A method and system for managing multi-source heterogeneous data of smart lamp poles

Abstract

The present invention provides a method and system for managing multi-source heterogeneous data of smart lamp poles, which relates to the field of smart city technology. The method can associate abnormal features in multi-source heterogeneous data generated by smart lamp poles with abnormal events occurring in the current scene, and filter out valuable parts for storage based on the association results. The storage volume of multi-source heterogeneous data on smart lamp poles is effectively reduced, and the stored data information is marked by corresponding event tags, which facilitates retrieval and use after storage, thereby improving the use value of multi-source heterogeneous data of smart lamp poles.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to a method and system for managing multi-source heterogeneous data of smart lamp poles. Background Art

[0002] With the acceleration of urbanization and the advancement of smart city construction, smart light poles, as an important part of smart cities, have been widely used in every corner of the city. Smart light poles not only provide basic lighting functions, but also integrate a variety of sensors and communication equipment for environmental monitoring, traffic management, public safety, etc. The data formats generated by different devices may be different, and because there are a large number of devices that continuously generate data, the overall data volume is very large. Moreover, although the total amount of data is large, the proportion of truly valuable information may be very small.

[0003] Therefore, how to effectively manage the multi-source heterogeneous data generated by smart light poles to fully tap their potential value is an urgent problem to be solved. Summary of the invention

[0004] In order to improve the above problems, the present invention provides a method and system for managing multi-source heterogeneous data of smart lamp poles.

[0005] A first aspect of an embodiment of the present invention provides a method for managing multi-source heterogeneous data of a smart lamp pole, the method comprising:

[0006] Acquire multi-source heterogeneous data generated by smart light poles;

[0007] Classify the acquired data and extract abnormal features according to the sources of the multi-source heterogeneous data to obtain a first abnormal feature;

[0008] Based on the time node at which the first data information corresponding to the first abnormal feature is generated and the location information of the smart lamp pole, data information generated by other smart sensing systems of the smart city at the corresponding time node and location is obtained;

[0009] Extracting a second abnormal feature of the acquired data information of other intelligent perception systems, wherein the data information corresponding to the second abnormal feature is the second data information;

[0010] Performing feature matching and time-series association on the first abnormal feature and the second abnormal feature according to the time sequence of generation of the first data information and the second data information;

[0011] According to the result of feature matching, an event tag is added to the first data information and stored.

[0012] Optionally, the step of classifying the acquired data and extracting abnormal features according to the respective sources of the multi-source heterogeneous data to obtain the first abnormal feature specifically includes:

[0013] Categorize acquired data based on device type;

[0014] For the classified data, screening abnormal data according to the corresponding device types to obtain first data information;

[0015] Feature extraction is performed on the screened first data information to obtain a first abnormal feature.

[0016] Optionally, the step of acquiring data information generated by other intelligent sensing systems of the smart city at corresponding time nodes and locations based on the time node at which the first data information corresponding to the first abnormal feature is generated and the location information of the smart lamp pole specifically includes:

[0017] The time node at which the first data information is generated is taken as the center, and the preset time threshold is taken as the range, as the time interval for acquiring data information of other intelligent perception systems;

[0018] Taking the position of the smart lamp pole generating the first data information as the center and the preset distance threshold as the range as the position interval for acquiring data information of other intelligent sensing systems;

[0019] The data information generated by other intelligent sensing systems is acquired according to the time interval and the location interval.

[0020] Optionally, the step of extracting the second abnormal feature of the acquired data information of other intelligent perception systems specifically includes:

[0021] Classifying the data information of the other intelligent sensing systems according to device types;

[0022] For the classified data information, abnormal data is screened according to the corresponding device types to obtain second data information;

[0023] Feature extraction is performed on the screened second data information to obtain a second abnormal feature.

[0024] Optionally, the step of extracting the second abnormal feature of the acquired data information of other intelligent perception systems specifically includes:

[0025] Directly identifying second data information marked as abnormal from the data information of the other intelligent perception system;

[0026] Feature extraction is performed on the second data information to obtain a second abnormal feature.

[0027] Optionally, the step of performing feature matching and time-series association on the first abnormal feature and the second abnormal feature according to the time sequence of generation of the first data information and the second data information specifically includes:

[0028] According to the time sequence of the generation of the first data information and the second data information, the first abnormal feature and the second abnormal feature are matched by a preset abnormal event judgment model to determine whether there is a logical correlation between the first abnormal feature and the second abnormal feature;

[0029] If so, the first abnormal feature and the second abnormal feature are temporally correlated in chronological order.

