Intelligent device control method, intelligent device and storage medium
By building personalized maps and predicting routes, smart devices can detect bumps in advance and make intelligent controls when navigation is off, solving the problems of poor user experience and low safety when navigation is off, and achieving improved comfort and safety in all scenarios.
Patent Information
- Application Number
- CN202411023949.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-26
- Publication Date
- 2024-11-15
AI Technical Summary
Existing smart devices cannot accurately perceive and predict road bumps when navigation is off, especially on curves or long stretches of road, resulting in a poor user experience and reduced safety.
Personalized maps are built by acquiring environmental and historical travel information from smart devices. Probabilistic models and neural networks are used to predict paths, match bump information, and perform intelligent control, including adjusting suspension stiffness and path planning.
It improves the safety and comfort of smart devices when navigation is off, reduces discomfort caused by bumps, and achieves a smart control experience in all scenarios.
Smart Images

Figure CN118963347A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of intelligent device control, and specifically provides an intelligent device control method, an intelligent device and a storage medium. Background Art
[0002] At present, most smart device control methods predict road bump information based on the planned navigation path when the navigation is turned on, and then control the smart device based on the predicted bump information.
[0003] However, when the navigation is turned off, it is still impossible to accurately perceive and predict the road ahead, especially for roads with turns ahead or roads at a long distance. The perception capabilities of radars and cameras are limited, resulting in the intelligent control functions related to vehicle handling and comfort that rely on bump information prediction being limited to navigation scenarios. In this case, the user experience will be poor and the safety of smart devices will be reduced. Summary of the invention
[0004] In order to overcome the above defects, this application is proposed to provide a solution or at least partially solve the technical problem that the existing smart device control method relies on the navigation scene, resulting in poor user experience and reduced security of the smart device. This application provides a smart device control method, a smart device and a storage medium.
[0005] In a first aspect, the present application provides a smart device control method, the method comprising:
[0006] Acquire environmental information and a first map of the smart device;
[0007] Acquire a target path based on the environmental information and the first map;
[0008] Acquire first bump information corresponding to the target path based on the environmental information;
[0009] matching the first bump information with the target path based on the environmental information;
[0010] The smart device is intelligently controlled based on the first matching result.
[0011] In a specific implementation of the present application, the first map is constructed by the following steps:
[0012] Obtaining historical travel information of the smart device;
[0013] Splitting the second map into a plurality of first map blocks;
[0014] Creating a road file and a node file corresponding to a road node in the first map block based on the historical travel information;
[0015] Creating a route file based on the historical travel information, the road file and the node file;
[0016] A mapping relationship between the road nodes and the path file is established to obtain the first map.
[0017] In a specific embodiment of the present application, the method further comprises:
[0018] Matching the path file with the historical paths in the path file library;
[0019] The path file library is updated based on the second matching result.
[0020] In a specific implementation of the present application, the acquiring the target path based on the environmental information and the first map includes:
[0021] Acquire at least one first path based on the environmental information and the first map;
[0022] Obtaining a predicted probability of the at least one first path using a probability model;
[0023] Acquire a second path based on the environmental information and the neural network model;
[0024] The target path is determined based on the predicted probability and the second path.
[0025] In a specific implementation of the present application, the first map includes a plurality of second map blocks; and acquiring at least one first path based on the environmental information and the first map includes:
[0026] Acquire a second map block in the first map based on the environmental information;
[0027] Determining a current position of the smart device in the second map block based on environmental information;
[0028] Obtaining road node information corresponding to the current position;
[0029] Acquire other road node information that is linked to the road node information;
[0030] The at least one first path is acquired based on the road node information and the other road node information.
[0031] In a specific implementation of the present application, the acquiring the first bump information corresponding to the target path based on the environmental information includes:
[0032] Acquire a path loading range based on the environmental information;
[0033] Acquire a third path based on the path loading range, wherein the third path is a path of the target path within the path loading range;
[0034] Performing thinning processing on the third path to obtain a fourth path;
[0035] The first bump information is acquired based on the fourth path.
[0036] In a specific implementation of the present application, matching the first bump information with the target path based on the environment information includes:
[0037] Matching the first bump information with the target path to obtain a first relative position of the first bump information in the target path;
[0038] Acquire a second relative position of the smart device in the target path based on the environmental information;
[0039] The distance between the bump information and the second relative position is updated based on the first relative position and the second relative position.
