WO2023065798A1 - Dynamic road event processing method and apparatus, device, and medium - Google Patents

Abstract

Disclosed herein are dynamic road event processing method and apparatus, a device, and a medium. The dynamic road event processing method comprises: acquiring unstructured dynamic road data from at least one data source; identifying from the dynamic road data a road location corresponding to where a dynamic road event occurs; and establishing an association between a road and the dynamic road event according to the road location.

Description

Method, device, equipment and medium for processing road dynamic events

This application claims priority to a Chinese patent application with application number 202111233859.3 filed with the China Patent Office on October 22, 2021, the entire contents of which are incorporated herein by reference.

technical field

The present disclosure relates to the technical fields of computer and image processing, such as artificial intelligence, automatic driving and intelligent transportation technologies.

Background technique

When people travel, they rely more and more on electronic maps. Electronic maps can be used for route navigation and road condition inquiries. Therefore, the accuracy and real-time performance of information presented by electronic maps has attracted more and more attention.

A large amount of data in the electronic map can be collected and generated in advance and presented to users. However, road dynamic events are the most unpredictable variables on urban roads, and these events will seriously affect the operational efficiency of society. Road dynamic events mainly refer to sudden and short-term events on the road, which may affect the normal traffic of the road. For example, traffic accidents, regulatory road closures, etc.

Due to the sporadic and unpredictability of road dynamic events, it is difficult for related technologies to efficiently produce this part of data through directional intelligence collection or mining, which affects the accuracy and real-time performance of road status data and affects people's travel.

Contents of the invention

The present disclosure provides a method, device, equipment and medium for processing road dynamic events, so as to effectively acquire road dynamic events.

According to a first aspect of the present disclosure, a method for processing road dynamic events is provided, the method including:

obtaining unstructured road dynamics data from at least one data source;

identifying a road location corresponding to the road dynamic event that occurs from the road dynamic data;

According to the road position, the association between the road and the road dynamic event is established.

According to a second aspect of the present disclosure, a processing device for road dynamic events is provided, including:

The dynamic data acquisition module is configured to acquire unstructured road dynamic data from at least one data source;

A road position identification module, configured to identify the road position corresponding to the occurred road dynamic event from the road dynamic data;

The location association module is configured to establish an association between the road and the road dynamic event according to the location of the road.

According to a third aspect of the present disclosure, an electronic device is provided, including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the above-mentioned method for processing road dynamic events.

According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to make the computer execute the above-mentioned method for processing road dynamic events.

According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned method for processing road dynamic events is implemented.

Description of drawings

FIG. 1A is a schematic flowchart of a method for processing road dynamic events provided by an embodiment of the present disclosure;

Fig. 1B is a schematic diagram of road surface water provided by an embodiment of the present disclosure;

Fig. 1C is a schematic diagram of a non-accumulated road surface provided by an embodiment of the present disclosure;

FIG. 1D is a schematic diagram of an electronic map provided by an embodiment of the present disclosure;

FIG. 1E is a schematic diagram of route planning provided by an embodiment of the present disclosure;

FIG. 1F is a schematic diagram of an approaching arrival provided by an embodiment of the present disclosure;

FIG. 1G is a schematic diagram of a keyword search result provided by an embodiment of the present disclosure;

FIG. 1H is a schematic diagram of a road database record provided by an embodiment of the present disclosure;

FIG. 2 is a schematic flowchart of another method for processing road dynamic events provided by an embodiment of the present disclosure;

Fig. 3 is a schematic flowchart of another method for processing road dynamic events provided by an embodiment of the present disclosure;

FIG. 4A is a schematic flowchart of another method for processing road dynamic events provided by an embodiment of the present disclosure;

Fig. 4B is a schematic diagram of a traffic sign provided by an embodiment of the present disclosure;

Fig. 5 is a schematic flowchart of another method for processing road dynamic events provided by an embodiment of the present disclosure;

Fig. 6 is a schematic structural diagram of a device for processing road dynamic events provided by an embodiment of the present disclosure;

Fig. 7 is a schematic structural diagram of a dynamic data acquisition module provided according to an embodiment of the present disclosure;

Fig. 8 is a schematic structural diagram of another device for processing road dynamic events according to an embodiment of the present disclosure;

FIG. 9 is a schematic structural diagram of an event type determination module provided according to an embodiment of the present disclosure;

Fig. 10 is a schematic structural diagram of a road position identification module provided according to an embodiment of the present disclosure;

Fig. 11 is a schematic structural diagram of an information identification unit provided according to an embodiment of the present disclosure;

Fig. 12 is a schematic structural diagram of another road location identification module provided according to an embodiment of the present disclosure;

Fig. 13 is a schematic structural diagram of an information matching unit provided according to an embodiment of the present disclosure;

Fig. 14 is a schematic structural diagram of a data matching subunit provided according to an embodiment of the present disclosure;

Fig. 15 is a schematic structural diagram of another data matching subunit provided according to an embodiment of the present disclosure;

Fig. 16 is a schematic structural diagram of another device for processing road dynamic events according to an embodiment of the present disclosure;

Fig. 17 is a schematic structural diagram of a location association module provided according to an embodiment of the present disclosure;

Fig. 18 is a schematic structural diagram of another device for processing road dynamic events according to an embodiment of the present disclosure;

Fig. 19 is a schematic structural diagram of an event presentation module provided according to an embodiment of the present disclosure;

Fig. 20 is a schematic structural diagram of another device for processing road dynamic events according to an embodiment of the present disclosure;

Fig. 21 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.

Detailed ways

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Only the parts relevant to the present disclosure are shown in the drawings. Before discussing the exemplary embodiments, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flow diagrams depict operations (or steps) as sequential processing, many of the operations may be performed in parallel, concurrently, or simultaneously. Additionally, the order of multiple operations can be rearranged. The process may be terminated when its operations are complete, but may also have additional steps not included in the figure.

Fig. 1A is a schematic flowchart of a method for processing road dynamic events provided by an embodiment of the present disclosure. This embodiment is applicable to the situation of processing road dynamic events, and the method can be implemented by a processing device for road dynamic events provided by an embodiment of the present disclosure. For execution, the device may be implemented in software and/or hardware, and the device may be configured in an electronic device capable of data processing such as a server.

As shown in FIG. 1A, a method for processing a road dynamic event provided by an embodiment of the present disclosure includes the following:

S110. Acquire unstructured road dynamic data from at least one data source.