[0030] Optionally, the step of adding an event tag to the first data information according to the result of feature matching and storing the event tag specifically includes:

[0031] If there is a logical association between the first abnormal feature and the second abnormal feature, obtaining an abnormal event generation event label according to the abnormal event judgment model;

[0032] Adding an event label to the first data information corresponding to the first abnormal feature;

[0033] The first data information to which the event tag is added and the second data information corresponding to the second abnormal feature are bound and stored together.

[0034] Optionally, the step of adding an event tag to the first data information according to the result of feature matching and storing the event tag further includes:

[0035] If there is no logical association between the first abnormal feature and the second abnormal feature, the abnormal event judgment model obtains the abnormal event only according to the first abnormal feature and generates a corresponding event label;

[0036] An event label is added to the first data information corresponding to the first abnormal feature and stored.

[0037] Optionally, the method further comprises:

[0038] If there is no logical association between the first abnormal feature and the second abnormal feature, the abnormal event judgment model obtains the abnormal event only according to the second abnormal feature and generates a corresponding event label;

[0039] Extracting third data information centered on the time node when the second data information was generated and within the time threshold from the multi-source heterogeneous data;

[0040] An event tag is added to the third data information, and the third data information is bound to the second data information and stored together.

[0041] A second aspect of an embodiment of the present invention provides a smart lamp pole multi-source heterogeneous data management system, including:

[0042] A data acquisition unit, used to acquire multi-source heterogeneous data generated by the smart light pole;

[0043] A feature extraction unit, used to classify the acquired data and extract abnormal features according to the sources of the multi-source heterogeneous data, to obtain a first abnormal feature;

[0044] The data acquisition unit is further used to acquire data information generated by other intelligent sensing systems of the smart city at corresponding time nodes and locations based on the time node at which the first data information corresponding to the first abnormal feature is generated and the location information of the smart lamp pole;

[0045] The feature extraction unit is further used to extract a second abnormal feature of the acquired data information of other intelligent perception systems, and the data information corresponding to the second abnormal feature is the second data information;

[0046] A feature association unit, configured to perform feature matching and time-series association on the first abnormal feature and the second abnormal feature according to the time sequence in which the first data information and the second data information are generated;

[0047] A data storage unit is used to add an event tag to the first data information according to the result of feature matching and store it.

[0048] In summary, the present invention provides a method and system for managing multi-source heterogeneous data of smart light poles, which can associate abnormal features in the multi-source heterogeneous data generated by the smart light poles with abnormal events occurring in the current scene, and filter out valuable parts for storage based on the association results. This effectively reduces the storage volume of multi-source heterogeneous data on smart light poles, and at the same time, identifies the stored data information through corresponding event tags, which facilitates retrieval and use after storage, and improves the use value of multi-source heterogeneous data of smart light poles. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 A method flow chart of a method for managing multi-source heterogeneous data of a smart lamp pole according to an embodiment of the present invention;

[0051] Figure 2This is a functional module block diagram of a smart lamp pole multi-source heterogeneous data management system according to an embodiment of the present invention.

[0052] Reference numerals:

[0053] Data acquisition unit 110; feature extraction unit 120; feature association unit 130; data storage unit 140. DETAILED DESCRIPTION

[0054] With the acceleration of urbanization and the advancement of smart city construction, smart light poles, as an important part of smart cities, have been widely used in every corner of the city. Smart light poles not only provide basic lighting functions, but also integrate a variety of sensors and communication equipment for environmental monitoring, traffic management, public safety, etc. The data formats generated by different devices may be different, and because there are a large number of devices that continuously generate data, the overall data volume is very large. Moreover, although the total amount of data is large, the proportion of truly valuable information may be very small.

[0055] Therefore, how to effectively manage the multi-source heterogeneous data generated by smart light poles to fully tap their potential value is an urgent problem to be solved.

[0056] In view of this, the designers of the present invention have designed a method and system for managing multi-source heterogeneous data of smart lamp poles.

[0057] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0058] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0060] In the description of the present invention, it should be noted that the terms "top", "bottom", "inside", "outside", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the invented product is usually placed when in use, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0061] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0062] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0063] The following is a detailed description of a smart lamp pole multi-source heterogeneous data management method provided in this embodiment.

[0064] See also Figure 1 This embodiment provides a method for managing multi-source heterogeneous data of smart lamp poles, the method comprising:

[0065] Step S101, obtaining multi-source heterogeneous data generated by the smart lamp pole.

[0066] There are many types of integrated functional units or integrated devices that can be installed on smart light poles. They not only provide basic lighting functions, but also integrate various environmental parameter sensors, image acquisition modules, positioning modules and communication modules for collecting and processing various data. For example, sensors such as temperature, humidity, light intensity, air quality, cameras, vehicle detectors, Wi-Fi, 5G, LoRa and other communication modules. Different smart light poles may have different numbers and types of integrated functional units installed according to their specific usage scenarios, so the composition of the generated multi-source heterogeneous data also varies. Usually, before these multi-source heterogeneous data are processed uniformly, certain data integration is required. The subsequent specific processing actions can be used to determine how to integrate the data in the early stage.

