association calculations based on association measurement parameters and indicators, as well as traffic rules, navigation rules, early warning rules, etc., and obtains various association data results in real time. At the same time, it establishes data association flow processes and knowledge graphs, and stores and updates association data, association logic, association models and other information.

[0216] Visualization module: mainly responsible for visualizing and displaying maps, road conditions, weather, tracks, pedestrians, vehicles, and related conditions on various screens or in the real air, and matching and mapping virtual and real data.

[0217] Hardware Management Module: Primarily responsible for the adjustment, inspection, maintenance, and intelligent computing safety early warning of various hardware components in the navigation and early warning system;

[0218] Software management module: mainly responsible for the adjustment, inspection, maintenance, and intelligent computing safety early warning of various software in the navigation and early warning system;

[0219] The language and image knowledge base module mainly classifies and stores navigation and early warning information data and related information data, including various types of language, speech, text, images, symbols, curves, structures, logic, etc., and there are mutual matching and association mapping between language, speech, text, images, symbols, curves, structures, logic, etc.

[0220] The NaviT navigation language translation module, based on a language image knowledge base, primarily combines intelligent technologies such as Transformer models and / or CNN models, and / or traversal learning, reinforcement learning, / statistical learning, and / or contrastive learning to handle the mutual translation and conversion of multimodal navigation information data. It is responsible for generating navigation commands, warning commands, map information, path planning information, annotation information, and parameter information. The mutual translation and conversion of multimodal navigation information data includes the translation and conversion between video streams, images, video stream languages, image languages, quantum languages, various types of natural languages, symbolic languages, various machine languages, various code languages, text, and speech, matching the system and user's needs accordingly.

[0221] Network connectivity control module: mainly responsible for network connectivity of various modules and units, interface management, network detection, network status calculation, connection protocol design, network information encryption and decryption calculation, security early warning, etc.

[0222] Road and real estate association knowledge database or cloud module: mainly responsible for digitizing, visualizing or simulating road and real estate and their spatio-temporal change conditions, and representing the calculation of the association relationship, association measurement parameters and indicators of road and real estate, forming the spatio-temporal association logic paradigm and model of each road segment and its connected road segments and surrounding real estate, and calculating and constructing and updating various scale maps;

[0223] Web interactive operating system module: mainly responsible for the safe information interaction between pedestrians and vehicles and each module of the system, such as publishing navigation or early warning requirements, and responsible for the safe information interaction between pedestrians and vehicles, and responsible for the safe information interaction between pedestrians and vehicles on each road segment, and also includes the interaction between various types of users such as people, machines and objects, and the interaction between various types of users and the distributed named navigation pedestrian and vehicle early warning system. Each road segment interaction group and or several road segment interaction groups can be established, pedestrians and vehicles entering the corresponding road segment automatically enter the corresponding road segment interaction group, and pedestrians and vehicles moving out of the corresponding road segment automatically exit the corresponding road segment interaction group. Based on the real-time map of the corresponding road segment, the interaction group can establish real-time information interaction, and the pedestrians and vehicles corresponding to the road segment can establish association at the corresponding position of the real-time map at the same time. Pedestrians and vehicles can also conduct real-time information interaction at the same time. The setting of the interaction group can expand and improve the corresponding function according to the actual spatio-temporal demand.

[0224] The establishment of the distributed named navigation pedestrian and vehicle early warning system also includes:

[0225] Each module forms a spatio-temporal neural network learning mechanism small model according to the association historical data and other information, and each module is connected to form a network, forming a spatio-temporal navigation NaviGPT or navigation intelligent agent and various types of navigation early warning API;

[0226] According to the corresponding neural network model of each module, the corresponding programmable and or software defined chip and or processor are designed and developed.

[0227] S3, classify and type pedestrians and vehicles respectively, and assign codes and or names to pedestrians and vehicles entering each road segment;

[0228] Pedestrians and vehicles can be collected by corresponding road segment camera sensing devices in real time and transmitted to each demand module of the distributed named navigation pedestrian and vehicle early warning system, and or pedestrians and vehicles can be collected by their own camera sensing mobile phone and tablet devices in real time and transmitted to each demand module of the distributed named navigation pedestrian and vehicle early warning system, and or pedestrians and vehicles can be registered on the display page such as web page or APP of the distributed named navigation pedestrian and vehicle early warning system; wherein the camera sensing devices of each road segment also include the camera sensing devices of each road segment air mobile platform and or some third party observation or observation equipment;

[0229] Pedestrian and vehicle envelope is to automatically configure appropriate envelope geometry image for each pedestrian and vehicle according to their shape, size and other characteristics. Envelope geometry image refers to using computer vision technology and machine learning algorithm to automatically generate appropriate envelope geometry image according to the characteristic data of various pedestrians and vehicles, so as to more accurately represent the warning and protection range of each pedestrian and vehicle. The pedestrians and vehicles are respectively enveloped by using geometric shape image. The appearance shape and volume size of the enveloped geometric image are generally not less than the actual shape and volume size of the pedestrians and vehicles, and the envelope color can be set according to relevant regulations, rules and specifications;

[0230] Each road section space can also be enveloped, and the envelope shape, size, color and the like can be set according to actual needs;

[0231] Enveloping is for safer warning. In actual application, according to needs, it is not required to be enveloped. Whether to envelop can be selected according to road section, environment, specification standard and the like, and the shape, size, color of the envelope and the range and time period of the enveloped pedestrian and vehicle itself and road section space can be selected;

[0232] The system can automatically configure appropriate envelope geometry image for each road section and pedestrian and vehicle on each road section, and the user can also adjust the size of the envelope geometry image and the part of the envelope in real time according to the needs;

[0233] According to the road segmentation condition, the road segmentation includes the basis for separating in the road environment module of the distributed navigation pedestrian and vehicle warning system, such as geographical position, geographical coordinates, special reference and the like.

[0234] The pedestrians and vehicles entering each road section are immediately classified, coded and or named, and the code and or name on the road section is uniformly used on the road section. When the pedestrians and vehicles move out of the road section, the code and or name is automatically invalidated and cleared. When entering another road section, the pedestrians and vehicles are re-coded and or named, and when moving out of the road section, the code and or name is automatically invalidated and cleared.

[0235] According to actual needs, a set of unified name can be used for pedestrians and vehicles on multiple continuous road sections without renaming in between, but each road section can be re-coded, that is, each pedestrian and vehicle can use one name and or one or more codes on multiple continuous road sections.

[0236] According to actual needs, a set of unified code and or name can also be used for multiple continuous road sections without re-coding and or naming in between, that is, each pedestrian and vehicle can use multiple names and or multiple codes on multiple continuous road sections.

[0237] The code assignment and / or naming can be pre-assigned before a pedestrian or vehicle enters a certain section of the road for a certain period of time, avoiding the problem of excessive pedestrians or vehicles entering a certain section of the road for a certain period of time, and the burden of code assignment and / or naming, that is, allowing the code assignment and / or naming on the section of the road to exist simultaneously with the code assignment and / or naming on the next section of the road for a certain period of time, including code assignment and / or naming according to the ordered coding rule, code assignment and / or naming according to the unordered coding rule, and code assignment and / or naming according to the encryption and decryption coding rule;

[0238] Each section of the road can use the same code assignment and / or naming mechanism, or different code assignment and / or naming mechanisms can be used, and multiple sets of code assignment and / or naming mechanisms can be set according to different entrances and moving directions on the same section of the road;

[0239] Code assignment and / or naming is automatically completed by the distributed naming navigation pedestrian and vehicle warning system in real time according to real-time information collected by pedestrians and vehicles, and pedestrians and vehicles cannot modify or adjust the code assignment and / or naming;

[0240] The distributed naming navigation pedestrian and vehicle warning system can associate and match the code assignment and / or naming of each section of the road with the registration information and / or historical association information of the pedestrian and vehicle;

[0241] The distributed naming navigation pedestrian and vehicle warning system can identify pedestrians and vehicles through pedestrian and vehicle feature detection, and can identify pedestrians and vehicles through the interconnection and sharing of pedestrian and vehicle information between road sections, and can establish the association and matching mapping of each pedestrian and vehicle with each section and the code assignment and / or naming;

[0242] According to the actual situation, each code assignment and / or naming on each section of the road can include part or all of the people, machines, and objects in the road space;

[0243] The code assignment and / or naming of people, machines, and objects in each section of the road and its space can be periodically re-circulated for a certain period of time, or different rules and mechanisms can be used to re-assign and / or name people, machines, and objects in the corresponding road space;

[0244] The length of the time period for code assignment and / or naming in each section of the road and its space can be adjusted and updated in a timely manner according to road environmental conditions, road traffic conditions, and other factors;

[0245] Through long-term learning of road environment conditions, road traffic conditions, and road uncertainty factor occurrence, form the logical paradigm and model of the space-time variation law of each section of the road environment conditions, the space-time variation law of each section of the road traffic conditions, the space-time variation law of each section of the road uncertainty factor occurrence, the space-time variation law of each section of the road space coding and or naming of people, machines and objects, and the update paradigm and model of the management rules, specifications and standards of traffic, navigation and early warning of each section of the road space;

[0246] According to the space-time variation law of each section of the road space coding and or naming of people, machines and objects, the coding and or naming of people, machines and objects in each section of the road space is carried out;

[0247] The space-time variation law of each section of the road space coding and or naming of people, machines and objects, and the other characteristic attributes of the people, machines and objects are combined to track and identify and authenticate the people, machines and objects, and the complex scene of the people, machines and objects cluster is tracked and identified, classified, and the space-time tracking identification, identity authentication and relationship identification of each pedestrian, each vehicle and each object are carried out.

[0248] The space-time variation law of each section of the road traffic conditions, the space-time variation law of each section of the road uncertainty factor occurrence, the space-time variation law of each section of the road space coding and or naming of people, machines and objects, and the update paradigm and model of the management rules, specifications and standards of traffic, navigation and early warning of each section of the road space all belong to the logical paradigm and model of event space-time variation law.

[0249] The real-time navigation and early warning related information is stored, and the expired and invalid storage information is deleted.

[0250] S104, the trajectory association between pedestrians and vehicles on each section of the road is established, and the correlation measurement parameters and indexes are established.

[0251] The association between the pedestrian and vehicle information and or its assigned code and or name and its moving trajectory on each section of the road is established, and a pedestrian and vehicle trajectory mapping database is formed.

[0252] The pedestrian and vehicle trajectory can be collected and uploaded to the distributed named navigation pedestrian and vehicle early warning system by corresponding road section camera sensing devices, and or the pedestrian and vehicle can collect and upload to the distributed named navigation pedestrian and vehicle early warning system by their own camera sensing mobile phones, tablets and other devices; wherein the camera sensing devices of each road section also include the camera sensing devices of each road section air mobile platform and or some third party observation or observation equipment;

[0253] The distributed naming navigation pedestrian and vehicle early warning system includes obtaining pedestrian and vehicle movement trajectories and real-time positioning information of corresponding road sections by using GPS navigation positioning, Beidou navigation positioning, base station positioning, network signal positioning, visual positioning, sensor positioning, etc.

[0254] The movement trajectories obtained by each pedestrian and each vehicle in multiple ways are distinguished and represented, such as different line shapes, different color line types, etc.