Unstructured road dynamic data refers to data that does not have a definite field structure, does not have a predefined data model, and is inconvenient to use two-dimensional logical tables of the database to represent data, such as text, pictures, and multi-type reports, etc., or can be It is image and video information, etc., which is not limited in this embodiment.

From data sources such as social networking sites, news media or cameras, information is collected through keyword search or active reporting to obtain irregular and unstructured road dynamic data.

The data sources include at least one of the following: news web pages, social networking sites and surveillance cameras. The form of the road dynamic data includes at least one of the following: text, image, audio and video.

Road dynamic data refers to the real-time change data of the road state, especially the road traffic state, and extracts the information that can be identified in the area where the event occurred. In one embodiment, there are three types of road dynamic data, which are text, picture and video respectively. The above three forms of road dynamic data can be processed and information can be extracted. The extracted information can be, for example, traffic signs and merchant signboards , or may be buildings, roads, etc., which are not limited in this embodiment.

Collect and obtain data directly or indirectly through news webpages, social networking sites, and surveillance cameras, such as retrieving the content of social networking sites, and collecting related information such as the retrieved content together. The corresponding obtained road dynamic data can be as follows: landslides”, “fog”, “mudslides” and “road collapses”, etc.

Exemplarily, the service platform may regularly or subscribe to search for "landslide" through keywords, search for relevant content and release time, and obtain information related to "landslide". The advantage of this setting is that information can be obtained through multiple methods, and unstructured data can be collected in real time and comprehensively.

Obtaining unstructured road dynamic data from at least one data source includes at least one of the following: searching or subscribing to at least one data source to obtain unstructured road dynamic data matching event keywords; receiving Unstructured road dynamics data actively reported by at least one data source.

Event keywords refer to hot search keywords caused by accidental events, which can accurately find relevant information according to information differences; active reporting means that when an event occurs, someone actively sends data in real time at the first time, for example, you can By receiving data actively reported by users or specialized institutions on specially set webpages and platforms.

There are many ways to obtain unstructured road dynamic data from at least one data source, for example, search through the keywords of the event, and obtain relevant information corresponding to the event associated with the keyword, or through active reporting , for data reception, after the witnesses witness the road dynamic event, they describe and record pictures, texts or videos on multiple social networking sites. The benefit of this setup is that multiple sources gather information to accurately determine dynamic events.

After obtaining the unstructured road dynamic data from at least one data source, it also includes: according to the road dynamic data, determining the event category of the road dynamic event that occurs; After the road position corresponding to the dynamic event, the method further includes: establishing an association between a road and an event category of the road dynamic event according to the road position.

Road dynamic events refer to things that happen in real time on the road; event categories such as heavy rain road closures and road subsidence are categories that road dynamic events are divided into according to event content, such as: road closures, flooding, or traffic control categories, the present embodiment This is not limited.

When a road dynamic event occurs, according to the provided dynamic data, that is, the real-time road change information, the event category is determined, what the event is, and key information is extracted for indexing. The advantage of this setting is that when there are road dynamic events, the event type can be clarified when searching, and the search results are accurate.

According to the road dynamic data, the way of determining the event category of the road dynamic event that occurs includes at least one of the following: identifying event keywords from the text of the road dynamic data, and determining the occurred road dynamic event according to the event keywords The event category of the road dynamic data; input the image of the road dynamic data into the event classification model, and perform event classification on the content corresponding to the image of the road dynamic data, so as to determine the event category of the road dynamic event that occurs.

Text includes original text and text recognized from audio or video.

According to the event keywords, the event category is determined. For the text road dynamic data, according to the keywords, the keyword table is used to search to determine the event category; at the same time, the image can be used to identify the text in the picture to determine the event type. For example, when searching for event keywords such as "flooding", there may be "flooding", "flooding" or "flooding", etc., and the search requirements are expanded to determine the event type. The advantage of this setting is to increase the coverage of the channel and predict the road dynamics.

The event category includes at least one of the following: road closure, landslide, heavy fog, flooding, road collapse and mudslide. The advantage of this setting is that it covers a variety of data and clarifies road dynamic events.

S120. From the road dynamic data, identify a road position corresponding to the occurred road dynamic event.

The road location refers to the information that can characterize the location of the road, such as the location information that can locate the road in the electronic map, for example, it can be the location information in the form of road name, road building sign, coordinates, etc., which is not discussed in this embodiment. To limit.

From the road dynamic data, the road location corresponding to the road dynamic event occurred is identified according to the road name, road building signs and location coordinates.

S130. Establish an association between a road and the road dynamic event according to the road position.

According to the location of the road, the location of the road is associated with the dynamic events that occur on the road. It may be to associate road dynamic events with roads in the electronic map, or, for databases related to roads stored in other forms, road dynamic events may also be associated and stored for subsequent operations. For example, a road database established for road maintenance can be used as a basis for road maintenance after associated storage of road dynamic events.

According to the road position, establishing the association between the road and the road dynamic event includes:

According to the road position, store the road dynamic event in association with the road in the electronic map; determine the road position according to the road dynamic data collected by the road, and then compare the road dynamic event occurring in the road position with the road in the electronic map Locations are mapped and stored associatively.

Exemplarily, when a landslide event occurs on road A, based on the road information released by user a, the road dynamic event that occurred is identified, and the service platform corresponds the road dynamic event to road A in the electronic map, and Landslide events that occur are stored.

The method further includes: presenting the associated road dynamic events of the roads in the presentation area in response to the user's electronic map presentation request.

A presentation request refers to a map presentation request initiated by a user to an electronic map-related program, for example, when route planning is required, or when a point of interest in an electronic map is inquired.

When the user sends a request to the electronic map to apply for a road, the electronic map will directly display the relevant road dynamic events on the road. The advantage of this setting is that it allows the user to know the road conditions of the road at a glance, judge the road conditions in time, and choose whether to continue driving on the road according to his driving situation.