[0067] It should be noted that, since the multi-source heterogeneous data on the smart light pole is continuously generated over time, the multi-source heterogeneous data can be acquired according to a preset time period, and the smart light pole multi-source heterogeneous data management method provided by this implementation is executed once each acquisition. In addition, certain trigger conditions can also be set, and when the conditions are met, the smart light pole multi-source heterogeneous data management method provided by this implementation is executed once.

[0068] Step S102 , classifying and extracting abnormal features from the acquired data according to the respective sources of the multi-source heterogeneous data, to obtain a first abnormal feature.

[0069] In the embodiment of the present invention, the preliminary processing of multi-source heterogeneous data is mainly to classify the data by source. For data from different devices or functional units, the data types are first divided, such as light intensity data, temperature data, camera data, etc.

[0070] Since the abnormal state judgment methods and judgment conditions of different types of data are different, only after the data is classified first, it is convenient to extract the abnormal part of the data later. The obtained first abnormal features correspond to the abnormal states of multiple different types of data. For example, if there are N functional units or integrated devices integrated in a smart lamp pole, each functional unit or integrated device with an abnormal state will extract a first abnormal feature. These multiple first abnormal features jointly reflect the data anomaly of the smart lamp pole within the scope of the extracted multi-source heterogeneous data.

[0071] As a preferred embodiment of the present invention, step S102 specifically includes:

[0072] Categorize acquired data based on device type;

[0073] For the classified data, screening abnormal data according to the corresponding device types to obtain first data information;

[0074] Feature extraction is performed on the screened first data information to obtain a first abnormal feature.

[0075] Specifically, after the acquired data is classified, since the abnormal judgment methods and conditions for different types of device data are different and can even be dynamically defined and set by the user, it is necessary to screen the abnormal data separately. For each different type of data, the abnormal first data information is screened out separately, and then feature extraction is performed based on the first data information to obtain multiple first abnormal features corresponding to different types of data.

[0076] It should be noted that when some types of data do not filter out abnormal data, the first abnormal feature of the data of this type will not be extracted.

[0077] Step S103, based on the time node at which the first data information corresponding to the first abnormal feature is generated and the location information of the smart lamp pole, obtain the data information generated by other intelligent sensing systems of the smart city at the corresponding time node and location.

[0078] In smart cities, there are usually many intelligent perception systems for different scenarios and different needs. In this embodiment, the other intelligent perception system is at least one of the vehicle-road-cloud system and the roadside holographic perception system. The types of information obtained include vehicle status data, vehicle positioning data, traffic status data, road environment status data, and crowd density data.

[0079] Problems with the data generated by the smart light pole itself may be caused by external or internal factors; at the same time, problems with the data generated by the smart light pole itself may also affect the data collected by other intelligent sensing systems. By obtaining the data information generated by other intelligent sensing systems at the corresponding time nodes and locations for comparison, effective judgments can be made, which facilitates the classification and division of abnormal data to improve the subsequent use value.

[0080] As a preferred embodiment of the present invention, step S103 specifically includes:

[0081] The time node at which the first data information is generated is taken as the center, and the preset time threshold is taken as the range, as the time interval for acquiring data information of other intelligent perception systems;

[0082] Taking the position of the smart lamp pole generating the first data information as the center and the preset distance threshold as the range as the position interval for acquiring data information of other intelligent sensing systems;

[0083] The data information generated by other intelligent sensing systems is acquired according to the time interval and the location interval.

[0084] It should be noted that the preset time threshold and the preset distance threshold are determined according to actual usage requirements. The larger the time threshold and the distance threshold are set, the more data is obtained and the more computing resources are consumed.

[0085] On the other hand, when the first data information includes multiple types of data, the time nodes of the generation of different types of data may be different. In this case, a time point can be selected or calculated based on the multiple time points as the time node of the generation of the first data information. The specific method can be to take the average value, or the middle value, or to take the earliest or latest time point as the time node.

[0086] As a preferred method of an embodiment of the present invention, when acquiring data information generated by other intelligent perception systems, all data that meet the acquisition conditions can be acquired, or the data type to be acquired can be determined based on the data type included in the first data information, for example, only data information of a type that can only be associated with the data type included in the first data information can be acquired.

[0087] Step S104: extracting a second abnormal feature of the acquired data information of other intelligent perception systems, wherein the data information corresponding to the second abnormal feature is the second data information.

[0088] Taking into account that other intelligent perception systems also have data processing and analysis functions, when obtaining data information from other intelligent perception systems, in addition to the data information itself, the information that has been processed can also be obtained. In this case, different processing methods can be adopted to obtain the second abnormal feature, which are explained in detail below.