[0040] In a specific implementation of the present application, matching the first bump information with the target path based on the environment information includes:
[0041] acquiring second bump information based on the environment information and the first bump information, wherein the second bump information is first bump information within a preset range along a target path direction;
[0042] determining a distance between the second bump information and the smart device based on the second bump information and the environment information;
[0043] The second bump information is sorted based on the distance.
[0044] In a second aspect, a smart device is provided, comprising:
[0045] at least one processor;
[0046] and, a memory communicatively coupled to the at least one processor;
[0047] Wherein, a computer program is stored in the memory, and the computer program is the aforementioned intelligent device control method when executed by the at least one processor.
[0048] In a third aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored in the computer-readable storage medium, wherein the program codes are suitable for being loaded and run by a processor to execute any one of the aforementioned intelligent device control methods.
[0049] The above one or more technical solutions of this application have at least one or more of the following Beneficial effects:
[0050] The intelligent device control method provided in the present application includes: obtaining environmental information and a first map of the intelligent device; obtaining a target path based on the environmental information and the first map; obtaining first bump information corresponding to the target path based on the environmental information; matching the first bump information with the target path based on the environmental information; and intelligently controlling the intelligent device based on the first matching result. By obtaining bump information in advance, the intelligent device can prepare or adjust the driving path in advance to avoid accidents and improve operational safety; at the same time, predicting bump information and adjusting the motion trajectory or suspension setting of the device can reduce the user's discomfort when encountering bumps and improve the user's riding experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] The disclosure of the present application will become more easily understood with reference to the accompanying drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present application. In addition, similar numbers in the drawings are used to represent similar components, among which:
[0052] Figure 1 This is a schematic diagram of the main process of a smart device control method in one embodiment of the present application;
[0053] Figure 2 It is a complete flow chart of a smart device control method in one embodiment of the present application;
[0054] Figure 3 is a schematic diagram of the main structure of an intelligent device control device according to an embodiment of the present application;
[0055] Figure 4 It is a schematic diagram of the main structure of a smart device in one embodiment of the present application. DETAILED DESCRIPTION
[0056] Some embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the protection scope of the present application.
[0057] In the description of the present application, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, memory, and may also include software parts, such as program code, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware or a combination of the two. Non-temporary computer-readable storage media include any suitable medium that can store program code, such as a disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B" and may include only A, only B or A and B. The singular terms "one" and "the" may also include plural forms.
[0058] Currently, most traditional methods can only perceive bumpy information and control smart devices accordingly in navigation scenarios, resulting in technical problems such as poor user experience and reduced safety of smart devices.
[0059] To this end, the present application proposes a smart device control method, a smart device and a storage medium.
[0060] It should be understood that the smart devices of the present application may include driving devices, smart vehicles, robots, aircraft and other devices, without specific limitation.
[0061] See attached Figure 1 , Figure 1 It is a flowchart of the main steps of a smart device control method according to an embodiment of the present application.
[0062] like Figure 1 As shown, the smart device control method in the embodiment of the present application mainly includes the following steps S10 to S50.
[0063] Step S10: Acquire environmental information and a first map of the smart device.
[0064] The environmental information may be information related to the environment of the current location of the smart device, such as current positioning information and road information of the road where the smart device is currently located, etc., without limitation.
[0065] Road information may include road name, road grade, road structure, etc.
[0066] The first map refers to a personalized map representation that is pre-built on the basis of the second map and combined with the user's historical travel information and stored on the smart device. The map contains geographic spatial information and the user's historical travel information, and can provide map views, navigation guidance, and user historical path selection services independently of an Internet connection.
[0067] The second map may be a common digitized map or a high-precision map pre-stored locally.
[0068] Step S20: Acquire a target path based on the environmental information and the first map.
[0069] The target path is the estimated driving path of the smart device obtained through prediction.
[0070] Step S30: obtaining first bump information corresponding to the target path based on the environmental information.
[0071] The first bump information is the uneven road conditions that the vehicle may encounter ahead of the vehicle, which may cause the vehicle to vibrate or shake, affecting the ride comfort and driving safety. For example, potholes, manhole covers, sharp turns, slopes, bridges, etc. may be examples of the first bump information.
[0072] Step S40: Match the first bump information with the target path based on the environmental information to obtain a first matching result.