Exemplarily, when the keyword "logged water" is searched on a social networking site, a small video content (as shown in Figure 1B) can be quickly obtained. Figure 1B is a schematic diagram of a pavement area provided by an embodiment of the present disclosure, and the information is obtained through text analysis: The name of the administrative division is "Lujiang County, Anhui Province"; through video content analysis, it is found that there is a signboard content "so-and-so clothing" in a specific frame, as shown in the left picture of Figure 1B; Figure 1C is a road without water accumulation provided by the embodiment of the present disclosure Schematic diagram, by searching the database, accurately matching the result "so-and-so clothing" and attaching road data (as shown in the signboard circled by a black frame in Figure 1C), to complete the production and production of dynamic event data; the produced road dynamic data can be flexibly It is used in the map application program (Application, APP), and displayed to the user through automatic push, when the user opens the map (as shown in Figure 1D), when the route is planned (as shown in Figure 1E) or is about to arrive during the journey (as shown in Figure 1F), Figure 1D is a schematic diagram of an electronic map provided by an embodiment of the present disclosure; Figure 1E is a schematic diagram of a route planning provided by an embodiment of the present disclosure; Figure 1F is a schematic diagram of an approaching arrival provided by an embodiment of the present disclosure; users can According to your own driving situation, you can choose whether to continue driving on this road.

Presenting the associated road dynamic events of the roads in the presentation area includes at least one of the following:

(1) In the presented electronic map, mark and display the event category or prompt information of the road dynamic event on the road; the prompt information refers to the content of the road dynamic event, for example, it can be the time of occurrence; or it can be the severity of the occurrence etc., which is not limited in this embodiment.

(2) In the presented electronic map, display the content or link of the road dynamic data of the road.

(3) During the navigation process, route planning and/or reminders are performed according to road dynamic events of the road.

Route planning refers to designing and providing the optimal driving route for the user based on the user's departure point and arrival point, combined with the user's needs and the occurrence of road dynamic events.

During the user's navigation and driving process, according to the occurrence of road dynamic events and the distance from the user's starting point to the destination, multiple routes are planned in time and the user is reminded of the existing road dynamic events.

Exemplarily, when user B is driving on road b, and road b is congested, the navigation plans three roads that can reach the destination according to user B's destination, and reminds user B that the congested event can be passed within 10 minutes , the other two paths are not congested, but one road is far away and needs to be detoured for 20 minutes, and the other road has 4 more traffic lights, so at this time, three paths are planned for users to choose from.

The advantage of this setting is that it can remind the user of road dynamic events in time, save the user's road driving time, and improve the efficiency of the user's driving process.

On the basis of the above technical solution, the road dynamic data processing may, for example, extract time information from the road dynamic data, and store the extracted time information in association with the road dynamic event.

When a road dynamic event occurs, extract the road dynamic data and record the occurrence time from it at the same time, associate the occurrence time in the road dynamic data with the event, and save it for use. The advantage of this setting is that when the user is driving, he already knows that a road dynamic event has occurred, and there is a time reminder to ensure the timeliness of the event.

In the technical solution of this embodiment, unstructured road dynamic data is obtained from at least one data source; the road position corresponding to the road dynamic event that occurs is identified from the road dynamic data; and the road and road are established according to the road position The association between the road dynamic events, based on unstructured data from sources such as social networking sites, solves the problem of low coverage of road dynamic events, and achieves real-time and comprehensive collection of unstructured data, from which road dynamic events can be determined. And it can be connected to the electronic map for display, so that the map presents road dynamics in a more timely, accurate and rich effect.

FIG. 2 is a schematic flowchart of another method for processing road dynamic events provided by an embodiment of the present disclosure. This embodiment is described based on the foregoing embodiments, and provides a method for identifying road location information. As shown in Figure 2, the processing method of road dynamic events is as follows:

S210. Acquire unstructured road dynamic data from at least one data source.

S220. Identify, from the road dynamic data, location-associated information corresponding to the occurred road dynamic event.

The position-associated information includes at least one of the following: administrative division name, road name, point of interest information, position coordinates and fingerprint information.

S230. Perform matching in a preset index library according to the location-associated information, so as to determine a road sign in the matched electronic map as the road location.

The point of interest information refers to an element point in the electronic map, for example, it may be a point of interest of a building; or it may be a point of interest of a scenic spot. Fingerprint information refers to the information that can be extracted from the image and uniquely identifies the road in the picture. For example, it can be information with natural semantics, such as shop names and road names; or it can be information without natural semantics, such as image Characterization information and the like are not limited in this embodiment.

Exemplarily, through video content analysis, it is found that there is traffic sign content in a specific frame, and the system automatically completes the identification of sign elements, and obtains elements in the sign, such as the time, place, and event category of road dynamic events, etc. The element is called the fingerprint information of the road dynamic event. The advantage of such setting is that the location where the road dynamic event occurs can be quickly and accurately determined.

Exemplarily, when the keyword "road closure" is retrieved from a social networking site, the small video content can be quickly obtained, as shown in Figure 1G, which is a schematic diagram of a keyword search result provided by an embodiment of the present disclosure; obtained through text analysis According to the information, the name of the administrative division is "Watoupo, Weinan City", the name of the road is "Watoupo Section of National Highway 210", and the time is "one week". After analyzing the video content, it is found that there is a traffic sign in a specific frame, such as The road sign shown in Figure 1H, Figure 1H is a schematic diagram of a road database record provided by the embodiment of the present disclosure; the system automatically completes the element identification, and obtains the composition information of the elements in the sign, such as the three-way intersection leading to Xi'an Gaoling and Sanyuan, and determines the road Unstructured road dynamics data for dynamic events.

On the basis of the above technical solution, identifying the location-related information corresponding to the occurred road dynamic event from the road dynamic data includes:

(1) Extract at least two frame images of text, independent images and/or videos from the road dynamic data as elements to be identified; where, a frame image refers to a still picture, the smallest unit in a video A single image frame; the elements to be recognized refer to road names, geographical location relationships, signboards and signs, etc.

Identify the location-related information corresponding to the road dynamic events that occurred from the text road dynamic data, and use the basis of natural language processing to extract information such as administrative divisions, road names, and geographical location relations from the text; call the text recognition of general services from pictures, Recognize the text information in the picture, extract administrative divisions, road names and other information; get road dynamic data from the video, and process each frame of video into a picture, and process it according to the processing method of the picture content.

(2) Input the elements to be identified sequentially or in parallel into at least one general identification service component to identify the location-related information corresponding to the road dynamic event that occurs; wherein, the at least one general identification service component includes at least one of the following Items: text recognition component, signboard recognition component, traffic sign recognition component and image representation recognition component.