[0255] On each road section, the codes and / or names of each pedestrian and each vehicle, as well as their envelopes, are associated with their movement trajectories to form a pedestrian and vehicle trajectory matching mapping database.

[0256] The pedestrian and vehicle correlation measurement parameters and indexes include, but are not limited to, trajectory time and location, trajectory line length, trajectory line change speed, trajectory line change acceleration, relative distance between multiple trajectory lines, relative speed between multiple trajectory lines, relative acceleration between multiple trajectory lines, multi-trajectory space correlation number, multi-trajectory space correlation connection structure, multi-trajectory space correlation connection structure density, multi-trajectory space correlation road connection structure density, multi-trajectory space correlation connection structure change trend, multi-trajectory space correlation connection structure change speed, and multi-trajectory space correlation connection structure change acceleration.

[0257] The correlation method and correlation structure of the data correlation adopt decision tree method, matrix method, knowledge graph method, manifold correlation, and flow space correlation, etc.

[0258] The trajectory correlation and correlation measurement parameters and indexes between pedestrians and vehicles on each road section also include: establishing correlation for all pedestrians and vehicles entering each road section, connecting the envelopes of each pedestrian and vehicle with connection lines, and each pedestrian and vehicle can be connected to all pedestrians and vehicles on the road section, or only connected to other pedestrians and vehicles in the vicinity.

[0259] The connection lines are extended or shortened according to the movement status of the pedestrians and vehicles, the length of the connection lines forms the relative distance quantitative measurement value between the pedestrians and vehicles or between the trajectories of the pedestrians and vehicles, and the length of the connection lines and its changes are directly determined according to the length of the connection lines on the environmental video stream image, or calculated and predicted according to the relative motion speed, relative acceleration, relative position, and relative movement trajectory of the correlated pedestrians and vehicles.

[0260] The length of the connection lines represents the real-time relative distance of the space-time trajectory, the speed and acceleration of the extension or shortening of the connection lines represent the relative speed and relative acceleration between the correlated parties, and the length of the connection lines and its changes are directly determined according to the length of the connection lines on the environmental video stream image, or calculated and predicted according to the actual relative speed, relative acceleration, relative position, and relative movement trajectory of the correlated parties.

[0261] The distributed named navigation pedestrian vehicle early warning system automatically establishes a metric connection line for each pedestrian vehicle, and the user can also adjust and select which pedestrians and vehicles to establish a metric connection line according to the surrounding environment, and the number of connection lines for each pedestrian or each vehicle is the connection degree of the pedestrian or the vehicle;

[0262] The pedestrian vehicle user can interact with the distributed named navigation pedestrian vehicle early warning system in real time to achieve the best personalized early warning;

[0263] The connection line can be displayed or implicitly exist;

[0264] The ratio of the total number of pedestrians and vehicles on a certain road segment to the area or spatial volume of the road segment, or the ratio of the area or spatial volume of the road segment connected by the outermost closed loop of pedestrians and vehicles on the road segment, is the road connection structure density of the road segment;

[0265] The correlation metric parameters and indicators include but are not limited to connection line length, connection line change speed, connection line change acceleration, relative distance, relative speed, relative acceleration, connection degree, connection structure, connection structure density, road connection structure density, structure change trend, structure change speed, and structure change acceleration;

[0266] The ratio of the total number of pedestrians and vehicles on a certain road segment to the area or spatial volume of the road segment, or the ratio of the area or spatial volume of the road segment connected by the outermost closed loop of pedestrians and vehicles on the road segment, is the road connection structure density of the road segment;

[0267] Real-time generation of correlation metric parameter and indicator values for each pedestrian and each vehicle on each road segment, and partial or all road segment pedestrian vehicle road connection structure density values.

[0268] The establishment of trajectory correlation and the establishment of correlation metric parameters and indicators between pedestrians and vehicles on each road segment also include:

[0269] According to the spatio-temporal correlation connection structure diagram, the structure spatio-temporal change trend, the structure spatio-temporal change speed, the structure spatio-temporal change acceleration, and other spatio-temporal change correlation metric parameter and indicator values, and according to the navigation rules, specifications, standards, etc. and / or early warning rules, specifications, standards, etc., calculate and plan to generate a spatio-temporal dynamic map, calculate and plan to generate the spatio-temporal relative positioning and navigation route of each pedestrian and each vehicle, calculate and plan to generate the navigation instructions, early warning instructions, and event representation, classification, and description of each pedestrian and each vehicle, and calculate and plan to generate the spatio-temporal navigation logic paradigm or graph paradigm and the spatio-temporal early warning logic paradigm or graph paradigm of pedestrians and vehicles;

[0270] According to actual needs, part or all of people, machines, objects and some risk points in the road space can be connected and associated by connecting lines each time;

[0271] According to actual needs, the association of people, machines, objects and some risk points can be associated across road segments or across road space;

[0272] The connection points of the connecting lines can be the key points on the surface of the people, machines, objects and some risk points, and the connection points of the connecting lines can also be the key points on the surface of the envelopes of the people, machines, objects and some risk points. Each connecting line can connect single or multiple key points on the surface of each person, machine, object and some risk point and or envelope;

[0273] Multiple people, machines and objects can also be enveloped as a whole and associated with other people, machines, objects and other multiple people, machines and objects, and according to needs, the multiple people, machines and objects can also be associated within the whole;

[0274] According to actual needs, the distributed named navigation pedestrian and vehicle warning system can automatically associate certain people, machines and objects, and form certain dynamic or static geometric shapes or shapes according to the association. The associated people, machines and objects move and or fly according to the moving speed, moving navigation route, moving acceleration and other parameters specified by the distributed named navigation pedestrian and vehicle warning system, so that the association between the associated people, machines and objects changes according to the predetermined dynamic geometric shape or shape and or the real-time generated dynamic geometric shape or shape according to the needs. The people, machines and objects can be distributed on different road segments, on the same road segment, or on different real estate locations. The people, machines and objects include dynamic and static objects, and the people, machines and objects can be adjacent or not adjacent. The associated navigation and warning method can be applied in multiple scenarios of navigation, warning or tracking, and can improve the accuracy and efficiency of navigation, warning or tracking;

[0275] Through long-term learning and calculation of road environment conditions, road traffic conditions, road uncertainty factor occurrence conditions and road people, machine, object and other association connection structure change conditions, the space-time change rule logic paradigm and model of each road environment condition, the space-time change rule logic paradigm and model of each road traffic condition, the space-time change rule logic paradigm and model of each road uncertainty factor occurrence condition, the space-time change rule logic paradigm and model of each road space coding and or naming of people, machines, objects, the update paradigm and model of the management rules, specifications and standards of each road space traffic, navigation and warning, and the space-time change rule logic paradigm and model of the association connection structure of people, machines, objects and other objects in each road space are formed;

[0276] According to the space-time change rule logical paradigm and model of the association and connection structure of people, machines, and objects in each section of the road space, the people, machines, and objects in the corresponding road space are associated and connected and calculated;

[0277] The space-time change rule logical paradigm and model of the road flow condition, the space-time change rule logical paradigm and model of the occurrence of uncertain factors in each section of the road, the space-time change rule logical paradigm and model of the coding and / or naming of people, machines, and objects in each section of the road space, the update paradigm and model of the management rules, specifications, and standards of traffic, navigation, and early warning of each section of the road space, and the space-time change rule logical paradigm and model of the association and connection structure of people, machines, and objects in each section of the road space all belong to the event space-time change rule logical paradigm and model.

[0278] Storing real-time navigation and early warning associated information and deleting expired and invalid stored information.

[0279] The establishment of trajectory association and the establishment of association measurement parameters and indexes between pedestrians and vehicles on each section of the road also include:

[0280] Establishing road environment space-time contrast measurement parameters and indexes according to road dynamic and static environment space-time data;

[0281] Establishing road meteorological environment space-time contrast measurement parameters and indexes according to road meteorological environment space-time data;

[0282] Establishing population structure contrast measurement parameters and indexes according to population structure data;

[0283] Establishing vehicle group structure contrast measurement parameters and indexes according to vehicle group structure data;

[0284] Establishing road connection structure contrast measurement parameters and indexes according to road connection structure data of each section of the road;

[0285] Establishing people, machine, and object connection structure contrast measurement parameters and indexes according to people, machine, and object connection structure data;

[0286] Establishing cluster trajectory data contrast measurement parameters and indexes according to people, machine, and object cluster space-time trajectory data;

[0287] Establishing scene contrast measurement parameters and indexes of road environment, meteorological environment, and corresponding pedestrian and vehicle or people, machine, and object independent movement or cluster movement associated connection structure data;

[0288] Based on actual trajectory data, establish trajectory data contrast indicators, such as spatiotemporal trajectory relative distance, spatiotemporal trajectory-envelope relative distance, relative distance change rate, relative distance change acceleration, etc. Infer trajectory contrast indicator values ​​through real-time calculation, and calculate and plan to generate spatiotemporal dynamic maps according to navigation rules, specifications, standards, etc. and / or warning rules, specifications, standards, etc.; collaboratively calculate and plan to generate spatiotemporal relative positioning and navigation routes for each pedestrian and vehicle; calculate and plan to generate navigation instructions, warning instructions and event representations, classifications and descriptions for each pedestrian and vehicle; calculate and plan to generate spatiotemporal navigation logic paradigms or graph paradigms and spatiotemporal warning logic paradigms or graph paradigms for pedestrians and vehicles.

[0289] Store real-time navigation warning information and delete expired or invalid stored information.

[0290] S5, a distributed named navigation pedestrian and vehicle early warning system, performs real-time calculations and provides navigation and / or early warnings.

[0291] Learn to calculate and reason about the spatiotemporal patterns, logical paradigms, and models of pedestrian and vehicle navigation warning events;

[0292] Learn to calculate and reason about the generation and updating of the relationship between pedestrians and vehicles, as well as the relationship measurement parameters and indicators, and the calculation logic paradigm and values ​​of the relationship measurement parameters and indicators.

[0293] Learn to calculate and reason to predict and update the associated environmental and meteorological conditions of each road segment;

[0294] Learn to compute and infer to predict and update dynamic road environment conditions;

[0295] It learns to calculate and reason to predict and generate planning maps, and updates the maps in real time;

[0296] Learn to compute and reason to predict and update relative positioning, navigation paradigms, and navigation routes;

[0297] Learn to compute and reason to predict, generate, and update early warning paradigms and warning levels;

[0298] Learn to calculate and reason about predicting and updating early warning event categories, intensities, and assessment methods;

[0299] Learn to calculate and reason to predict, generate, and update navigation rules, specifications, standards, and early warning rules, specifications, and standards;

[0300] Learn to compute and reason to predict, generate, and update navigation and warning commands;

[0301] Learn to compute and reason to predict security failure points and vulnerabilities within and between systems, and generate and update collaborative secure computing paradigms in real time.

[0302] The distributed named navigation pedestrian vehicle warning system real-time calculation and navigation and or warning also includes but is not limited to:

[0303] Learning calculation and reasoning prediction generation and update technology includes various intelligent learning calculation technology, including mapping learning, crossing learning, reinforcement learning, statistical learning, contrast learning, inductive learning, adversarial learning, deep neural network learning, federated learning, distributed learning, Transformer model, probability learning, evolutionary learning, instruction learning, association learning, event space-time model learning.