[0073] The purpose of matching bump information with the target path is to be able to predict and respond to bumpy sections that may be encountered during the driving of the smart device, thereby improving safety and riding comfort.
[0074] Step S50: Intelligently control the smart device based on the first matching result.
[0075] Specifically, taking the vehicle as an example, the suspension stiffness, damping and height can be adjusted in real time according to the first matching result (bumping information in front of the smart device) to reduce body vibration and improve ride comfort and stability. If severe bumps or poor road conditions are predicted ahead, the vehicle can automatically slow down to avoid severe vibrations and reduce the risk of damage to the tires and chassis. Or based on real-time and predicted bump information, the smart vehicle can re-plan the route to avoid bumpy sections and improve driving efficiency and comfort.
[0076] Based on the above steps S10 to S50, firstly, the environment information and the first map of the smart device are obtained; the target path is obtained based on the environment information and the first map; the first bump information corresponding to the target path is obtained based on the environment information; the first bump information is matched with the target path based on the environment information; and the smart device is intelligently controlled based on the first matching result. By obtaining the bump information in advance, the smart device can prepare or adjust the path in advance to avoid accidents and improve the safety of operation; at the same time, predicting the bumps and adjusting the movement trajectory or suspension settings of the device can reduce the discomfort of the user when encountering bumps and improve the user's riding experience.
[0077] The above steps S10 to S50 are further explained below.
[0078] Specifically, the first map in the above step S10 can be implemented through the following steps S101 to S105.
[0079] Step S101: Obtain historical travel information of the smart device.
[0080] Historical travel information is a travel file generated by the smart device during previous driving. For example, when the smart device is driving, it records the device positioning information, road information, vehicle status, etc. in sequence at preset distance intervals and stores the obtained travel file. The device positioning information at least includes latitude and longitude and heading angle, and the road information at least includes road name, road grade and road structure. The preset distance interval can be one meter, two meters, three meters, etc., without limitation.
[0081] It is understandable that the trip file can also be triggered to store when some important events or information are detected, such as encountering bumpy information, or special road conditions such as sharp turns, long downhill slopes, etc.
[0082] Step S102: dividing the second map into a plurality of first map blocks.
[0083] The second map may be a common digitized map or a high-precision map that is pre-built or acquired.
[0084] The first map block refers to a smaller map unit obtained by dividing the first map according to certain rules. The first map block usually contains information of a specific geographical area in the first map.
[0085] Specifically, the first map may be segmented according to a preset segmentation threshold to obtain a plurality of first map blocks. The preset segmentation threshold may be a pre-set value, which may be adjusted according to actual application scenarios. For example, 1 square kilometer, 2 square kilometers, 3 square kilometers, etc. may be used as examples of the preset segmentation threshold, which is not limited thereto.
[0086] Step S103: Creating a road file and a node file corresponding to the road node in the first map block based on the historical travel information.
[0087] The road file is used to store and represent the basic information of the roads in the first map block, including but not limited to the road geometry (such as the latitude and longitude coordinates of the starting and ending points, and the way these points are connected by line segments or curves), road type (such as expressway, ordinary road, pedestrian path, etc.), road name, directionality (one-way or two-way), road grade (such as main road, secondary road, branch road, etc.), and possible traffic restrictions (such as speed limit, no turn, etc.). Road files can be stored in vector data format to facilitate spatial query and analysis.
[0088] The node file is used to store and represent the information of the road nodes in the first map block and the adjacent or link relationship between these road nodes. In a road network, a node usually represents an intersection, endpoint or other important connection point of a road. The node file records the location (latitude and longitude) of each node, possible intersection types (such as crossroads, T-junctions, roundabouts, etc.), and a list of roads or nodes connected to it (i.e., adjacent relationships).
[0089] Regarding the creation of road files, the road information related to each first map block can be extracted from the historical travel information according to the positioning information of the smart device, and the road information in each first map block can be segmented and stored as multiple road files according to the road information (such as road name, road grade and road structure).
[0090] For the creation of node files, firstly, a clustering algorithm can be used to cluster the trajectory points; then the trajectory points are mapped to the road network corresponding to the first map block; intersections or turning points can be identified by looking for sudden changes in direction, slowdowns, or changes in road information in the trajectory points; connections between nodes are established to determine which nodes are connected by which roads, and the node files of the road nodes are obtained.
[0091] Step S104: Create a route file based on the historical travel information, the road file and the node file.