Universal recognition services are processed separately for text, image, and video sources. Sequential input means that the elements to be recognized in the collected road dynamic data are sequentially input into the sign recognition component, signboard recognition component and text recognition component, and the recognition is carried out step by step. Parallel input means that the elements to be identified in the collected road dynamic data are input into three components at the same time, and the corresponding relevant information is identified respectively.

The text recognition component is to recognize the input traffic signs or shop signs, and obtain the text content. Using the text recognition component needs to be able to support robust processing of pictures in scenes such as rotation, deformation, and color change. The signboard recognition component is to process a picture, identify whether the picture contains a shop signboard, and circle the area where the text is located, which can be extracted by combining deep residual network 50 (Deep Residual Network 50, ResNet50) and other image feature extraction methods and Classifiers such as fully connected layers and softmax perform modeling processing. The traffic sign recognition component is to process a picture, identify whether there is a traffic sign, and circle the area. Through sample labeling and image recognition technology, general capacity building can be carried out. The key recognition targets are mainly blue-bottomed signs Mainly to ensure the recognition accuracy.

The advantage of this setting is that text, pictures, and videos are recognized separately to ensure the robustness of the data.

On the basis of the above technical solution, input the elements to be identified sequentially or in parallel into at least one general identification service component to identify the location-associated information corresponding to the occurred road dynamic event including:

(1) Input the element to be identified in the image form into the signboard recognition component, the traffic sign recognition component and/or the image representation recognition component to perform image segmentation and obtain the output image representation information; wherein, the image representation information refers to the image high-level abstract features. Image segmentation refers to separating the target object in the image from the background. The segmentation method may be, for example, grayscale threshold segmentation and edge segmentation; or may be region segmentation, etc., which is not limited in this embodiment.

The element to be recognized in the form of an image is input into the signboard recognition component, the traffic sign recognition component and/or the image representation recognition component, and the image is segmented according to the objects and background in the whole image to obtain the desired target object.

(2) Input the segmented image into the character recognition component to perform character recognition; input the segmented image into the character recognition component, and recognize the characters through the picture. First, the picture is preprocessed, grayscaled, and then binarized to convert the text in the picture The text is separated from the background, and then the image file is analyzed and processed. Through the sliding window algorithm, the entire image is traversed, and the characteristics of the training sample are supervised to judge, and the target image is found to be rectangularized and extracted; a one-dimensional sliding window is made in the rectangle. Move, judge the distance between characters, and divide the characters; predict the characters according to the supervised algorithm for the divided characters; finally recognize the entire character.

(3) Determine location-related information according to the image representation information and the recognized text.

According to the image representation information and the recognized text, it is possible to determine the location where the road dynamic event occurs, and determine the location-related information in combination with the location information.

The advantage of such a setting is that the dynamic event is combined with information such as the location where it occurs, and the road dynamic information is clarified.

In an embodiment, identifying the location-related information corresponding to the occurred road dynamic event from the road dynamic data includes: performing text recognition on the text in the road dynamic data to determine the location-related information.

Analyzing and recognizing based on text to obtain location information such as road names and administrative division names is location-related information. The advantage of this setting is that the location of road dynamic events can be determined from the text.

In one embodiment, identifying the location-related information corresponding to the occurred road dynamic event from the road dynamic data includes: inputting an independent image in the road dynamic data or at least two frame images in the video into the image representation recognition component Image representation information is extracted to obtain output image representation information as the position association information.

Input the independent image in the road dynamic data or at least two frame images in the video into the image representation recognition component to extract image representation information, and use the model for extracting image representation information to undergo pre-training, and the training sample set includes positive samples And negative samples, the trained model can extract image representation information from the image, so that the image can be uniquely identified, and the output image representation information can be used as location-related information.

The advantage of this setting is that the road location information of the occurrence of road dynamic events can be determined and presented in time.

S240. Establish an association between a road and the road dynamic event according to the road position.

According to the road position where the road dynamic event occurs and the position association information, the association between the road and the road dynamic event is established.

In the technical solution of this embodiment, by identifying the location-related information corresponding to the occurred road dynamic event from the road dynamic data; according to the location-related information, matching is performed in the preset index library to determine the road sign in the matched electronic map, As the road position; according to the road position, the relationship between the road and the road dynamic event is established, so as to achieve the effect of clarifying the location of the road dynamic event and associating the map in time.

FIG. 3 is a schematic flow chart of another method for processing road dynamic events provided by an embodiment of the present disclosure. This embodiment is described based on the foregoing embodiments. Wherein, after identifying the location-related information corresponding to the occurred road dynamic event from the road dynamic data, a process of identifying and matching based on the index library is also included. The method includes:

S310. Acquire unstructured road dynamic data from at least one data source.

S320. Identify, from the road dynamic data, location-related information corresponding to the occurred road dynamic event.

The position-associated information includes at least one of the following: administrative division name, road name, point of interest information, position coordinates and fingerprint information.

S330. Record the location-associated information of the road dynamic data as attribute data together with the identifier of the road dynamic data as an item to be queried.

S340. Match at least one attribute data of the item to be queried with attribute data of index items in a preset index library.

That is, through the above operations, matching is performed in the preset index library according to the location-associated information, so as to determine the road sign in the matched electronic map.

Each index item in the preset index library includes an identification and at least one attribute data, and at least one attribute data is used to store a predetermined road identification; wherein, the attribute data refers to data that can have the characteristics of road dynamic data; the index The identifier included in the item refers to an element identifier, for example, it may be an identifier for extracting a picture of a road dynamic event. For example, an image of a traffic sign and an image of a store sign are two elements.

Establish an index database, provide database services, and associate the index obtained from the data identification service with attributes such as administrative divisions, road names, and road identifiers (Identifier, ID). In the index database, the traffic sign ID T_i is correspondingly stored with multi-level attribute content such as the road L_i in front of the sign, the administrative area, and the road name.

Exemplary, for example: the fingerprint feature "Wenhui West Road-Yangzijiang Middle Road-Weiyang Road-Jiangyang Middle Road" of the traffic sign is index-matched in the attribute item, and other attributes in the matching item are obtained in the matching item , that is, the corresponding road ID: 12345 and the road name "Weiyang Road, Yangzhou City, Jiangsu Province", etc.