[0304] The distributed named navigation pedestrian vehicle warning system real-time calculation and navigation and or warning also includes:

[0305] The event space-time model learning refers to the learning of the space-time variation law of events, which can calculate and infer the model, logical paradigm, state curve, geometric structure, dynamic characteristics, diffusion efficiency transfer metric paradigm, knowledge language semantic atlas, etc. of the space-time variation of the associated events, and on this basis, further intelligent association learning can deduce and evolve to generate higher level event space-time variation law model intelligent science and technology;

[0306] The instruction learning refers to the learning and understanding of instruction language, which can infer the semantics, logic and execution process of instructions, and can generate new reliable and available instructions. Instruction language includes text language, voice language, symbol language, image language, video stream language, multi-modal language, etc.

[0307] The association learning includes according to the knowledge resource library, through the semantic understanding of data, according to the association relationship between semantic concept and semantic connotation, the data is represented and processed in space-time, the data automatic classification, standardization and standardization process is executed, the data association network flow space is automatically constructed, the intelligent navigation data mapping knowledge graph and resource library are formed, and according to the data association relationship and data association degree measurement method, the data space-time change logical paradigm or graph paradigm and the data association event space-time change logical paradigm or graph paradigm are automatically generated.

[0308] The distributed named navigation pedestrian vehicle warning system real-time calculation and navigation and or warning also includes:

[0309] According to the results of learning calculation and reasoning prediction generation, the navigation rules, specifications, standards, etc. and or warning rules, specifications, standards, etc. are compared, and the information such as map generation, map update, relative positioning, navigation route, navigation instruction, warning level, warning instruction, event representation classification and description is discriminated and decided.

[0310] Through Figure 4 The system can realize Figure 1The illustrated step function requirements and method flow, i.e. the distributed naming navigation pedestrian and vehicle early warning system described in the application can automatically realize the function of each step in claim 1, Figure 4 The illustrated module and unit connection combination is only one embodiment, and can be named, networked, block chained, and clustered, Figure 5 is a distributed naming navigation pedestrian and vehicle early warning cluster collaboration system schematic diagram provided for the embodiments of the application, Figure 4 The gray solid line in represents a backup connection, and there can be multiple backup connections to enhance the safety and reliability of the normal operation of the distributed naming navigation pedestrian and vehicle early warning system. The module and unit connection combination can have many connection combination modes, and the application will not enumerate them one by one.

[0311] Figure 5 is a cluster collaboration based on Figure 4 The system is regarded as A system, Figure 4 B, C, D, E… in are the same or similar systems of A system, Figure 5 It can be distributed based on real estate and road and pedestrian and vehicle distribution, and the cluster of networked systems can realize the collaboration of large and small systems and block chaining, which is beneficial to expand the navigation and early warning range, facilitate collaborative safety calculation and fault detection and troubleshooting, facilitate the realization of safe and efficient cross-domain, cross-network and cross-cloud of the distributed naming navigation pedestrian and vehicle early warning system, improve the accuracy of navigation and early warning, and enhance the robustness, stability and safety and reliability of system operation. Figure 5

[0312] In the embodiment, each lane and pedestrian lane of the road segment is enveloped and different geometric shapes are adopted, which have different envelope ranges. The geometric shapes can also be irregular geometric shapes, and the application does not limit them. In the figure, each lane and pedestrian lane of the road segment is sequentially sorted and coded, such as 1, 2, 3, 4…, which is helpful for the statistics and tracking identification of the road segment and pedestrian and vehicle, and also achieves the anonymous privacy protection of the pedestrian and vehicle. In order to track the pedestrian and vehicle of multiple road segments, the pedestrian and vehicle can be renamed based on the sorting and coding, such as m1, m2, m3…, which can be shared by the same pedestrian or the same vehicle of multiple road segments. Even if the road segment changes, the coding rule or mechanism or sorting changes, the same naming can be used to efficiently track a pedestrian or vehicle, and the adaptability of the distributed naming navigation pedestrian and vehicle early warning system to the mobility and flexibility of the pedestrian and vehicle is enhanced. The coding and or naming of objects other than the pedestrian and vehicle on the road can be selected according to the dynamic or static nature, such as Figure 6 In the embodiment, static objects are enveloped and named, such as stones and trees. Figure 6

[0313] Figure 7 ​The connection line is associated with the person, machine, and object, and the association is also the real-time association of the pedestrian and vehicle trajectory. The road conditions can be collected by the corresponding road section camera sensor and other devices in real time, and transmitted to the distributed named navigation pedestrian and vehicle warning system, and or the pedestrian and vehicle with camera sensor mobile phone and other devices collect the surrounding person, machine, and object in real time, and transmit to the distributed named navigation pedestrian and vehicle warning system, wherein the camera sensor device of each road section also includes the camera sensor device of the air mobile platform of each road section and or some third party observation or observation equipment. The distributed named navigation pedestrian and vehicle warning system includes the use of GPS navigation positioning, Beidou navigation positioning, base station positioning, network signal positioning, visual positioning, sensor positioning and other methods to obtain the pedestrian and vehicle moving trajectory, real-time positioning, speed and other moving conditions of the corresponding road section, and or the pedestrian and vehicle transmits the moving real-time conditions such as position, speed, acceleration through network interaction. After obtaining the road condition information, the distributed named navigation pedestrian and vehicle warning system will automatically establish a metric connection line for the pedestrian and vehicle, such as Figure 7 As shown, the connection line is used to establish the association between the person, machine, and object. Through the Web interactive operating system, users can also adjust and select which pedestrians and vehicles to establish a metric connection line according to the surrounding environment, and can individually select a certain pedestrian or a certain vehicle or a certain number of pedestrians or a certain number of vehicles to establish a metric connection line, or can select the corresponding person, machine, and object to establish a metric connection line according to the distance, range, and other slices or ranges. The number of connection lines of each pedestrian or each vehicle is the connection degree of the pedestrian or the vehicle.

[0314] According to actual needs, part or all of the person, machine, and object in the road space and or some risk points can be connected and associated by the connection line each time; according to actual needs, the association of the person, machine, and object and or some risk points can be associated across road sections or across road spaces; the connection point of the connection line can be the key point on the surface of the person, machine, and object and or some risk points, and the connection point of the connection line can also be the key point on the surface of the envelope of the person, machine, and object and or some risk points. Each time, the connection line can connect a single or multiple key points on the surface of each person, machine, object and or some risk points and or the envelope.

[0315] Multiple persons, machines, and objects can also be enveloped as a whole and associated with other persons, machines, and objects and or other multiple persons, machines, and objects, and according to needs, the multiple persons, machines, and objects can also be associated internally.

[0316] According to actual needs, the distributed named navigation pedestrian and vehicle warning system can automatically associate certain people, machines, and objects, and form certain dynamic or static geometric shapes or bodies from the association, real-time navigation or warning the associated people, machines, and objects to move and / or fly according to the moving speed, moving navigation route, moving acceleration, etc. specified by the distributed named navigation pedestrian and vehicle warning system, so that the associated connection geometry or body between the people, machines, and objects changes according to the predetermined and / or real-time generated dynamic geometry or body changes according to the needs, the people, machines, and objects can be distributed on different road segments, or on the same road segment, or in different real estate locations, the people, machines, and objects include dynamic and static objects, the people, machines, and objects can be adjacent or not, the associated navigation and warning method can be applied in multiple scenarios of navigation, warning or tracking, and improve the accuracy and efficiency of navigation, warning or tracking.

[0317] Figure 7 d represents the length of the associated connection line and also represents the real-time relative distance between the trajectories of the associated pedestrians and vehicles, such as d34aEF representing the length between the key point E and the key point F of the associated connection line between vehicle 3 and vehicle 4 in road segment ①ATHW003a. According to traffic rules, specifications and user self-setting, when the connection line is less than a certain threshold, the distributed named navigation pedestrian and vehicle warning system will warn the associated pedestrians and vehicles of the corresponding connection line and issue warning instructions. The length measurement of the connection line can be the length of the connection line in the picture in the image video stream, and the corresponding threshold is the threshold set according to the picture length; the length measurement of the connection line can also be the real-time physical relative distance between the actual trajectories of the pedestrians and vehicles, and the corresponding threshold is the threshold set according to the actual physical relative distance. In addition, the speed, acceleration, etc. of the extension or shortening of d can also be calculated according to the difference between the video stream time sequence frame images and / or the comparison learning, crossing learning, etc. between the video stream time sequence frame images, which are also the change speed, acceleration, etc. of the relative distance between the pedestrians and vehicles associated by the connection line, so as to warn the relative speed, relative acceleration, and change of the speed and acceleration of the associated pedestrians and vehicles, etc. According to the association of the connection line, the relative positioning and navigation route of all the associated pedestrians and vehicles can be cooperatively decided and calculated. The change speed and acceleration of the relative distance between the pedestrians and vehicles associated by the connection line can also be calculated according to the real-time physical relative distance between the actual trajectories of the pedestrians and vehicles, and the change speed and acceleration of the relative distance between the pedestrians and vehicles associated by the connection line can also be calculated according to the real-time actual speed and acceleration of the pedestrians and vehicles.

[0318] According to Figure 7The connection structure of the middle car 3 is an ellipse, and the density of the connection structure of the car 3 can be calculated. According to the traffic rules, specifications and user's self-setting, when the connection structure density is greater than a certain threshold value, the distributed named navigation pedestrian and vehicle early warning system will issue a warning instruction to the corresponding connection line associated pedestrian and vehicle early warning. Figure 7 The warning embodiment shown in the middle is just one of them, and actual calculation and warning methods can be various models, various parameters, environment and weather, uncertain factors, etc. According to the connection structure association, the relative positioning and navigation route of all associated pedestrian and vehicle can be calculated and cooperatively decided.

[0319] Figure 8 The main description is an embodiment of trajectory direct association warning, such as Figure 8 The trajectory of the pedestrian and vehicle shown in the figure is also the trajectory of the envelope of the pedestrian and vehicle itself, Figure 8 The trajectory of the pedestrian and vehicle behind itself in the middle is represented by a gray area with the same width as the envelope, which can also be represented by a trajectory line as shown by the solid and dashed lines in the figure. In the trajectory database, the trajectory line can be described in text to represent a geometric body trajectory area with the same maximum width and maximum height as the corresponding pedestrian envelope or vehicle envelope. Figure 8 The trajectory of the pedestrian and vehicle entity and the envelope in front is represented by a bar pattern area with the same width as the envelope, which can also be represented by a trajectory line as shown by the solid line in the figure. In the trajectory database, the trajectory line can be described in text to represent a geometric body trajectory area with the same maximum width and maximum height as the corresponding pedestrian envelope or vehicle envelope. When the trajectory of the pedestrian and vehicle entity and the envelope in front overlaps with other pedestrian and vehicle entities and or their envelopes, such as Figure 8 As shown in the middle, the overlapping area A, the overlapping area B and the overlapping area C, a warning can be set to issue a warning instruction to the associated pedestrian and vehicle. The size and shape of the pedestrian and vehicle envelope, the distributed named navigation pedestrian and vehicle early warning system will automatically set the initial envelope and issue rules and specifications, and the user can set and adjust according to the user's own needs and the rules and specifications of the distributed named navigation pedestrian and vehicle early warning system envelope. According to the difference between the video stream time sequence frame image and or the contrast learning, crossing learning, etc. between the video stream time sequence frame image, the speed, acceleration, etc. of the increase or decrease of the trajectory overlapping area between the pedestrian and vehicle can be calculated, which is also the change speed, acceleration, etc. of the relative distance between the associated pedestrian and vehicle, so that the relative speed, relative acceleration and the increase and decrease of the speed and acceleration of the associated pedestrian and vehicle and the change of the moving direction, etc. of the associated pedestrian and vehicle can be warned. According to the trajectory association, the relative positioning and navigation route of all associated pedestrian and vehicle can be calculated and cooperatively decided. According to the trajectory association of all pedestrian and vehicle on each road section, the relative positioning and navigation route of all associated pedestrian and vehicle can be calculated and cooperatively decided.