[0092] A path file is a file that records and describes the specific route or track that a smart device takes from one location to another.
[0093] Specifically, it is necessary to map the trajectory points in the trip file to the road network described by the road file; divide the mapped trajectory into multiple sections according to road changes (such as turns, entering different roads); for each section, extract the corresponding road information from the road file, including road ID, type, name, etc.; identify the nodes at both ends of each section; find the nodes corresponding to the two ends of each section in the node file, and establish the association between them and the road; construct the path file based on the extracted road and node information. The path file should contain the sequence of all roads passed by this trip, as well as the node information at both ends of each road.
[0094] In addition, the created path file can be saved in an appropriate format (such as JSON, XML, CSV, etc.), without specific limitation.
[0095] Step S105: Establish a mapping relationship between road nodes and path files to obtain a first map.
[0096] The mapping relationship refers to the process of matching specific road nodes (such as intersections, junctions and other key locations) with path files (data files containing road information) in the map data structure, so that each road node can correspond to the specific road segment information in the path file.
[0097] Specifically, in the route file, an explicit association with a start node and an end node is established for each road or road segment according to the trip information.
[0098] In a specific implementation of the present application, the method further includes: matching the path file with the historical path in the path file library; and updating the path file library based on the matching result.
[0099] The path file library is a data set that stores multiple path files, each of which contains information about a specific path, such as the geometry, attributes, and road nodes of the road. The path file library is used to save historical paths, which can be used to match new path files to support path planning, navigation, and control functions.
[0100] Specifically, after obtaining a new route file for this trip, it will be matched with the historical routes in the route file library, and the route file library will be updated based on the matching results, such as adding new routes, replacing old routes, or adjusting the weight coefficient of the route. The weight coefficient is a numerical value used to adjust or quantify the importance of different factors on the route (such as time, space, distance, cost, etc.). The adjustment of the weight coefficient is based on multiple factors such as the frequency of use of the route, road conditions, traffic conditions, and user usage habits.
[0101] By pre-building the first map, smart devices can still have a basic understanding of road conditions in the absence of real-time navigation instructions, which helps smart devices predict bumpy roads or sharp turns in advance, so as to take preventive measures and improve driving safety.
[0102] The above is a further description of step S10 , and the following is a further description of step S20 .
[0103] Specifically, the above step S20 is implemented through the following steps S201 to S204.
[0104] Step S201: Acquire at least one first path based on environmental information and a first map.
[0105] The first path is a possible path obtained after preliminary screening based on environmental information and the first map.
[0106] Specifically, step S201 can be implemented through the following steps S2011 to S2015.
[0107] Step S2011: Obtain a second map block in the first map based on environmental information.
[0108] The environmental information may include the current location information and road information of the smart device. Specifically, in this embodiment, the second map block where the smart device is currently located can be obtained in the pre-built first map according to the current location information and road information, and the second map block includes a road file and a node file.
[0109] The second map block refers to a map unit obtained by adding the user's historical travel information to the first map block.
[0110] Step S2012: Determine the current position of the smart device in the second map block based on the environmental information.
[0111] Specifically, the real-time positioning information and road information are matched with the road information of the second map block to determine the current position of the smart device in the second map block.
[0112] Step S2013: Obtain the road node information corresponding to the current position.
[0113] Since each second map block includes a road file and a node file, the road node with the highest correlation with the smart device can be obtained according to the current location of the smart device.
[0114] Step S2014: Acquire other road node information that is linked to the road node information.
[0115] Specifically, other road nodes that are linked to the road node with the highest correlation with the smart device can be queried in the node file.
[0116] Step S2015: Acquire at least one first path based on the road node information and other road node information.
[0117] At least one first path can be obtained by combining the road node closest to the smart device, other road node information, and link relationships between road nodes.
[0118] In a specific embodiment of the present application, preset rules can also be used to screen at least one first path, and subsequent predictions of the predicted path can be achieved on this basis to pre-filter out a portion of the first paths that do not meet the preset conditions, thereby increasing the prediction accuracy of the path.
[0119] The preset rules may include traffic rules (such as traffic lights, road speed limits, etc.), road types (such as curvature of expressways, average speed of urban roads, etc.), lane information (such as right-turn lanes cannot go straight), etc., and there are no specific limitations on this.
[0120] Step S202: Obtain the predicted probability of at least one first path using a probability model.