Matching at least one attribute data of the item to be queried with the attribute data of the index item in the preset index library includes: matching the fingerprint information in the item to be queried with the fingerprint information of the index item in the preset index library Matching; if the same or similar fingerprint information is matched with the fingerprint information in the item to be queried, the attribute data of the non-fingerprint information in the item to be queried is matched with the attribute data of the non-fingerprint information of the matched index item .

Fingerprint information refers to determining the set of pictures containing signs or signboards, and identifying the actual area of the sign or signboard in the picture, and then performing textual processing on the content in the actual area, and obtaining text information after processing. The signboard text information can be directly used for merchant signboard recognition, and the processed signboard text information will generate fingerprint information according to certain rules.

Match the fingerprint information in the item to be queried with the fingerprint information of each index item in the preset index library.

The advantage of this setting is that the corresponding fingerprint information is matched according to the attribute data, and the road dynamic event is determined.

Matching the at least one attribute data of the item to be queried with the attribute data of the index item in the preset index library includes: matching the name of the administrative division in the item to be queried with the index stored in the preset index library The attribute data of the item is matched, wherein, the attribute data of the index item includes the administrative division; according to the matched administrative division, determine the index item covering the scope of the matched administrative division; The fingerprint information is matched with the fingerprint information of the index items covered within the scope of the matched administrative division.

The name of the administrative division refers to the location where the road dynamic event occurs.

In the attribute data of the index item in the preset index library, the basic administrative division location is stored, and the name of the administrative division in the item to be queried is input, and the query matching is performed in the attribute data of the index item in the preset index library, Determine the scope of the administrative division, and then match the fingerprint information of the road dynamic event to the corresponding administrative division according to the matched corresponding administrative division and the fingerprint information in the item to be queried.

The advantage of this setting is that it can quickly determine the range corresponding to the road dynamic event that occurs and match the corresponding division range in the index library in time to determine the division range and road signs.

S350. Determine the road identifier of the road dynamic data according to the road identifier in the attribute data of the matched index item.

According to the road sign in the attribute data of the matched index item, it is determined whether the road sign corresponding to the road dynamic data in the electronic map is correspondingly displayed. Road markings serve as road locations.

S360. Establish an association between a road and the road dynamic event according to the road position.

In the technical solution of this embodiment, by using the location-related information of the road dynamic data as attribute data, it is recorded together with the identification of the road dynamic data as an item to be queried; Matching, to determine the road identification in the matched electronic map and determine the road identification of the road dynamic data according to the road identification in the attribute data of the matched index item, so that the road dynamic data presented by the map is more abundant.

Fig. 4A is a schematic flowchart of another method for processing road dynamic events provided by an embodiment of the present disclosure. On the basis of the above-mentioned embodiments, this embodiment identifies the location corresponding to the occurred road dynamic event from the road dynamic data Related information will be explained. The method includes:

S410. Acquire unstructured road dynamic data from at least one data source.

S420. If the independent image in the road dynamic data or at least two frame images in the video include a signboard, identify the image of the signboard to output signboard fingerprint information as the location-associated information.

The signboard fingerprint information includes interest point information included in the signboard image and/or image representation information of the signboard image.

Signboards are generally the name brand logos of shops or some institutions. The point of interest information can be the name of the shop, and the image representation information is the image semantic information extracted from the signboard image.

Screen out the road network pictures containing signboards to obtain a picture set S, and circle the actual area of the signboard in the picture, textualize the content on the signboard circled in the pictures in the picture set S, and directly use it for merchants Signboard identification to determine the location of the merchant.

S430. If the independent image in the road dynamic data or at least two frame images in the video include a traffic sign, identify the image of the traffic sign to output traffic sign fingerprint information as the location Associated information.

The traffic sign fingerprint information includes interest point information included in the traffic sign image and/or image representation information of the traffic sign image.

Filter out the road network pictures containing traffic signs, get the picture set P, circle the actual area of the traffic signs in the picture, and textualize the content on the traffic signs circled in the pictures in the picture set P processing, and then generate fingerprint information according to certain rules, and use it as location-associated information.

Exemplarily, an image containing a traffic sign is captured, as shown in FIG. 4B , which is a schematic diagram of a traffic sign provided by an embodiment of the present disclosure; where the traffic sign is a line at a crossroad, which can be obtained from From left to right, the fingerprint generation of road names is performed from top to bottom to obtain road information, such as "Wenhui West Road-Yangzijiang Middle Road-Weiyang Road-Jiangyang Middle Road", which is used for traffic sign identification.

The above operations S420 and S430 may be implemented independently or together, and the order of their implementation is not limited.

S440. Perform matching in a preset index library according to the location-associated information, so as to determine a road sign in the matched electronic map as the road location.

S450. Establish an association between a road and the road dynamic event according to the road position.

In the technical solution of this embodiment, the position-related information corresponding to the occurred road dynamic event is identified from the road dynamic data by separately identifying the signboard and the traffic sign.

Fig. 5 is a schematic flowchart of another method for processing road dynamic events provided by an embodiment of the present disclosure. On the basis of the above embodiments, the method may also include the process of building the preset index library, including:

S510. Input the road-acquisition images collected on the road into at least one general recognition service component sequentially or in parallel, so as to identify the location-associated information of the road-acquisition images.

The general recognition service component includes at least one of the following: a character recognition component, a signboard recognition component, a traffic sign recognition component and an image representation recognition component.

The image collected by the road is scanned, and the description information is extracted, which can be input into one component, or input into multiple components at the same time to identify its location-related information.

Exemplarily, an image collection is collected, which contains text information, signboard information, traffic sign information and image representation information, and the image collection can be input into the text recognition component, signboard recognition component, traffic sign recognition component and image representation recognition in sequence For example, after entering the text recognition component, directly extract related information such as administrative divisions, road names, and geographical locations. After the recognition is completed, enter the signboard recognition component to identify whether there is a shop signboard, and circle the text area for recognition , and so on for sequential input. At the same time, the image collection can also be directly input into the text recognition component, signboard recognition component, traffic sign recognition component and image representation recognition component at the same time, and the four components can be recognized at the same time to identify the location-related information of the corresponding road sampling image.

S520. Store the location-associated information as attribute data together with the identifier of the road sampling image as an index item.

Recognize the location-related information, use it as attribute data, generate an index with the identification of the road sampling image, and save it in the database as an index item.

The process of building an index library can be completed offline by calling various common service components. In the road dynamic event identification process of the foregoing embodiments, it may also be implemented by calling a general service component.