[0320] Figure 9 The group association is shown in the middle, A route section 2, 3, 4, 5 vehicle cluster is associated as a group to move, named A2-5 association group, A2-5 association group and A route section 1 pedestrian and X route section 2 vehicle and target address A1 real estate group association geometry, named A2-5-1-X2- A1 geometry, the geometry can be closely associated with the position, navigation route, driving speed, acceleration and other factors of A2-5 association group and A route section 1 pedestrian and X route section 2 vehicle, and can be dynamically planned or regulated in real time. A route section 1 vehicle and X route section 1 vehicle form an associated geometry A1-X1-M1 with the common tracking target M route section 1 vehicle, the geometry changes in real time according to the movement status of M1 and the tracking status and navigation warning status of A1 and X1, and the distributed named navigation pedestrian and vehicle warning system can real-time regulate and plan the spatial and temporal changes of the geometry and the spatial and temporal changes of the associated connection line.

[0321] According to actual needs, the distributed named navigation pedestrian and vehicle warning system can automatically associate certain people, machines and objects, and form a certain dynamic or static geometry or shape with the association, real-time navigate or warn the associated people, machines and objects to move and or fly according to the moving speed, moving navigation route, moving acceleration and other specified by the distributed named navigation pedestrian and vehicle warning system, so that the associated connection geometry or shape between the people, machines and objects changes according to the predetermined and or real-time generated dynamic geometry or shape changes according to the demand, the people, machines and objects can be distributed on different road sections, also can be distributed on the same road section, or distributed in different real estate locations, the people, machines and objects include dynamic and static objects, the people, machines and objects can be adjacent or not adjacent, the associated navigation and warning method can be applied in multiple scenarios of navigation, warning or tracking, and improve the accuracy and efficiency of navigation, warning or tracking.

[0322] As Figure 10As shown, through the collaborative calculation of meteorological environment, pedestrian and vehicle, road environment and other data of each road section, the information data of road connection structure, path planning and real-time map are inferred, and through the collaborative calculation of road connection structure, path planning and real-time map and other data, the information data of relative positioning of people, machines and objects, and the associated map of connection structure and real-time map are inferred, and through the collaborative calculation of relative positioning of people, machines and objects, and the associated map of connection structure and real-time map and other data, the information data of early warning decision evaluation, associated event management, pedestrian and vehicle trajectory and navigation route are inferred, and the information data of early warning decision evaluation, associated event management, pedestrian and vehicle trajectory and navigation route are fed back to each step of collaborative calculation in real time, helping to infer the data results after each step of collaborative calculation, forming a navigation and early warning associated data deep perception and cognition closed-loop flow space, such as Figure 11 As shown, Figure 11 The distributed naming navigation pedestrian and vehicle early warning system data deep perception and cognition associated flow space schematic diagram provided by the embodiment of the application is shown in the figure.

[0323] The early warning decision evaluation includes early warning decision information and evaluation information of the early warning decision information.

[0324] The associated event management includes associated event information and management information of the event, and the associated event includes various determined events and uncertain events occurring on each road section, including navigation events and early warning events.

[0325] The associated collaborative calculation model can be realized by chip cluster collaborative calculation, or by processor cluster collaborative calculation, or by chip and processor joint cluster collaborative calculation.

[0326] The association data of the association collaborative computing model includes current meteorological environment of each road section, time and space variation law of meteorological environment of each road section, time and space logic paradigm and graph paradigm of meteorological environment of each road section, current static environment of each road section, time and space variation law of static environment of each road section, time and space logic paradigm and graph paradigm of static environment of each road section, current dynamic environment of each road section, time and space variation law of dynamic environment of each road section, time and space logic paradigm and graph paradigm of dynamic environment of each road section, current pedestrian and vehicle demand of each road section, time and space variation law of pedestrian and vehicle demand of each road section, time and space logic paradigm and graph paradigm of pedestrian and vehicle demand of each road section, current connection structure of each road section, time and space variation law of connection structure of each road section, time and space logic paradigm and graph paradigm of connection structure of each road section, current path planning and real-time map of each road section, time and space variation law of path planning and real-time map of each road section, time and space logic paradigm and graph paradigm of path planning and real-time map of each road section, current relative positioning of pedestrian and vehicle of each road section, time and space variation law of relative positioning of pedestrian and vehicle of each road section, time and space logic paradigm and graph paradigm of relative positioning of pedestrian and vehicle of each road section, current association map of connection structure and real-time map, time and space variation law of association map of connection structure and real-time map, time and space logic paradigm and graph paradigm of association map of connection structure and real-time map, current early warning decision evaluation of each road section, time and space variation law of early warning decision evaluation of each road section, time and space logic paradigm and graph paradigm of early warning decision evaluation of each road section, current pedestrian and vehicle trajectory of each road section, time and space variation law of pedestrian and vehicle trajectory of each road section, time and space logic paradigm and graph paradigm of pedestrian and vehicle trajectory of each road section, current association event management of each road section, time and space variation law of association event management of each road section, time and space logic paradigm and graph paradigm of association event management of each road section, current navigation route of each road section, time and space variation law of navigation route of each road section, time and space logic paradigm and graph paradigm of navigation route of each road section. The "pedestrian and vehicle" in the current pedestrian and vehicle demand of each road section can generally refer to the quantity condition, characteristic attribute condition and uncertain condition of each type of person, machine and object on each road section, and the "demand" in the current pedestrian and vehicle demand of each road section can include various types of demands published by the distributed named navigation pedestrian and vehicle early warning system and other persons, machines and objects not on the current road section, and various types of associated demands published by the distributed named navigation pedestrian and vehicle early warning system and the interaction of other persons, machines and objects. Figure 11 As shown in Figure 11 The distributed named navigation pedestrian and vehicle early warning system data deep perception and cognition association flow space schematic diagram provided by the embodiment of the application is shown. The data deep perception and cognition is helpful for the optimization of the association collaborative computing model and the improvement and stability of various performances, and the association collaborative computing model is helpful for the optimization of the data deep perception and cognition association flow space and the improvement and stability of the data use efficiency.

[0327] Figure 10 and Figure 11 Provided is an embodiment of a spatio-temporal multi-dimensional multi-modal correlation collaborative computing model associated with the "named-connection structure-association map-navigation and early warning visualization" and "data spatio-temporal multi-dimensional multi-modal deep perception cognitive flow space" constructed by the present application, which can automatically perform risk early warning analysis, prediction and event evaluation on pedestrians and vehicles, improve the efficiency of data transmission processing, reduce the amount of transmission data, effectively reduce the energy consumption of the system and or network, enhance the accuracy, real-time performance and safety and reliability of navigation and early warning, and thus realize deep understanding, cognition, decision-making and execution of data.

[0328] As Figure 12 shown, there are input units, output units, correlation control units, correlation calculation units, correlation learning units, correlation metric parameter and index units, correlation topology structure units, correlation storage units, correlation decision-making units, and network connection control units integrated; Figure 12 The middle gray line is a backup connection route.

[0329] The input unit is mainly responsible for inputting known correlation data of events generated by the correlation chip, correlation processor or correlation device responsible for inference calculation and or generation, and safety processing, such as pedestrian and vehicle video streams, graphics images, pedestrian and vehicle trajectory data, road environment data, environmental meteorological data, pedestrian and vehicle navigation or early warning needs in each road space segment;

[0330] The output unit is mainly responsible for outputting correlation data for navigation and or early warning generated by the correlation chip, correlation processor or correlation device responsible for inference calculation and or generation, and safety processing;

[0331] The correlation control unit is mainly responsible for rules, specifications and or standards of events that need to be inferred and or generated, and safety processing methods, and controls and adjusts the interconnection and intercommunication of each unit of the correlation chip, correlation processor or correlation device, and the safety processing methods of each unit;

[0332] The correlation calculation unit is mainly responsible for inference calculation and or generation of correlation logic operations and result data of events according to navigation and or early warning rules, standards, etc., including fusion, evaluation and encryption and decryption of various safety calculations;

[0333] The correlation learning unit is mainly responsible for learning and prediction calculation of spatio-temporal variation rules of correlation events, such as traffic conditions, road environment conditions, environmental meteorological conditions, connection structure conditions, map construction conditions, path planning conditions, relative positioning conditions, navigation route conditions, early warning event conditions, and safety calculation methods in each time period of each road space;

[0334] The correlation metric parameter and index unit is mainly responsible for reasoning calculation and selection, generation and update of the metric parameter and index of the event;

[0335] The correlation topology unit is mainly responsible for generation, sorting, comparison and reasoning calculation of the correlation topology of the calculated event, and safety processing, such as the connection topology of pedestrians and vehicles, the connection topology of people, machines and objects on the road, the connection topology of each road segment and the road connected thereto and the surrounding real estate, the topology of map collaborative construction, the matching mapping topology of the code and or naming of pedestrians and vehicles and the trajectory and envelope of pedestrians and vehicles, the connection topology of the input module of the distributed naming navigation pedestrian and vehicle early warning system and or the corresponding interface and or equipment, the connection topology of the output module of the distributed naming navigation pedestrian and vehicle early warning system and or the corresponding interface and or equipment, and the network transmission routing topology.

[0336] The correlation storage unit is mainly responsible for storing the main correlation data, correlation computing power and correlation model information of each unit of the correlation chip, correlation processor or correlation device.

[0337] The correlation generation decision unit is mainly responsible for generating navigation and or early warning and correlation event decision information and or decision instructions according to the calculation results and navigation and or early warning rules, standards and the like. The decision information can be relative positioning information, navigation route information, map construction and update, early warning categories, levels, instructions, event evaluation methods, rules, standards and results, and new navigation and or early warning rules, standards, methods and the like.

[0338] The network connection control unit is mainly responsible for connection with various types of networks, responsible for information interaction with the Internet, connection control of various API interfaces, network status calculation, safety processing of information network transmission and the like.

[0339] The distributed naming navigation pedestrian and vehicle early warning correlation chip can perform spatio-temporal multi-dimensional multi-modal data parallel collaborative calculation and output, or single-dimensional single-modal data independent calculation and output.

[0340] Figure 13 The distributed naming navigation pedestrian and vehicle early warning correlation chip structure provided by the embodiment of the present application Figure 2 The middle part in Figure 12 is replaced by a correlation model, which also illustrates that the connection, combination and integration of each unit in Figure 12 may have multiple ways, and is not limited to the embodiment shown in Figure 12 . The correlation model can also be the distributed naming navigation pedestrian and vehicle early warning system correlation collaborative calculation model shown in Figure 10 or various derivative models thereof. The distributed naming navigation pedestrian and vehicle early warning correlation chip can perform spatio-temporal multi-dimensional multi-modal data parallel collaborative calculation and output, or single-dimensional single-modal data independent calculation and output.