[0121] A probability model is a mathematical framework for describing random phenomena, which uses probability theory to express uncertainty and randomness. For example, a Markov model can be used as an example of the probability model.
[0122] The Markov model is a statistical model used to describe the changes in a system state sequence, in which the state at the next moment depends only on the current state and has nothing to do with the previous state. Next, the specific implementation process of this step is explained using the Markov model as an example of a probability model.
[0123] The predicted probability refers to the probability of the first path actually occurring in the future as calculated by the probability model. This probability value is usually between 0 and 1, where 0 means that the event is almost impossible to occur and 1 means that the event is almost certain to occur.
[0124] First, determine all possible state sets in the Markov model. The state set represents the nodes or road segments in the first map. Then, obtain the historical data related to the path prediction, group the historical data, and count the frequency of transitions from different states to other states. Calculate the transition probability based on the frequency to form a transition probability matrix. Determine the probability distribution of the initial state based on the current environmental information. Based on the properties of the Markov chain, the recursive formula can be used to calculate the state probability at any future moment. Specifically, start from the initial state and use the transition probability matrix to gradually calculate the state probability at each future moment.
[0125] Step S203: Acquire a second path based on the environmental information and the neural network model.
[0126] The second path refers to the recommended path obtained by using the neural network model prediction.
[0127] Exemplarily, a recurrent neural network (RNN) can be used as an example of the neural network model. The recurrent neural network learns the long-term dependencies between nodes in the historical path, and uses the driving paths with displacement sequence relationships stored according to the historical driving trajectory as the training set of the RNN network to train the model to predict unknown paths. The RNN network can process sequence data of any length and has a certain generalization ability.
[0128] Specifically, the second path can be obtained by inputting the trajectory data of the current smart device within a preset range into the trained RNN model, wherein the preset range can be a pre-set specific numerical range, such as 1km, 2km, 3km, etc. from the current location of the smart device.
[0129] Step S204: Determine the target path based on the predicted probability and the second path.
[0130] Specifically, the predicted probability of the first path obtained by the probability model and the second path predicted by the neural network model are matched, and the path that intersects the two and has the highest probability is used as the target path, thereby improving the accuracy of the first prediction precision.
[0131] The above is a further description of step S20 , and the following is a further description of step S30 .
[0132] Specifically, when the target path is obtained in step S20, the probability of obtaining the target path is determined to be a familiar path when the probability is greater than or equal to a preset probability threshold, otherwise the path is determined to be a new path.
[0133] The preset probability threshold may be a pre-set probability value, which may be adaptively adjusted according to actual application scenarios. For example, 75%, 80%, 90%, etc. may be used as examples of the preset probability threshold.
[0134] When the target path is a familiar path, the above step S30 can be implemented through the following steps S301 to S304.
[0135] Step S301: Obtaining a path loading range based on environmental information.
[0136] The path loading range refers to the distance range of the predicted path that is pre-set according to the road type and loaded into the system for subsequent processing. For example, the path loading range for expressways can be 8km, 9km, 10km, etc., the path loading range for elevated roads can be 3km, 4km, 5km, etc., and the path loading range for other roads can be 1km, 2km, etc.
[0137] Step S302: acquiring a third path based on the path loading range, wherein the third path is a path of the target path within the path loading range.
[0138] Specifically, the third path can be obtained by loading the target path according to the preset path loading range.
[0139] Step S303: performing thinning processing on the third path to obtain a fourth path.
[0140] Thinning, also known as data downsampling or data sparsification, is a data preprocessing technique that is mainly used to reduce the number of data points in a data set while retaining the original characteristics and trends of the data as much as possible.
[0141] Specifically, the Douglas-Pudo algorithm can be used to thin the trajectory points of the third path to reduce the amount of searching for bump information. Exemplarily, when performing trajectory thinning, the loaded trajectory is first segmented according to the road information to ensure that the first point when the road information changes is retained on the thinned curve, and then each segmented trajectory is thinned, and finally the thinned trajectories are spliced to obtain the fourth path.
[0142] Step S304: obtaining first jolt information based on the fourth path.
[0143] Specifically, the fourth path may be matched with a pre-built jolt information library to obtain the first jolt information.
[0144] When the target path is a new road, the first bump information can be obtained by directly matching the positioning information and road information of the smart device with the pre-built bump information library.