In the technical solution of this embodiment, the road-picking image collected by the road is input into at least one general identification service component sequentially or in parallel to identify the location-related information of the road-picking image; and the location-related information is used as attribute data to be combined with the road-picking image The identification of the road is stored as an index item, so that according to the unstructured data of the road mining, the location-related information is identified, and the road identification is determined and saved.

Fig. 6 is a schematic structural diagram of a processing device for road dynamic events provided by an embodiment of the present disclosure. This embodiment can be applied to the situation of processing road dynamic events. As shown in Fig. 6, the processing device for road dynamic events includes: dynamic data An acquisition module 610 , a road location identification module 620 and a location association module 630 . in:

The dynamic data acquisition module 610 is configured to obtain unstructured road dynamic data from at least one data source; the road position identification module 620 is configured to identify the road position corresponding to the road dynamic event that occurs from the road dynamic data; the position The association module 630 is configured to establish an association between a road and the road dynamic event according to the road position.

The technical solution of this embodiment is based on the unstructured data of social networking sites, solves the problem of low coverage of road dynamic events, and achieves real-time and comprehensive collection of unstructured data, from which road dynamic events can be determined and linked to the electronic map Display on the map, making the map present a more timely and rich effect of road dynamics.

In one embodiment, the data source includes at least one of the following: news web pages, social networking sites, and surveillance cameras; the form of the road dynamic data includes at least one of the following: text, image, audio, and video.

In one embodiment, as shown in FIG. 7, the dynamic data acquisition module 610 includes:

Obtain dynamic data unit 710, set to search or subscribe from at least one data source, to obtain unstructured road dynamic data matching event keywords; receive dynamic data unit 720, set to receive from at least one data source Actively reported unstructured road dynamic data.

In one embodiment, as shown in FIG. 8, the device for processing road dynamic events further includes:

The event type determination module 640 is configured to determine the event category of the road dynamic event that occurs according to the road dynamic data; the association establishment module 650 is configured to establish a relationship between the road and the event category of the road dynamic event according to the road position. connection between.

In one embodiment, as shown in FIG. 9, the event type determination module 640 includes:

The keyword determination unit 910 is configured to identify event keywords from the text of the road dynamic data, and determine the event category of the road dynamic event that occurs according to the event keywords; the image determination unit 920 is configured to convert the road dynamic data The image input event classification model performs event classification on the content corresponding to the image of the road dynamic data, so as to determine the event category of the road dynamic event that occurs.

In one embodiment, as shown in FIG. 10 , the road location identification module 620 includes:

The information identification unit 1010 is configured to identify the location-related information corresponding to the occurred road dynamic event from the road dynamic data; wherein, the location-related information includes at least one of the following: administrative division name, road name, point of interest information , location coordinates and fingerprint information; the information matching unit 1020 is configured to perform matching in a preset index library according to the location-associated information, so as to determine the road sign in the matched electronic map as the road location.

In one embodiment, as shown in Figure 11, the information identification unit 1010 includes:

The element determination subunit 1110 is configured to extract at least two frame images of text, independent images and/or videos from the road dynamic data as elements to be identified; the element information identification subunit 1120 is configured to extract the to-be-identified Recognition elements are input sequentially or in parallel into at least one general recognition service component to identify location-related information corresponding to road dynamic events that occur; wherein, the at least one general recognition service component includes at least one of the following: text recognition components, signboards Recognition component, traffic sign recognition component and image representation recognition component.

In one embodiment, the element information identification subunit 1120 is set to:

Input the element to be recognized in the form of an image into the signboard recognition component, the traffic sign recognition component and/or the image representation recognition component to perform image segmentation and obtain the output image representation information; input the segmented image into the text recognition component for text recognition Recognition: determining location-related information according to the image representation information and the recognized text.

In one embodiment, the information identification unit 1010 is set to:

Text recognition is performed on the text in the road dynamic data to determine location-associated information.

In one embodiment, the information identification unit 1010 is set to:

If the independent image in the road dynamic data or at least two frame images in the video include a signboard, then identify the image of the signboard to output signboard fingerprint information as the location-associated information; wherein, the signboard The fingerprint information includes interest point information included in the signboard image and/or image representation information of the signboard image.

In one embodiment, the information identification unit 1010 is set to:

If the independent image in the road dynamic data or at least two frame images in the video include a traffic sign, then identify the image of the traffic sign to output traffic sign fingerprint information as the location-related information ; Wherein, the traffic sign fingerprint information includes interest point information included in the traffic sign image and/or image representation information of the traffic sign image.

In one embodiment, the information identification unit 1010 is set to:

An independent image in the road dynamic data or at least two frames of images in the video are input to the image representation recognition component to extract image representation information, so as to obtain output image representation information as the location-related information.

In one embodiment, as shown in FIG. 12, the road location identification module 620 further includes:

The data identification unit 1030 is configured to record the position-associated information of the road dynamic data as attribute data together with the identification of the road dynamic data as an item to be queried.

In one embodiment, as shown in FIG. 13, the information matching unit 1020 includes:

The data matching subunit 1310 is configured to match at least one attribute data of the item to be queried with the attribute data of the index item in the preset index library; wherein, each index item in the preset index library includes logo and at least one attribute data, at least one attribute data is used to store a predetermined road logo; the road logo determination subunit 1320 is configured to determine the road of the road dynamic data according to the road logo in the attribute data of the matched index item logo.

In one embodiment, as shown in FIG. 14, the data matching subunit 1310 includes:

The fingerprint information matching subunit 1410 is configured to match the fingerprint information in the item to be queried with the fingerprint information of the index item in the preset index library; the attribute data matching subunit 1420 is configured to match the fingerprint information of the item to be queried if it matches the If the fingerprint information in the query item is the same or similar to the fingerprint information, the attribute data of the non-fingerprint information in the item to be queried is matched with the attribute data of the non-fingerprint information of the matching index item.

In one embodiment, as shown in Figure 15, the data matching subunit 1310 includes:

The preset index library matching subunit 1510 is configured to match the name of the administrative division in the item to be queried with the attribute data of the index item stored in the preset index library, wherein the attribute data of the index item includes The administrative division; the determining index item subunit 1520 is configured to determine the index item covered within the scope of the matched administrative division; the index item information matching subunit 1530 is configured to use the fingerprint information in the item to be queried, Matching is performed with the fingerprint information of the index items covered within the scope of the matched administrative division.