[0341] Figure 14 The distributed naming navigation pedestrian vehicle warning correlation chip structure diagram of the embodiment of the present application provides Figure 3 , Figure 14 A kind of visualization chip, the present application mainly realizes navigation, early warning or tracking data classification and or combination visualization, there is input unit, output unit, visualization control unit, network connection control unit, visualization storage unit and navigation, early warning or tracking data classification and or combination visualization unit composition, specific data can be input by input unit, visualization control unit controls the interconnection and intercommunication of each unit and the flow rule, specification and or standard of data, data can be transmitted to network or other chip or processor on system on network connection control unit to execute specific processing calculation process, then the result data is transmitted to Figure 14 Navigation, early warning or tracking data classification and or combination visualization unit shown in figure for visualization processing preparation output;According to functional requirements, navigation, early warning or tracking data classification and or combination visualization unit can also be designed to execute specific processing calculation process, then output. Visualization storage unit mainly stores correlation data, model, algorithm, rule specification and other information.

[0342] Figure 15 The air robot correlation warning schematic diagram of the distributed naming navigation pedestrian vehicle warning system of the embodiment of the present application provides, Figure 15Examples include flight path h1a at an altitude h1 above the ground and flight path h2a at an altitude h2 above the ground. Route segments h1a and h2a are adjacent flight path segments at different altitude levels. The distributed naming navigation pedestrian and vehicle warning system can set initial envelopes for each aircraft within the route segment. Aircraft can also set different types of envelopes themselves based on envelope setting rules, specifications, and standards through real-time interaction with the distributed naming navigation pedestrian and vehicle warning system. The distributed naming navigation pedestrian and vehicle warning system can establish trajectory associations between aircraft. Multiple aircraft can be clustered together to set large envelopes, and these clustered aircraft can then be treated as a whole with other aircraft and / or flying objects. The system can associate trajectories with multiple aircraft or aircraft clusters, and aircraft can also independently select which aircraft or aircraft clusters to associate with based on association settings rules, specifications, and standards through real-time interaction with the distributed naming navigation pedestrian and vehicle warning system. After establishing association, the distributed naming navigation pedestrian and vehicle warning system can perform real-time route planning, map building, navigation, and warnings for each aircraft, aircraft, and cluster by deeply sensing and collaboratively computing data on the spatiotemporal changes of each aircraft's or aircraft's flight needs, flight status, association connection topology, connecting lines, meteorological environment, and route environment. In route segment h1a, aircraft 4, 5, and 6 formed a cluster and were assigned an overall B-elliptic envelope. In route segment h2a, aircraft 1, 2, and 3 formed a cluster and were assigned an overall A-elliptic envelope. Depending on requirements, the distributed naming navigation pedestrian and vehicle warning system can also set route envelopes for route segments h1a and h2a, such as... Figure 15 As shown, when an unidentified flying object flies into or is about to fly into the route envelope, the distributed naming navigation pedestrian and vehicle early warning system can broadcast early warning instructions on the route segment and provide real-time navigation and scheduling of aircraft or flying objects that may cause danger on the route, including their position, route, speed, and acceleration. Figure 15 The black arrow in the middle represents real-time path planning, which can mark information such as speed and acceleration. It can be displayed on various screens or in the air in front of the actual flight path. The corresponding associated maps of each aircraft can also be displayed on various screens or in the air in front of the actual flight path, with virtual and real collaborative matching and mapping.

[0343] Figure 16 This is a schematic diagram illustrating the distributed naming navigation pedestrian and vehicle early warning system provided in an embodiment of the present invention, which tracks and identifies pedestrians based on names. Figure 16The pedestrians gradually converge to a target address from multiple road segments such as A road segment, B road segment, X road segment, and M road segment, and each pedestrian and the association between the pedestrians can be tracked and identified according to the naming of the pedestrians in the crowd or the naming sequence of the pedestrians formed by the naming of the pedestrians at each road segment, such as the consistent association of the starting location of the pedestrians and the consistent association of the trajectories of the pedestrians. According to the code assigned to the pedestrians in the crowd, the number of pedestrians in the crowd can be counted, and the crowd density can be calculated. In addition, the naming of the pedestrians by the distributed naming navigation pedestrian and vehicle warning system, the video stream image information monitored by the camera sensing device of the distributed naming navigation pedestrian and vehicle warning system at each road segment, the registration information of the pedestrians in the distributed naming navigation pedestrian and vehicle warning system, the interactive information of the pedestrians with the distributed naming navigation pedestrian and vehicle warning system, the interactive information of the pedestrians with other pedestrians in the distributed naming navigation pedestrian and vehicle warning system, and the trajectory of the pedestrians can be associated, matched, mapped, and calculated to infer the identity of the pedestrians, perform face recognition and identity authentication of the pedestrians, and perform more association calculations. The naming enables the traceability of the pedestrians and vehicles.

[0344] As Figure 17 The distributed naming navigation pedestrian and vehicle warning device provided by the embodiment includes:

[0345] A processor and a memory.

[0346] The memory is configured to store computer execution instructions.

[0347] The processor is configured to execute the computer execution instructions stored in the memory.

[0348] The processor realizes each step performed by the distributed naming navigation pedestrian and vehicle warning device in the above embodiment by executing the computer execution instructions stored in the memory. For details, refer to the related description in the above method embodiment. Alternatively, the memory can be independent or integrated with the processor, and the embodiment does not make a specific limitation. When the memory is independently arranged, the distributed naming navigation pedestrian and vehicle warning device further includes a bus for connecting the memory and the processor.

[0349] The embodiment of the application further provides a computer readable storage medium, and the computer readable storage medium stores computer execution instructions. When the processor executes the computer execution instructions, the distributed naming navigation pedestrian and vehicle warning method described above is realized.

[0350] In the application, the road types include highways, railways, dirt roads, waterways, air routes, tunnels, pipelines, indoor, outdoor, forests, space, interstellar, and other paths and spaces where people, machines, and objects can move or fly.

[0351] The concept and connotation of the pedestrian in the present application can be extended to biological people and non-biological robots, and the robots include biped robots, quadruped robots, various foot robots and various mobile robots. The concept and connotation of the vehicle in the present application can be extended to various vehicles, various ships, various hot air balloons, various aircrafts, satellites, space stations, various mobile robots and various mobile terminals. The present application is also applicable to the navigation and early warning of various mobile objects.

[0352] Obviously, the above-described drawings are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0353] In the several embodiments of the present application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are only schematic. The division of the modules is only a logical function division. There can be another division manner in actual implementation, for example, a plurality of modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the modules shown or discussed can be indirect coupling or communication connection through some interface, device or module, and can be electrical, mechanical or other forms.

[0354] The modules described as separate components can or can not be physically separated, and the components shown as modules can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment of the present application.

[0355] In addition, the functional modules in each embodiment of the present application can be integrated in one processing unit, or each module can exist physically, or two or more modules can be integrated in one unit. The integrated unit can be realized in the form of hardware, or in the form of hardware plus software function unit.

[0356] The integrated module realized in the form of software function module can be stored in a computer readable storage medium. The software function module stored in the storage medium includes a plurality of instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) execute part of the steps of the method described in each embodiment of the present application.

[0357] It should be understood that the above-mentioned processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the application can be directly embodied as hardware processor execution, or executed by a combination of hardware and software modules in the processor, and the storage and calculation can be separated or integrated. The above-mentioned chip can be a conventional chip, a special-purpose chip, a software-defined chip, etc., and the storage and calculation can be separated or integrated.

[0358] The memory can include a high-speed RAM memory, and can also include a non-volatile storage NVM, such as at least one disk memory, and can also be a U disk, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0359] The bus can be an industry standard architecture (ISA) bus, a peripheral component (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the bus in the drawings of the present application does not limit only one bus or one type of bus.

[0360] The above-mentioned storage medium can be realized by any type of volatile or non-volatile storage device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0361] An example storage medium is coupled to the processor such that the processor can read information from, and can write information to, the storage medium. Of course, the storage medium can be a part of the processor. Consistent with the teachings provided herein, the processor (acting in response to a plurality of instructions executed by the processor) can be capable of implementing any of the features, steps, or functions disclosed herein, including the methods and techniques described above. The storage medium can be realized as a collection of processing elements (e.g., objects, databases, data structures, etc.) that are stored in a computer readable storage medium. Consistent with the teachings provided herein, a computer program product can include a computer readable storage medium storing computer program code, which can be executed by the processor to implement any of the features, steps, or functions disclosed herein, including the methods and techniques described above.

[0362] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware. The foregoing program can be stored in a computer readable storage medium. The program executes to perform the steps of the above-mentioned method embodiments; and the foregoing storage medium includes ROM, RAM, magnetic disk or optical disk and various storage media that can store program codes.