[0145] The bump information database is a pre-stored data set or system used to store and manage information about road bumps. This information usually comes from a variety of data sources, including but not limited to road measurement data, driving records, user feedback, etc. The bump information database records in detail the bumpiness, location, type (such as potholes, cracks, undulations, etc.) and possible impacts (such as speed limits, wear and tear, etc.) of different road sections.
[0146] The search for bumpy information can be implemented on the smart device side or on the cloud side, and there is no specific limitation on this. In addition, when any of the following conditions is met, a new bumpy information search request needs to be regenerated: 1) the road name has changed; 2) the driving distance from the last generated route exceeds a certain range of the last generated route, such as 70%, 80%, or 90%. When the smart device side or the cloud side receives a new bumpy information search request, it searches for bumpy information consistent with the current road name within a preset radius with the current location of the smart device as the center of the circle. The preset radius is a pre-set value, such as 3km, 4km, 5km, etc. can be used as examples of preset radii.
[0147] The above is a further description of step S30 , and the following is a further description of step S40 .
[0148] Specifically, when the target path is a familiar path, the above step S40 is implemented through the following steps S401 to S403.
[0149] Step S401: Match the first bump information with the target path to obtain a first relative position of the first bump information in the target path.
[0150] The first relative position refers to the specific position information of the first bump information relative to the target path. The first relative position information is relative because it is not based on the absolute coordinates of the global positioning system (GPS), but based on the length, direction or relative position of a specific marking point of the target path itself.
[0151] Specifically, the first bump information is first matched with the target path, specifically by calculating the spherical distance and heading angle deviation between each bump information and each point in the first predicted trajectory, and determining the relative position (first relative position) of each bump information in the target path through the deviation of the spherical distance and heading angle.
[0152] Step S402: Acquire a second relative position of the smart device in the target path based on the environmental information.
[0153] The second relative position refers to the specific position of the smart device in the target path determined by considering environmental information. The second relative position information is relative because it is not based on the absolute coordinates of the global positioning system (GPS), but on the length, direction or relative position of a specific marker point of the target path itself.
[0154] Specifically, the relative position (second relative position) of the smart device in the target path is determined according to the positioning information of the current smart device in the environmental information.
[0155] Step S403: updating the distance between the first bump information and the second relative position based on the first relative position and the second relative position.
[0156] The distance between the first bump information and the second relative position refers to the relative distance between the first bump information and the second relative position of the smart device on the target path, that is, the distance from the current position of the smart device to the expected bump point ahead of the smart device.
[0157] Since the bump information within the preset time range is obtained based on the positioning information corresponding to the starting time of the time range, as the smart device travels, the bump information closest to the smart device and the distance between the two can be determined based on the device's current positioning information, and the distance of subsequent bump information along the target path from the device's current position can be updated based on the distance between the two.
[0158] Specifically, when the target path is a new road, the above step S40 is implemented through the following steps S404 to S406.
[0159] Step S404: acquiring second bump information based on the environment information and the first bump information, where the second bump information is the first bump information within a preset range along the target path direction.
[0160] The preset range may be a preset heading angle less than a preset angle threshold and a distance less than a preset distance threshold, wherein the selection of the preset angle threshold and the preset distance threshold for different road levels may be adaptively adjusted according to the actual application scenario, and is not limited thereto. For example, 28°, 29°, 30°, etc. may be used as examples of the preset angle threshold, and 28m, 29m, 30m may be used as examples of the preset distance threshold.
[0161] Exemplarily, based on the deviation of the absolute heading angle and relative heading angle between each bump point in the first bump information and the current position, bump information with a heading angle <30° and a straight-line distance less than 30m in the direction of the target path can be screened out as the second bump information.
[0162] Step S405: determining the distance between the second bump information and the smart device based on the second bump information and the environment information.
[0163] The distance between the second bump information and the smart device refers to the relative distance between the second bump information and the smart device.
[0164] Specifically, after the second bump information along the target path direction is determined, the distance between the second bump information and the smart device is further determined according to the second bump information and the current positioning information of the device.
[0165] Step S406: sorting the second jolt information based on the distance.
[0166] Specifically, the second bump information is sorted along the vehicle's driving path to notify the smart device of the bump information closest to it and the subsequent bump information that may appear, so as to achieve intelligent control of the smart device and increase the user's comfort experience.
[0167] In one embodiment, Figure 2 As shown, the smart device control method of the present application is described in detail by taking a vehicle as an example of a smart device.