In one embodiment, as shown in FIG. 16 , the device for processing road dynamic events further includes: a road position identification module 660 configured to construct the preset index library, including:

The identification road acquisition information unit 1610 is configured to input the road acquisition images collected by the road into at least one general identification service component sequentially or in parallel, so as to identify the location-related information of the road acquisition images; wherein, the at least one general identification The service component includes at least one of the following: a text recognition component, a signboard recognition component, a traffic sign recognition component, and an image representation recognition component; the index item storage unit 1620 is configured to use the location-associated information as attribute data, and the road The ID of the captured image is stored as an index item.

In one embodiment, as shown in FIG. 17, the location association module 630 includes:

The road association storage unit 1710 is configured to associate and store the road dynamic event with the road in the electronic map according to the road position.

In one embodiment, as shown in Figure 18, the device further includes:

The event presentation module 670 is configured to present the associated road dynamic events of the roads in the presentation area in response to the user's electronic map presentation request.

In one embodiment, as shown in FIG. 19, the event presentation module 670 includes:

The marked road information unit 1910 is configured to mark and display the event category or prompt information of the road dynamic event of the road in the presented electronic map; the road data display unit 1920 is configured to display the road information of the road in the presented electronic map The contents or links of the dynamic data are displayed; the route planning unit 1930 is configured to perform route planning and/or reminders according to the road dynamic events of the road during the navigation process.

In one embodiment, the event category includes at least one of the following: road closure, landslide, heavy fog, flooding, road collapse and mudslide.

In one embodiment, as shown in Figure 20, the device further includes:

The dynamic event storage module 680 is configured to extract time information from the road dynamic data, and store the extracted time information in association with the road dynamic event.

The device for processing road dynamic events provided by the embodiments of the present disclosure can be configured to execute the method for processing road dynamic events provided by the embodiments of the present disclosure, and has corresponding functions and effects.

In the technical solution of the present disclosure, the acquisition, storage and application of control events and audio and video data involved are in compliance with relevant laws and regulations, and do not violate public order and good customs.

According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

Fig. 21 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure, and Fig. 7 shows a schematic block diagram of an example electronic device 700 that can be used to implement the embodiment of the present disclosure. Electronic device 700 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic device 700 may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in Figure 21, the electronic device 700 includes a computing unit 701, which can be loaded into a random access memory (Random Access Memory, RAM) 703 to execute various appropriate actions and processes. In the RAM 703, various programs and data necessary for the electronic device 700 to perform operations can also be stored. The computing unit 701, ROM 702, and RAM 703 are connected to each other through a bus 704. An input/output (Input/Output, I/O) interface 705 is also connected to the bus 704 .

Multiple components in the electronic device 700 are connected to the I/O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, an optical disk etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 709 allows the electronic device 700 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

Computing unit 701 may be various general and/or special purpose processing components with processing and computing capabilities. Some examples of computing unit 701 include, but are not limited to, a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU), a variety of dedicated artificial intelligence (Artificial Intelligence, AI) computing chips, a variety of operating Computing units of machine learning model algorithms, digital signal processors (Digital Signal Processing, DSP), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 executes multiple methods and processes described above, for example, the method of processing road dynamic events. For example, in some embodiments, the method road dynamic event processing may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program can be loaded and/or installed on the electronic device 700 via the ROM 702 and/or the communication unit 709. When the computer program is loaded into RAM 703 and executed by computing unit 701, one or more steps of the above-described method of processing road dynamic events may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured in any other appropriate way (for example, by means of firmware) to perform the method of processing road dynamic events.

Various implementations of the systems and technologies described above in this paper can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (Field Programmable Gate Array, FPGA), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Application Specific Standard Parts (ASSP), System on Chip (System on Chip, SOC), Complex Programmable Logic Device (Complex Programmable Logic Device, CPLD), computer hardware, firmware, software, and/or their realized in combination. Various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that can is a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, RAM, ROM, Erasable Programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM, or Flash memory) ), fiber optics, Compact Disc Read-Only Memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having a display device (e.g., a cathode ray tube (CRT) or a liquid crystal display ( Liquid Crystal Display (LCD) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which a user can provide input to the computer. Other types of devices may also be configured to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and may be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.

The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (Wide Area Network, WAN), blockchain networks, and the Internet.

A computer system may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the problems existing in traditional physical host and virtual private server (Virtual Private Server, VPS) services. The defects of difficult management and weak business expansion. The server can also be a server of a distributed system, or a server combined with a blockchain.

Steps can be reordered, added, or removed using the various forms of flow shown above. For example, multiple steps described in the present disclosure may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in the present disclosure can be achieved, no limitation is imposed herein.

Claims (24)

1. A method for processing road dynamic events, comprising:

   obtaining unstructured road dynamics data from at least one data source;

   identifying a road location corresponding to the road dynamic event that occurs from the road dynamic data;

   According to the road position, the association between the road and the road dynamic event is established.
2. The method according to claim 1, wherein,

   The data sources include at least one of the following: news web pages, social networking sites and surveillance cameras;

   The form of the road dynamic data includes at least one of the following: text, image, audio and video.
3. The method according to claim 1, wherein said acquiring unstructured road dynamic data from at least one data source comprises at least one of the following:

   Searching or subscribing to the at least one data source to obtain unstructured road dynamics data matching event keywords; or

   receiving unstructured road dynamic data actively reported by the at least one data source.
4. The method according to claim 1, after obtaining the unstructured road dynamic data from at least one data source, further comprising:

   Determine the event category of the road dynamic event that occurs according to the road dynamic data;

   After the identification of the road position corresponding to the occurred road dynamic event from the road dynamic data, it also includes:

   According to the road position, the association between the road and the event category of the road dynamic event is established.
5. The method according to claim 4, wherein, according to the road dynamic data, determining the event category of the occurred road dynamic event comprises at least one of the following:

   Identify event keywords from the text of the road dynamic data, and determine the event category of the road dynamic event that occurs according to the event keywords; or

   Inputting the image of the road dynamic data into an event classification model, performing event classification on the content corresponding to the image of the road dynamic data, so as to determine the event category of the road dynamic event that occurs.
6. The method according to claim 1, wherein the identifying the road location corresponding to the occurred road dynamic event from the road dynamic data comprises:

   Identifying location-related information corresponding to the road dynamic event that occurs from the road dynamic data; wherein the location-related information includes at least one of the following: administrative division name, road name, point of interest information, location coordinates, and fingerprint information;

   Matching is performed in a preset index library according to the position association information, so as to determine the road sign in the matched electronic map as the road position.
7. The method according to claim 6, wherein the identifying the location-related information corresponding to the occurred road dynamic event from the road dynamic data includes:

   Extracting at least one of the following from the road dynamic data as an element to be identified: text, an independent image, and at least two frame images in a video;

   Input the elements to be identified sequentially or in parallel into at least one general identification service component to identify the location-related information corresponding to the road dynamic event that occurs; wherein, the at least one general identification service component includes at least one of the following: text Recognition components, signboard recognition components, traffic sign recognition components and image representation recognition components.
8. The method according to claim 7, wherein said inputting said elements to be identified sequentially or in parallel into at least one general identification service component to identify the position-associated information corresponding to the occurred road dynamic event comprises:

   Inputting the element to be identified in the form of an image into at least one of the signboard recognition component, the traffic sign recognition component, and the image representation recognition component to perform image segmentation and obtain output image representation information;

   Input the segmented image into the character recognition component for character recognition;

   The position-associated information is determined according to the image representation information and the recognized text.
9. The method according to claim 6, wherein the identifying the location-related information corresponding to the occurred road dynamic event from the road dynamic data includes:

   Text recognition is performed on the text in the road dynamic data to determine the location-associated information.
10. The method according to claim 6, wherein the identifying the location-related information corresponding to the occurred road dynamic event from the road dynamic data includes:

    In the case where the independent image in the road dynamic data or at least two frame images in the video include a signboard, identify the image of the signboard to output signboard fingerprint information as the location-related information; wherein, The signboard fingerprint information includes at least one of interest point information included in the signboard image and image representation information of the signboard image.
11. The method according to claim 6, wherein the identifying the location-related information corresponding to the occurred road dynamic event from the road dynamic data includes:

    In the case where the independent image in the road dynamic data or at least two frame images in the video include a traffic sign, identify the image of the traffic sign to output traffic sign fingerprint information as the location Associated information; wherein, the traffic sign fingerprint information includes at least one of interest point information included in the traffic sign image and image representation information of the traffic sign image.
12. The method according to claim 6, wherein the identifying the location-related information corresponding to the occurred road dynamic event from the road dynamic data includes:

    An independent image in the road dynamic data or at least two frames of images in the video are input to the image representation recognition component to extract image representation information, so as to obtain output image representation information as the location-related information.
13. The method according to claim 6 or 7, after identifying the location-related information corresponding to the occurred road dynamic event from the road dynamic data, further comprising:

    Recording the location-associated information of the road dynamic data as attribute data together with the identification of the road dynamic data as an item to be queried;

    The matching is performed in a preset index library according to the location-associated information to determine the road sign in the matched electronic map, including:

    Match at least one attribute data of the item to be queried with the attribute data of the index item in the preset index library; wherein, each index item in the preset index library includes an identifier and at least one attribute data , the at least one attribute data is used to store a predetermined road sign;

    Determine the road identifier of the road dynamic data according to the road identifier in the attribute data of the matched index item.
14. The method according to claim 13, wherein the matching of at least one attribute data of the item to be queried with the attribute data of the index item in the preset index database includes:

    matching the fingerprint information of the item to be queried with the fingerprint information of the index item in the preset index library;

    In the case of matching fingerprint information that is the same as or similar to the fingerprint information in the item to be queried, the attribute data of the non-fingerprint information in the item to be queried is compared with the attribute data of the non-fingerprint information of the matched index item match.
15. The method according to claim 13, wherein the matching of at least one attribute data of the item to be queried with the attribute data of the index item in the preset index database includes:

    matching the name of the administrative division in the item to be queried with the attribute data of the index item stored in the preset index library, wherein the attribute data of the index item includes the administrative division;

    determining the index items covered within the scope of the matched administrative division;

    Match the fingerprint information in the item to be queried with the fingerprint information of the index items covered within the scope of the matched administrative division.
16. The method according to claim 6, wherein the preset index library is constructed in the following manner:

    The road sampling images collected by the road are input into at least one general identification service component sequentially or in parallel to identify the location-associated information of the road sampling images; wherein, the at least one general identification service component includes at least one of the following: Text recognition components, signboard recognition components, traffic sign recognition components and image representation recognition components;

    The location-associated information is used as attribute data and stored together with the identification of the road sampling image as an index item.
17. The method according to claim 1, wherein said establishing an association between a road and said road dynamic event according to said road position comprises:

    According to the road position, the road dynamic event is stored in association with the road in the electronic map;

    The method also includes:

    In response to the user's electronic map presentation request, the associated road dynamic events of the roads in the presentation area are presented.
18. The method according to claim 17, wherein said presenting the road dynamic events associated with the roads in the presenting area comprises at least one of the following:

    In the presented electronic map, mark and display the event category or prompt information of the road dynamic event on the road;

    In the presented electronic map, display the content or link of the road dynamic data of the road; or

    During the navigation process, at least one of route planning and reminder is performed according to the road dynamic events of the road.
19. The method according to claim 4, wherein the event category includes at least one of the following: road closure, landslide, fog, flooding, road collapse and mudslide.
20. The method according to claim 1, further comprising:

    Time information is extracted from the road dynamic data, and the extracted time information is associated with the road dynamic event for storage.
21. A processing device for road dynamic events, comprising:

    The dynamic data acquisition module is configured to acquire unstructured road dynamic data from at least one data source;

    A road position identification module, configured to identify the road position corresponding to the occurred road dynamic event from the road dynamic data;

    The location association module is configured to establish an association between the road and the road dynamic event according to the location of the road.
22. An electronic device comprising:

    at least one processor; and

    a memory communicatively coupled to the at least one processor; wherein,

    The memory stores instructions executable by the at least one processor, the instructions are executed by the at least one processor, so that the at least one processor can perform any one of claims 1-20 The processing method of the road dynamic event.
23. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to make the computer execute the road dynamic event processing method according to any one of claims 1-20.
24. A computer program product, comprising a computer program, the computer program implements the road dynamic event processing method according to any one of claims 1-20 when executed by a processor.

Images