[0363] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the above embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A distributed naming navigation pedestrian vehicle early warning method, characterized in that, Comprise the following steps: S1, the road classification partition section, the real estate classification fragment, the road and the surrounding real estate are established correlation, the map and the knowledge base are constructed; S2, the establishment of distributed naming navigation pedestrian and vehicle early warning system; S3, the pedestrian and vehicle classification type is respectively enveloped, and the pedestrian and vehicle entering each road section is respectively coded and named; S4, the track correlation between the pedestrian and vehicle on each road section and the correlation degree parameter and index are established, including: The correlation between the pedestrian and vehicle information on each road section and or its assigned code and or name and its moving track is established, and the pedestrian and vehicle track mapping database is formed; The pedestrian and vehicle track is collected by the corresponding road section camera sensing device and or the respective camera sensing mobile phone and tablet device of the pedestrian and vehicle and is uploaded to the distributed naming navigation pedestrian and vehicle early warning system in real time; The distributed naming navigation pedestrian and vehicle early warning system comprises the pedestrian and vehicle moving track and real-time positioning information of the corresponding road section obtained by using GPS navigation positioning, Beidou navigation positioning, base station positioning, network signal positioning, visual positioning and sensor positioning; The moving track obtained by each pedestrian and vehicle in multiple ways is distinguished and represented; The code and or name of each pedestrian and vehicle on each road section, its envelope and moving track are correlated, and the pedestrian and vehicle track matching mapping database is formed; The pedestrian and vehicle correlation degree parameter and index include but are not limited to track time and place, track line length, track line change speed, track line change acceleration, relative distance between multiple track lines, relative speed between multiple track lines, relative acceleration between multiple track lines, multiple track space correlation number, multiple track space correlation connection structure, multiple track space correlation connection structure density, multiple track space correlation road connection structure density, multiple track space correlation connection structure change trend, multiple track space correlation connection structure change speed, multiple track space correlation connection structure change acceleration; The correlation mode and correlation structure of the data correlation adopt decision tree mode, matrix mode, knowledge graph mode, manifold correlation and flow space correlation; In S4, all the pedestrian and vehicle entering each road section are correlated, and the envelopes of the pedestrians and vehicles are connected by connection lines, each pedestrian and vehicle connects all the pedestrians and vehicles on the road section, or only connects the other pedestrians and vehicles around it; The connection line is lengthened or shortened according to the moving state of the pedestrian and vehicle, the connection line length forms the relative distance quantitative measurement value between the pedestrians and vehicles or between the pedestrian and vehicle tracks, and the connection line length and its change are directly determined according to the connection line length on the environmental video stream image or calculated and predicted according to the relative motion speed, relative acceleration, relative position and relative moving track of the correlated pedestrians and vehicles; In S4, the connection line length represents the real-time relative distance of the space-time track, the speed and acceleration of the lengthening or shortening of the connection line represent the relative speed and relative acceleration between the correlated two parties, and the connection line length and its change are directly determined according to the connection line length on the environmental video stream image or calculated and predicted according to the actual relative speed, relative acceleration, relative position and relative moving track of the correlated two parties; S4, the distributed named navigation pedestrian and vehicle early warning system automatically establishes the metric connection line for the pedestrian and vehicle, and the user can also adjust and select the metric connection line with the surrounding vehicles and pedestrians according to the surrounding environment, and the number of connection lines of each pedestrian or each vehicle is the connection degree of the pedestrian or the vehicle; S4, the pedestrian and vehicle user interacts with the distributed named navigation pedestrian and vehicle early warning system in real time to achieve the best personalized early warning demand; S4, the connection line display exists or implicitly exists; S4, the ratio of the total number of the pedestrian or the vehicle and all the connected other pedestrians and vehicles to the area or space volume of the road connected by the outermost pedestrian and vehicle in the pedestrian or the vehicle and all the connected other pedestrians and vehicles is the connection structure density of the pedestrian or the vehicle; The correlation metric parameters and indexes include but are not limited to connection line length, connection line change speed, connection line change acceleration, relative distance, relative speed, relative acceleration, connection degree, connection structure, connection structure density, road connection structure density, structure change trend, structure change speed, and structure change acceleration; S4, the ratio of the total number of the pedestrian or the vehicle and all the connected other pedestrians and vehicles to the area or space volume of the road connected by the outermost pedestrian and vehicle in the pedestrian or the vehicle and all the connected other pedestrians and vehicles is the connection structure density of the pedestrian or the vehicle; Real-time generation of correlation metric parameter and index values of each pedestrian and each vehicle on each road segment and pedestrian and vehicle road connection structure density values of part or all road segments; S4 also includes: According to the spatio-temporal correlation connection structure diagram between pedestrians and vehicles, the structure spatio-temporal change trend, the structure spatio-temporal change speed, the structure spatio-temporal change acceleration, and other spatio-temporal change correlation metric parameters and indexes, and according to the navigation rules, specifications, standards, and or early warning rules, specifications, standards, the spatio-temporal dynamic map is calculated and generated, the spatio-temporal relative positioning and navigation route of each pedestrian and each vehicle is calculated and generated, the navigation instruction, early warning instruction, and event representation, classification, and description of each pedestrian and each vehicle are calculated and generated, and the spatio-temporal navigation logic paradigm or graph paradigm and the spatio-temporal early warning logic paradigm or graph paradigm of the pedestrian and vehicle are calculated and generated; S5, the distributed named navigation pedestrian and vehicle early warning system calculates and navigates and or warns in real time. 2.The distributed naming navigation pedestrian and vehicle early warning method according to claim 1, characterized in that: S1, the immovable property is classified, fragmented, and associated with the surrounding roads and immovable property to build a map and a knowledge base, including: S11, the roads are classified, zoned, and segmented, the immovable property is classified, fragmented, and coded and or named, and is digitized by images, video streams, and text descriptions; S12, each road segment is associated with its surrounding immovable property and the correlation metric parameters and indexes are established; The association is established by using geographical geometric figures or textual language description; The correlation metric parameters and indexes include distance, direction, pedestrian and vehicle spatio-temporal flow, pedestrian and vehicle travel frequency, and various spatio-temporal attribute characteristics of pedestrians and vehicles and pedestrian and vehicle clusters; S13, each road segment is associated with each road segment connected thereto and the correlation metric parameters and indexes are established; The association is established by using geographical geometric figures or textual language description; The correlation measure parameters and indexes include: connection direction, distance, pedestrian and vehicle space-time flow, pedestrian and vehicle transfer probability, pedestrian and vehicle travel frequency, various space-time attribute characteristics of pedestrian and vehicle and pedestrian and vehicle cluster; S14, updating the map according to the correlation of each road segment and real estate, the space-time change update state, and the vehicle prediction calculation; The map and knowledge base also include all people, machines, and objects in the surrounding real estate and environment as reference objects for each road segment and its connecting roads, and the map and path planning are constructed based on the mutual correlation and / or reference of multiple parties; S15, encrypting and decrypting the coding and / or naming and feature information of roads and real estate; S16, visualizing or simulating the roads and real estate and their space-time change conditions, and establishing a road and real estate knowledge database or cloud. 3.The distributed naming navigation pedestrian and vehicle pre-warning method according to claim 1, characterized in that: The distributed named navigation pedestrian and vehicle warning system in S2 includes: A distributed named navigation pedestrian and vehicle warning system is established using servers, base stations, gateways, routers, switches, sensors, cameras, and radars; According to the classification and segmentation of roads, the distributed named navigation pedestrian and vehicle warning system is blockchained; According to the classification and segmentation of roads, the distributed named navigation pedestrian and vehicle warning network system adopts a gateway cluster architecture to establish collaboration, and can also adopt a named data network security architecture that combines naming and addressing.

4. The distributed naming navigation pedestrian vehicle warning method of claim 3, wherein: The distributed named navigation pedestrian and vehicle warning system in S2 includes: An input module, an output module, a secure computing processing module, a navigation warning control module, a navigation warning event management module, a storage module, a map module, an environmental and meteorological module, a road environment module, a pedestrian module, a vehicle module, a trajectory module, a correlation module, a visualization module, a hardware management module, a software management module, a language and image knowledge base module, a navigation language translation NaviT module, a network connection control module, a road and real estate correlation knowledge database or cloud module, and a Web interactive operating system module; The above modules are interconnected, and the modules can be divided into multiple different processing units, which can be distributed in different servers or clouds through physical isolation and / or virtual isolation. The modules and units can be integrated in the same device, and each module and unit can have a cache area according to efficiency and data conditions. The input module, input unit, output module, and output unit can be embedded and integrated into other modules, or can be interconnected with other modules; The functions of each module of the distributed named navigation pedestrian and vehicle warning system are as follows: The input module is responsible for collecting information for navigation and warning, including various sensors, radars, cameras, network interfaces, and intelligent devices; The output module is responsible for transmitting processed navigation and warning information to the corresponding user, terminal, device, and interface. Security computing processing module: responsible for trajectory comparison calculation according to various intelligent learning and or intelligent computing processing technology, road environment obstacle avoidance and risk avoidance calculation, weather prediction calculation, path planning calculation, event space-time change rule logic calculation, correlation learning calculation, video stream compression encoding calculation, network transmission processing, various interconnection security protocol design, various information and data security processing and encryption and decryption calculation; Navigation warning control module: responsible for mutual communication between modules, and forms navigation information instructions and warning information instructions according to interactive information, rule specification standard, calculation result, and evaluates classification and grading, and issues navigation instructions and or warning instructions to pedestrians and or vehicles; Navigation warning event management module: responsible for evaluating classification and grading of specific navigation events and warning events, establishing event data logical model associated flow space, forming event mapping database and calculating statistics, for various learning calculations; Storage module: responsible for storing module data, rules, algorithms, models, strategies, hierarchical block object storage, and setting effective period and refreshing invalid data in time according to use and importance; Map module: responsible for calculating and generating and updating map, route, landmark information, responsible for calculating and reasoning to generate real-time dynamic path planning information, navigation route scheduling information of each pedestrian and each vehicle, including various electronic maps, virtual reality maps and mixed reality maps and associated matching mapping data information; Environmental meteorological module: responsible for collecting, detecting, identifying, classifying and standardizing environmental meteorological real-time information data, and predicting and calculating environmental meteorological information; Road environment module: responsible for collecting, detecting, identifying, classifying and standardizing road environment real-time information data, road classification, segmentation and zoning, and predicting and planning mobile route calculation; Pedestrian module: responsible for pedestrian identification classification labeling, pedestrian coding and decoding, naming and eliminating naming, pedestrian statistical calculation, pedestrian space-time flow change rule calculation and registration, identity authentication, user and system interaction, wherein the pedestrian identification classification labeling includes identification classification labeling according to pedestrian coding, naming, clothing, appearance, age, shape, action characteristics, also includes identification classification labeling according to pedestrian cluster structure, density, number, behavior, clothing, age and cluster team activity type, and also includes pedestrian identification classification labeling according to human, machine and object interaction characteristics; Vehicle module: responsible for vehicle identification classification labeling, vehicle coding and decoding, naming and eliminating naming, vehicle statistical calculation, vehicle time and space flow change law calculation and registration, vehicle authentication, user interaction with the system, wherein the vehicle identification classification labeling includes identification classification labeling according to the characteristics of vehicle coding, naming, color, brand, license plate number, shape, moving or flying speed, and also includes identification classification labeling according to the characteristics of vehicle fleet feature attributes such as cluster structure, density, number of vehicles, moving or flying speed and cluster group activity type, and also includes identification classification labeling according to the characteristics of human, machine and object interaction, and the vehicle authentication includes vehicle identity authentication, vehicle owner authentication and vehicle user authentication, as well as the association of various authentication data information with the vehicle; Trajectory module: responsible for collecting real-time movement trajectories of pedestrians and vehicles, and forming pedestrian and vehicle trajectory maps; Correlation module: responsible for establishing correlations between roads, weather, environment, maps, pedestrians, vehicles and trajectories, performing correlation calculations based on correlation measurement parameters and indicators as well as traffic rules, navigation rules and early warning rules, obtaining real-time correlation data results, and establishing data deep perception and cognitive correlation flow processes and knowledge graphs, storing and updating correlation data, correlation logic and correlation model information; Visualization module: responsible for visualizing and displaying map, road conditions, weather, trajectory, pedestrian, vehicle and correlation status on various screens or in real air, and matching mapping between virtual and real; Hardware management module: responsible for adjusting, checking, repairing and intelligent computing safety warning of each hardware of the navigation and early warning system; Software management module: responsible for adjusting, checking, repairing and intelligent computing safety warning of each software of the navigation and early warning system; Language image knowledge base module: responsible for storing various languages, voices, texts, images, symbols, curves, structures and logic knowledge of navigation and early warning information data and their associated information data by classification and scaling, and matching and mapping between languages, voices, texts, images, symbols, curves, structures and logic; Navigation language translation NaviT module: based on the language image knowledge base, combining Transformer model and or CNN model and or cross-learning and or reinforcement learning and or statistical learning and or contrast learning intelligent technology method, responsible for language mutual translation and mutual conversion of multi-modal navigation information data, and responsible for generating navigation instructions, early warning instructions, map information, path planning information, labeling information and parameter information; Network connection control module: responsible for network connection, interface management, network detection, network status calculation, connection protocol design, network information encryption and decryption calculation, and safety warning of each module and each unit; Road and real estate correlation knowledge database or cloud module: responsible for digitizing, visualizing or simulating road and real estate and their time and space change conditions, and representing and calculating the correlation relationship, correlation measurement parameters and indicators of road and real estate, forming the time and space correlation logic paradigm and model of each section of road and its connected roads and surrounding real estate, and calculating and updating various scale maps; Web interaction system module: mainly responsible for the interaction of safety information between pedestrians and vehicles and the modules of the system, and responsible for the interaction of safety information between pedestrians and vehicles, and responsible for the interaction of safety information between pedestrians and vehicles on each road section, also including the interaction between various types of users such as people, machines and objects, and the interaction between various types of users and the distributed named navigation pedestrian and vehicle warning system.