[0168] Step S1: Construct a vehicle-side map. For the specific construction method, please refer to the aforementioned steps S101 to S105 and will not be repeated here.
[0169] Step S2: predict the target path. For specific prediction methods, please refer to the aforementioned steps S201 to S204, which will not be described in detail here.
[0170] Step S3: Determine whether the path is a familiar road or a new road based on the probability corresponding to the vehicle's driving path. If it is a familiar road, execute the following steps S4 to S7 and step S11; if it is a new road, execute the following steps S8 to step S11.
[0171] Step S4: Load the target path in the familiar path mode.
[0172] Step S5: Thin out the target path to reduce the amount of data.
[0173] Step S6: Send the thinned data to the cloud for search to obtain the first turbulence information.
[0174] Step S7: Match the first bump information with the target path.
[0175] Step S8: Send a bump information search request in the familiar road mode.
[0176] Step S9: The cloud obtains first bump information by searching for bump information within a preset range from the current position along the target path.
[0177] Step S10: Match the first bump information with the current positioning information and road information.
[0178] Step S11: Intelligently control the vehicle according to the matching result.
[0179] By building a local map on the vehicle side based on historical data, such as vehicle positioning and road information, combined with the vehicle's current location and road information, a hybrid model consisting of a Markov model, a recurrent neural network (RNN) and a rule model is used to predict the driving path; based on the cloud-based bumpy database, bumpy events are searched along the target path, and finally the bumpy event search results are screened and matched according to the current location and road information, so that the vehicle can perceive the bumpy events ahead in advance without turning on the navigation, and finally achieves the advance perception of bumpy events and suspension prediction control with performance equivalent to that under navigation path planning. In this way, even if the user does not turn on the navigation, such as in the commuting section or familiar road mode, the user can still get the same vehicle control and comfort experience as when the navigation is turned on; the new road mode is also available, truly realizing the full-scenario use of intelligent functions related to vehicle control and comfort.
[0180] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effect of the present application, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present application.
[0181] Furthermore, the present application also provides a smart device control device.
[0182] See attached Figure 3 , Figure 3 It is a main structural block diagram of an intelligent device control device according to an embodiment of the present application.
[0183] like Figure 3 As shown, the intelligent device control apparatus in the embodiment of the present application mainly includes a first acquisition module 31, a second acquisition module 32, a third acquisition module 33, a matching module 34 and a control module 35. In some embodiments, one or more of the first acquisition module 31, the second acquisition module 32, the third acquisition module 33, the matching module 34 and the control module 35 can be combined into one module.
[0184] In some embodiments, the first acquisition module 31 may be configured to acquire environmental information and a first map of the smart device.
[0185] The second acquisition module 32 may be configured to acquire a target path based on the environmental information and the first map.
[0186] The third acquisition module 33 may be configured to acquire first bump information corresponding to the target path based on the environmental information.
[0187] The matching module 34 may be configured to match the first bump information with the target path based on the environmental information;
[0188] The control module 35 may be configured to intelligently control the smart device based on the matching result.
[0189] In one implementation, the description of the specific implementation functions can refer to steps 10 to 50.
[0190] The above-mentioned intelligent device control device is used to execute Figure 1 The embodiments of the intelligent device control method shown in the figure are similar in their technical principles, technical problems solved and technical effects produced. Technicians in this technical field can clearly understand that for the convenience and conciseness of description, the specific working process and related instructions of the intelligent device control device can refer to the contents described in the embodiments of the intelligent device control method, which will not be repeated here.
[0191] It is understood by those skilled in the art that all or part of the processes in the method for implementing the above-mentioned embodiment of the present application can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium, etc. that can carry the computer program code.
[0192] Furthermore, the present application also provides an intelligent device, which may include at least one processor; and a memory connected to the at least one processor; wherein a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the intelligent device control method described in any of the above embodiments is implemented. Figure 4 As shown, Figure 4 exemplarily shows the structure of a smart device, which includes a processor 100 and a memory 200.
[0193] Furthermore, the present application also provides a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present application, the computer-readable storage medium can be configured to store a program for executing the intelligent device control method of the above-mentioned method embodiment, and the program can be loaded and run by the processor to implement the above-mentioned intelligent device control method. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present application. The computer-readable storage medium can be a memory device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present application is a non-temporary computer-readable storage medium.