5. The distributed named navigation pedestrian and vehicle warning method according to claim 4, wherein: In S2, the time-space neural network learning mechanism small model of each module of the distributed named navigation pedestrian and vehicle warning system is formed according to the associated historical data information, each module is connected to form a time-space navigation NaviGPT or navigation intelligent agent and various types of navigation warning API. According to the corresponding neural network model of each module, the corresponding programmable and or software defined chip and or processor is designed and developed.

6. The distributed naming navigation pedestrian vehicle warning method of claim 1, wherein: The sub-steps of S3 include: The pedestrians and vehicles are collected by the camera sensing devices of the corresponding road section in real time and transmitted to the demand modules of the distributed named navigation pedestrian and vehicle warning system, and or the pedestrians and vehicles each have a camera sensing mobile phone or tablet device to collect and transmit to the demand modules of the distributed named navigation pedestrian and vehicle warning system in real time, and or some third party observation or observation device to collect and transmit to the demand modules of the distributed named navigation pedestrian and vehicle warning system in real time, and or the pedestrians and vehicles each register on the display page of the distributed named navigation pedestrian and vehicle warning system, including web page or APP; Pedestrian and vehicle enveloping is to envelop pedestrians and vehicles respectively by using geometric shape images according to the shape and volume characteristics of pedestrians and vehicles, and the appearance shape and volume size of the enveloped geometric image are generally not less than the overall actual shape and volume size of pedestrians and vehicles; According to the road segmentation condition, the road segmentation includes the separation by special dividing line or special road sign or the separation according to the road segmentation mechanism in the road environment module of the distributed named navigation pedestrian and vehicle warning system; The pedestrians and vehicles entering each road section are immediately classified, coded and or named, and the code and or name on the road section is used uniformly, and when the pedestrians and vehicles move out of the road section, the code and or name is automatically invalidated and cleared; when entering another road section, the pedestrians and vehicles are re-coded and or named, and when moving out of the road section, the code and or name is automatically invalidated and cleared.

7. The distributed naming navigation pedestrian vehicle warning method of claim 6, wherein: In S3, one name and or one or more codes or multiple names and or multiple codes are used by each pedestrian and each vehicle on multiple consecutive road sections.

8. The distributed named navigation pedestrian and vehicle warning method according to claim 7, wherein: In S3, the code and or name is pre-coded within a certain period of time before the pedestrian and vehicle enter a certain road section, that is, the code and or name on the road section and the code and or name on the next road section exist simultaneously within a certain period of time, and the code and or name includes coding and or naming according to the ordered coding rule, coding and or naming according to the unordered coding rule, and coding and or naming according to the encryption and decryption coding rule; The same coding and / or naming mechanism is used for each road segment in S3, or different coding and / or naming mechanisms are used, and multiple sets of coding and / or naming mechanisms are set for the same road segment according to different entrances and different moving directions; In S3, the coding and / or naming is automatically completed in real time by the distributed naming navigation pedestrian and vehicle warning system based on the real-time information collected by the system, and the pedestrian and vehicle cannot modify or adjust the coding and / or naming; In S3, the distributed naming navigation pedestrian and vehicle warning system associates and matches the coding and / or naming of each road segment with the registration information and / or historical association information of the pedestrian and vehicle; In S3, the distributed naming navigation pedestrian and vehicle warning system identifies the pedestrian and vehicle through feature detection and identifies the pedestrian and vehicle through the interconnection and sharing of information between road segments, and establishes the association and matching mapping of each pedestrian, each vehicle, and each object with each road segment and the coding and / or naming.

9. The distributed naming navigation pedestrian and vehicle warning method according to claim 8, characterized in that: Each coding and / or naming on each road segment in S3 includes part or all of the people, machines, and objects in the road space; The coding and / or naming of people, machines, and objects in each road segment and its space is periodically recycled or re-coded and / or named according to different rules and mechanisms in a certain period of time; The length of the time period for coding and / or naming in each road segment and its space is adjusted and updated according to the road environment, road traffic conditions, and other factors; Through long-term learning and calculation of road environment, road traffic conditions, and uncertain factors, the logical paradigm and model of the spatiotemporal variation of each road environment, the logical paradigm and model of the spatiotemporal variation of each road traffic, the logical paradigm and model of the spatiotemporal variation of uncertain factors, the logical paradigm and model of the spatiotemporal variation of coding and / or naming of people, machines, and objects in each road space, and the updating paradigm and model of the management rules, specifications, and standards of traffic, navigation, and warning in each road space are formed; Coding and / or naming of people, machines, and objects in each road space is performed according to the spatiotemporal variation logical paradigm and model of coding and / or naming of people, machines, and objects in each road space; The spatiotemporal tracking identification and identity authentication of people, machines, and objects are performed by combining the spatiotemporal variation logical paradigm of coding and / or naming of people, machines, and objects in each road space with other characteristic attributes of the people, machines, and objects, and the tracking identification classification, traffic statistics, spatiotemporal tracking identification, identity authentication, and relationship identification and authentication of people, machines, and objects in complex scenarios are performed by combining the spatiotemporal variation logical paradigm of coding and / or naming of people, machines, and objects in each road space with other characteristic attributes of the people, machines, and objects. The logical paradigm and model of the spatiotemporal variation of the road traffic condition of each section, the logical paradigm and model of the spatiotemporal variation of the occurrence of uncertain factors of each section, the logical paradigm and model of the spatiotemporal variation of the coding and or naming of people, machines, and objects in the space of each section, and the updating paradigm and model of the management rules, specifications, and standards of traffic, navigation, and early warning of the space of each section all belong to the logical paradigm and model of the spatiotemporal variation of events. Storing real-time navigation and early warning associated information and deleting expired and invalid stored information.

10. The distributed named navigation and early warning method for pedestrian and vehicle according to claim 1, characterized in that: In S4, some or all people, machines, objects, and or some risk points in the road space are connected by connection lines to establish associations; In S4, the associations of people, machines, objects, and or risk points can be across road sections or across road spaces; In S4, the connection points of the connection lines are the key points on the people, machines, objects, and or some risk points themselves or the key points on the envelopes of the people, machines, objects, and or some risk points, and each connection line connects single or multiple key points on each person, machine, object, and or some risk point itself or envelope; Multiple people, machines, and objects are enveloped as a whole and associated with other people, machines, objects, and or other multiple people, machines, and objects, and according to needs, associations are also established among the multiple people, machines, and objects.

11. The distributed named navigation and early warning method for pedestrian and vehicle according to claim 10, characterized in that: In S4, the distributed named navigation and early warning system for pedestrian and vehicle automatically associates certain people, machines, and objects, and forms certain dynamic or static geometric shapes or bodies with the associations, and real-time navigation or early warning of the associated people, machines, and objects moving and or flying according to the moving speed, moving navigation route, and moving acceleration specified by the distributed named navigation and early warning system for pedestrian and vehicle, so that the associated geometric shapes or bodies of the people, machines, and objects change according to the predetermined dynamic geometric shapes or bodies or the dynamic geometric shapes or bodies generated in real time according to needs; The people, machines, and objects can be distributed on different road sections, on the same road section, or on different real estate locations, and include dynamic and static objects, and can be adjacent or not adjacent, and the associated navigation and early warning method can be applied in multiple scenarios of navigation, early warning, or tracking.

12. The distributed named navigation and early warning method for pedestrian and vehicle according to claim 11, characterized in that: The distributed naming navigation pedestrian and vehicle early warning system in S4 calculates the road environment condition, the road traffic condition, the road uncertainty factor occurrence condition and the road human, machine and object connection structure change condition through long time learning, forms the logic paradigm and model of the space-time change rule of each section road environment condition, forms the logic paradigm and model of the space-time change rule of each section road traffic condition, forms the logic paradigm and model of the space-time change rule of each section road uncertainty factor occurrence condition, forms the logic paradigm and model of the space-time change rule of each section road space coding and or naming for human, machine and object, forms the update paradigm and model of the management rule, specification and standard of each section road space traffic, navigation and early warning, and forms the logic paradigm and model of the space-time change rule of each section road space connection structure for human, machine and object; According to the logic paradigm and model of the space-time change rule of each section road space connection structure for human, machine and object, the corresponding road space human, machine and object are connected and calculated; The logic paradigm and model of the space-time change rule of each section road traffic condition, the logic paradigm and model of the space-time change rule of each section road uncertainty factor occurrence condition, the logic paradigm and model of the space-time change rule of each section road space coding and or naming for human, machine and object, the update paradigm and model of the management rule, specification and standard of each section road space traffic, navigation and early warning, and the logic paradigm and model of the space-time change rule of each section road space connection structure for human, machine and object all belong to the logic paradigm and model of the event space-time change rule; The real-time navigation early warning association information is stored, and the expired invalid storage information is deleted.

13. The distributed naming navigation pedestrian vehicle warning method of claim 12, wherein: S4 also includes: The road environment space-time contrast measurement parameter and index are established according to the road dynamic and static environment space-time data; The road meteorological environment space-time contrast measurement parameter and index are established according to the road meteorological environment space-time data; The human group structure contrast measurement parameter and index are established according to the human group structure data; The vehicle group structure contrast measurement parameter and index are established according to the vehicle group structure data; The road connection structure contrast measurement parameter and index are established according to the road connection structure data; The human, machine and object connection structure contrast measurement parameter and index are established according to the human, machine and object connection structure data; The cluster trajectory data contrast measurement parameter and index are established according to the human, machine and object cluster space-time trajectory data; The scene contrast measurement parameter and index of the road environment, meteorological environment, corresponding pedestrian and vehicle or human, machine and object independent movement or cluster movement associated space-time scene are established according to the road environment, meteorological environment, corresponding pedestrian and vehicle or human, machine and object independent movement or cluster movement associated connection structure data; According to the actual trajectory data, the trajectory data contrast measure parameters and indicators are established, the trajectory contrast measure parameters and indicator values are calculated in real time, and the space-time dynamic map is calculated and generated according to the navigation rules, specifications, standards and or early warning rules, specifications, standards, the space-time relative positioning and navigation route of each pedestrian and each vehicle are calculated and generated, the navigation instructions, early warning instructions and event representation, classification and description of each pedestrian and each vehicle are calculated and generated, the space-time navigation logic paradigm or graph paradigm and the space-time early warning logic paradigm or graph paradigm of the pedestrians and vehicles are calculated and generated; The real-time navigation and early warning related information is stored, and the expired and invalid stored information is deleted.