[0194] Further, it should be understood that since the setting of each module is only for illustrating the functional units of the device of the present application, the physical devices corresponding to these modules may be the processor itself, or a part of the software in the processor, a part of the hardware, or a part of the combination of software and hardware. Therefore, the number of each module in the figure is only schematic.
[0195] It is understood by those skilled in the art that each module in the device can be adaptively split or merged. Such splitting or merging of specific modules will not cause the technical solution to deviate from the principle of the present application, and therefore, the technical solutions after splitting or merging will fall within the protection scope of the present application.
[0196] The relevant user personal information that may be involved in the various embodiments of this application is strictly in accordance with the requirements of laws and regulations, following the principles of legality, legitimacy and necessity, based on the reasonable purposes of business scenarios, to process the personal information that users actively provide during the use of products / services or generated due to the use of products / services, as well as the personal information obtained with the user's authorization.
[0197] The user personal information processed by this application will vary depending on the specific product / service scenario, and will be based on the specific scenario in which the user uses the product / service. It may involve the user's account information, device information, driving information, vehicle information or other related information. The applicant will treat the user's personal information and its processing with a high degree of diligence.
[0198] This application attaches great importance to the security of user personal information and has taken reasonable and feasible security protection measures that meet industry standards to protect user information and prevent personal information from being accessed, disclosed, used, modified, damaged or lost without authorization.
[0199] So far, the technical solutions of the present application have been described in conjunction with the specific implementations shown in the accompanying drawings, but it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific implementations. Without departing from the principles of the present application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present application.
Claims
1. A method for controlling an intelligent device, characterized in that: The method comprises: Acquire environmental information and a first map of the smart device; Acquire a target path based on the environmental information and the first map; Acquire first bump information corresponding to the target path based on the environmental information; matching the first bump information with the target path based on the environmental information; The smart device is intelligently controlled based on the first matching result.
2. The intelligent device control method according to claim 1, characterized in that: The first map is constructed by the following steps: Obtaining historical travel information of the smart device; Splitting the second map into a plurality of first map blocks; Creating a road file and a node file corresponding to a road node in the first map block based on the historical travel information; Creating a route file based on the historical travel information, the road file and the node file; A mapping relationship between the road nodes and the path file is established to obtain the first map.
3. The intelligent device control method according to claim 2, characterized in that: The method further comprises: Matching the path file with the historical paths in the path file library; The path file library is updated based on the second matching result.
4. The intelligent device control method according to claim 1, characterized in that: The acquiring a target path based on the environmental information and the first map includes: Acquire at least one first path based on the environmental information and the first map; Obtaining a predicted probability of the at least one first path using a probability model; Acquire a second path based on the environmental information and the neural network model; The target path is determined based on the predicted probability and the second path.
5. The intelligent device control method according to claim 4, characterized in that: The first map includes a plurality of second map tiles; The acquiring at least one first path based on the environmental information and the first map includes: Acquire a second map block in the first map based on the environmental information; Determining a current position of the smart device in the second map block based on environmental information; Obtaining road node information corresponding to the current position; Acquire other road node information that is linked to the road node information; The at least one first path is acquired based on the road node information and the other road node information.
6. The intelligent device control method according to claim 1, characterized in that: The acquiring first bump information corresponding to the target path based on the environmental information includes: Acquire a path loading range based on the environmental information; Acquire a third path based on the path loading range, wherein the third path is a path of the target path within the path loading range; Performing thinning processing on the third path to obtain a fourth path; The first bump information is acquired based on the fourth path.
7. The intelligent device control method according to claim 1, characterized in that: The matching the first bump information with the target path based on the environmental information includes: Matching the first bump information with the target path to obtain a first relative position of the first bump information in the target path; Acquire a second relative position of the smart device in the target path based on the environmental information; The distance between the first bump information and the second relative position is updated based on the first relative position and the second relative position.
8. The intelligent device control method according to claim 1, characterized in that: The matching the first bump information with the target path based on the environmental information includes: acquiring second bump information based on the environment information and the first bump information, wherein the second bump information is first bump information within a preset range along a target path direction; determining a distance between the second bump information and the smart device based on the second bump information and the environment information; The second bump information is sorted based on the distance.
9. A smart device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores a computer program, and when the computer program is executed by the at least one processor, the intelligent device control method according to any one of claims 1 to 8 is implemented.
10. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the intelligent device control method according to any one of claims 1 to 8.