14. The distributed naming navigation pedestrian vehicle warning method of claim 1, wherein: In S5, the distributed named navigation pedestrian and vehicle early warning system calculates and navigates and or warns in real time, including but not limited to: Learning to calculate and infer to predict to generate and update the space-time change rule, logic paradigm and model of the occurrence of pedestrian and vehicle navigation and early warning events; Learning to calculate and cooperatively infer to predict to generate and update the correlation mode, correlation measure parameters and indicators and correlation measure parameter and indicator calculation logic paradigm and correlation measure parameter and indicator value between pedestrians and vehicles; Learning to calculate and infer to predict to generate and update the environmental and meteorological conditions; Learning to calculate and infer to predict to generate and update the dynamic conditions of the road environment; Learning to calculate and cooperatively inferring to predict to generate a planning map for each pedestrian and each vehicle, and updating the map in real time; Learning to calculate and cooperatively inferring to predict to generate and update the relative positioning, navigation paradigm and navigation route of each pedestrian and each vehicle; Learning to calculate and cooperatively inferring to predict to generate and update the early warning paradigm and early warning level of each pedestrian and each vehicle; Learning to calculate and infer to predict to generate and update the early warning event category, intensity and evaluation method; Learning to calculate and infer to predict to generate and update the navigation rules, specifications, standards and early warning rules, specifications, standards; Learning to calculate and infer to predict to generate and update the navigation instructions and early warning instructions; Learning to calculate and inferring to predict the security failure points and security weak points in the system and between systems, and generating and updating the cooperative security calculation paradigm in real time.

15. The distributed named navigation pedestrian and vehicle early warning method according to claim 14, characterized in that: The learning to calculate and infer to predict to generate and update technology in S5 includes various intelligent learning calculation technologies, including mapping learning, traversal learning, reinforcement learning, statistical learning, contrast learning, inductive learning, adversarial learning, deep neural network learning, federated learning, distributed learning, Transformer model, probability learning, evolutionary learning, instruction learning, correlation learning, event space-time model learning; According to the results of the learning to calculate and infer to predict, the navigation rules, specifications, standards and or early warning rules, specifications, standards are compared, and the map, relative positioning, navigation route, navigation instruction, early warning level, early warning instruction, event representation classification and description information are generated and updated.

16. The distributed named navigation pedestrian and vehicle early warning method according to claim 15, characterized in that: The event space-time model learning refers to learning the space-time change law of events, calculating and predicting the generation of a model, a logic paradigm, a state curve, a geometric structure, a dynamic characteristic, a diffusion efficiency transmission metric paradigm, and a knowledge language semantic atlas of the associated event space-time change, and further intelligently associating and learning to deduce and induce and evolve a higher-level event space-time change law model; The instruction learning refers to learning and understanding an instruction language, reasoning and generating semantics, logic, and execution process of an instruction, and decision-making and generating a new reliable and available instruction, and an intelligent science and technology of instruction language including text language, voice language, symbol language, image language, video stream language, and multi-modal language; The association learning includes representing and processing data in space-time according to semantic concepts and semantic connotations of association relationship of a knowledge resource library, performing data automatic classification, normalization, and standardization process, automatically constructing a networked flow space of data association, forming an intelligent navigation data mapping knowledge graph and a resource library, and automatically generating a data space-time change logic paradigm or a graph paradigm and a data association event space-time change logic paradigm or a graph paradigm according to a data association relationship and a data association degree measurement method.

17. A distributed naming navigation pedestrian vehicle warning device, comprising: a plurality of naming navigation devices; and a plurality of vehicle devices. The distributed named navigation pedestrian and vehicle early warning device is realized on the basis of the distributed named navigation pedestrian and vehicle early warning method in any one of claims 1 to 16. The device type is formed by one module or two module combinations or multiple module combinations or all module combinations in the input module, the output module, the safety calculation processing module, the navigation early warning control module, the navigation early warning event management module, the storage module, the map module, the environmental meteorological module, the road environment module, the pedestrian module, the vehicle module, the trajectory module, the association module, the visualization module, the hardware management module, the software management module, the language image knowledge base module, the navigation language translation NaviT module, the network connection control module, the road and real estate association knowledge database or cloud module, and the Web interactive operating system module of the distributed named navigation pedestrian and vehicle early warning system; Each device can be used alone or multiple devices can be interconnected to form a new device; The device can be embedded in the distributed named navigation pedestrian and vehicle early warning system or the Internet.

18. The distributed naming navigation pedestrian vehicle warning device of claim 17, wherein, It includes: At least one processor and a memory; The memory stores computer execution instructions; The at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the distributed named navigation pedestrian and vehicle early warning method in any one of claims 1 to 16.

19. A distributed named navigation pedestrian vehicle warning chip, characterized by: The distributed named navigation pedestrian and vehicle early warning chip is realized on the basis of the distributed named navigation pedestrian and vehicle early warning method in any one of claims 1 to 16. The various types of chips are designed according to the way of collecting, calculating, transmitting, controlling and correlating data of each module of the input module, the output module, the safety calculation processing module, the navigation and early warning control module, the navigation and early warning event management module, the storage module, the map module, the environmental and meteorological module, the road environment module, the pedestrian module, the vehicle module, the trajectory module, the correlation module, the visualization module, the hardware management module, the software management module, the language and image knowledge base module, the navigation language translation NaviT module, the network connection control module, the road and real estate correlation knowledge database or cloud module, and the Web interactive operating system module of the distributed named navigation and early warning system for pedestrians and vehicles. 20.A distributed naming navigation pedestrian vehicle warning association chip, association processor or association device, characterized in that: The distributed named navigation and early warning correlation chip, correlation processor or correlation device is realized on the basis of the distributed named navigation and early warning method according to any one of claims 1 to 16. All correlation chips, correlation processors or correlation devices are integrated by multiple units or all units including the input unit, the output unit, the correlation control unit, the correlation calculation unit, the correlation learning unit, the correlation metric parameter and index unit, the correlation topology structure unit, the correlation storage unit, the correlation decision generation unit, and the network connection control unit. The input unit is responsible for inputting known correlation data of events generated by the correlation chip, the correlation processor or the correlation device for reasoning calculation and safety processing method, including pedestrian and vehicle video stream, graphical image, pedestrian and vehicle trajectory data, road environment data, environmental and meteorological data, pedestrian and vehicle navigation or early warning demand in each road space. The output unit is responsible for outputting correlation data for navigation and early warning generated by the correlation chip, the correlation processor or the correlation device for reasoning calculation and safety processing decision. The correlation control unit is responsible for rules, specifications and standards of events generated by the correlation chip, the correlation processor or the correlation device for reasoning calculation and safety processing method, and controls and adjusts the interconnection and safety processing method of each unit of the correlation chip, the correlation processor or the correlation device. The correlation calculation unit is responsible for correlation logic operation and result data of events generated by the correlation chip, the correlation processor or the correlation device for reasoning calculation and safety processing method, including fusion, evaluation and encryption and decryption of various safety calculations. The correlation learning unit is responsible for learning and prediction calculation of the spatio-temporal variation law of correlation events, including traffic condition, road environment condition, environmental and meteorological condition, connection structure condition, map construction condition, path planning condition, relative positioning condition, navigation route condition, early warning event condition, and safety calculation method of each road space at each time period. The correlation metric parameter and index unit is responsible for selection, generation and update of metric parameters and indexes of events generated by the correlation chip, the correlation processor or the correlation device for reasoning calculation and safety processing method. The association topology unit is responsible for the generation, ordering, comparison, and inference calculation of the association topology of the calculated events, including the connection topology of pedestrians and vehicles, the connection topology of people, machines, and objects on the road, the connection topology of each road segment and the road connected to it and the surrounding real estate, the map collaborative construction topology, the matching mapping topology of pedestrian and vehicle coding and or naming and pedestrian and vehicle trajectory and envelope, the input module corresponding interface and or device connection topology of the distributed named navigation pedestrian and vehicle warning system, the output module corresponding interface and or device connection topology of the distributed named navigation pedestrian and vehicle warning system, and the network transmission routing topology. The association storage unit is responsible for storing the association data, association computing power, and association model information of each unit of the association chip, association processor, or association device. The association generation decision unit is responsible for generating navigation and or warning and association event decision information and or decision instructions according to the calculation results and navigation and or warning rules, standards, decision information can be relative positioning information, navigation route information, map construction and update, warning category, level, instruction, event evaluation method, rule, standard and result, new navigation and or warning rule, standard, method; The network connection control unit is responsible for connecting with various networks, responsible for information interaction with the Internet, connection control of various API interfaces, network status calculation, connection protocol design, and security processing of information network transmission. The distributed named navigation pedestrian and vehicle warning association chip, association processor, or association device can perform spatiotemporal multi-dimensional multi-modal data parallel collaborative calculation and output, or single-dimensional single-modal data independent calculation and output.

21. A correlation and cooperation computing model of a distributed naming navigation pedestrian vehicle early warning system, characterized in that: The association collaborative calculation model is realized on the basis of the distributed named navigation pedestrian and vehicle warning method of any one of claims 1 to 16; The association collaborative calculation model is realized on the basis of the distributed named navigation pedestrian and vehicle warning method of any one of claims 1 to 16; The warning decision evaluation includes warning decision information and evaluation information of the warning decision information; The association event management includes association event information and management information of the event, the association event includes various types of determined events and uncertain events occurring on each road segment, including navigation events and warning events, including the distributed named navigation pedestrian and vehicle warning system or network security events; The associated cooperative computing model is realized by means of chip cluster cooperative computing, processor cluster cooperative computing or joint chip and processor cluster cooperative computing; The associated data of the associated cooperative computing model comprises current meteorological environment of each road section, time-space variation law of meteorological environment of each road section, time-space logic paradigm and graph paradigm of meteorological environment of each road section, current static environment of each road section, time-space variation law of static environment of each road section, time-space logic paradigm and graph paradigm of static environment of each road section, current dynamic environment of each road section, time-space variation law of dynamic environment of each road section, time-space logic paradigm and graph paradigm of dynamic environment of each road section, current pedestrian and vehicle demand of each road section, time-space variation law of pedestrian and vehicle demand of each road section, time-space logic paradigm and graph paradigm of pedestrian and vehicle demand of each road section, current connection structure of each road section, time-space variation law of connection structure of each road section, time-space logic paradigm and graph paradigm of connection structure of each road section, current path planning and real-time map of each road section, time-space variation law of path planning and real-time map of each road section, time-space logic paradigm and graph paradigm of path planning and real-time map of each road section, current relative positioning of pedestrian and vehicle of each road section, time-space variation law of relative positioning of pedestrian and vehicle of each road section, time-space logic paradigm and graph paradigm of relative positioning of pedestrian and vehicle of each road section, current associated map of connection structure and real-time map, time-space variation law of associated map of connection structure and real-time map, time-space logic paradigm and graph paradigm of associated map of connection structure and real-time map, current early warning decision evaluation of each road section, time-space variation law of early warning decision evaluation of each road section, time-space logic paradigm and graph paradigm of early warning decision evaluation of each road section, current pedestrian and vehicle trajectory of each road section, time-space variation law of pedestrian and vehicle trajectory of each road section, time-space logic paradigm and graph paradigm of pedestrian and vehicle trajectory of each road section, current associated event management of each road section, time-space variation law of associated event management of each road section, time-space logic paradigm and graph paradigm of associated event management of each road section, current navigation route of each road section, time-space variation law of navigation route of each road section, time-space logic paradigm and graph paradigm of navigation route of each road section.

Images