[0089] As a preferred embodiment of the present invention, step S104 specifically includes:

[0090] Classifying the data information of the other intelligent sensing systems according to device types;

[0091] For the classified data information, abnormal data is screened according to the corresponding device types to obtain second data information;

[0092] Feature extraction is performed on the screened second data information to obtain a second abnormal feature.

[0093] When the acquired data information only includes raw data, the second abnormal feature needs to be acquired in the same way as the first abnormal feature. That is, the data is first classified according to the device type, and then the abnormal data is screened. For each different type of data, the abnormal second data information is screened out respectively, and then feature extraction is performed based on the second data information to obtain multiple second abnormal features corresponding to different types of data.

[0094] As a preferred embodiment of the present invention, step S104 specifically includes:

[0095] Directly identifying second data information marked as abnormal from the data information of the other intelligent perception system;

[0096] Feature extraction is performed on the second data information to obtain a second abnormal feature.

[0097] When acquiring data information, if processed information of the processed anomaly-labeled data is also acquired at the same time, the second data information labeled as abnormal can be directly identified therefrom, and then feature extraction is performed on the second data information to obtain a second abnormal feature.

[0098] Regardless of the above methods, multiple second abnormal features corresponding to different data types can be extracted, and these multiple second abnormal features jointly reflect the data abnormalities of other intelligent sensing systems in the corresponding time interval near the smart lamp pole. It should be noted that when some types of data are not screened out as abnormal data, the second abnormal features of this type of data will not be extracted.

[0099] Step S105 , performing feature matching and time-series association on the first abnormal feature and the second abnormal feature according to the time sequence in which the first data information and the second data information are generated.

[0100] Through feature matching based on time sequence, it is possible to determine whether there is a logical association between the first abnormal feature and the second abnormal feature. The multi-source heterogeneous data of smart lamp poles that are associated with data anomalies of other intelligent perception systems are valuable information worth storing. Temporal association is a way to present the specific value of multi-source heterogeneous data. Through temporal association, the multi-source heterogeneous data of smart lamp poles can be linked with data anomalies of other intelligent perception systems in time sequence, which is convenient for subsequent search and call.

[0101] Specifically, the above step S105 specifically includes:

[0102] According to the time sequence of the generation of the first data information and the second data information, the first abnormal feature and the second abnormal feature are matched by a preset abnormal event judgment model to determine whether there is a logical correlation between the first abnormal feature and the second abnormal feature;

[0103] If so, the first abnormal feature and the second abnormal feature are temporally correlated in chronological order.

[0104] Whether it is an external factor that causes a problem with the data generated by the smart light pole itself, or a problem with the data generated by the smart light pole itself that affects the data collected by other intelligent sensing systems, the process of affecting the transmission can inevitably be reflected in the order of time. Therefore, matching the first abnormal feature and the second abnormal feature at once according to the order of time when the first data information and the second data information are generated can more efficiently determine the correlation between the two.

[0105] When matching the first abnormal feature and the second abnormal feature, it is done through the abnormal event judgment model. In the abnormal event judgment model, the status of all abnormal events related to the multi-source heterogeneous data of the smart lamp pole is pre-entered, and when each abnormal event occurs, the specific related data type and the time series change law of the data abnormal feature corresponding to each data type are recorded. By inputting the first abnormal feature and the second abnormal feature into the model, firstly, it can be matched to see whether there is a corresponding abnormal event, and secondly, if there is a match, it can be further judged the correlation between the first abnormal feature and the second abnormality, which is the triggering factor and which is affected.

[0106] It should be noted that the establishment of an abnormal event judgment model can be achieved in many ways, such as collecting relevant real original data when various types of events occur based on the knowledge graph model of smart transportation; then clearing noise data, processing missing values, and formatting and standardizing data; using natural language processing (NLP) and machine learning technology to extract entities and their relationships from text data; converting the extracted entities and relationships into nodes and edges in the graph database; defining ontology to standardize entity types and relationship types; providing a query interface to support complex query requirements, setting the data of the query interface as abnormal features, and setting the query result output as abnormal events and the order of influence of abnormal features in abnormal events. Through the above process, the abnormal event judgment model can be established through the knowledge graph model.

[0107] In addition, based on the relevant real original data collected when each type of event occurs, a model based on machine learning and artificial intelligence can be established to implement an abnormal event judgment model. In some scenarios where the data type is relatively simple, an abnormal event judgment model can also be established based on database technology, rule engines, etc., which are common applications of existing technologies and will not be repeated here.

[0108] In the above steps of this embodiment, it is mentioned that multiple first data information in multiple different types of data respectively correspond to multiple first abnormal features, and the time nodes at which these first data information are generated may be different. Correspondingly, the time nodes at which multiple second data information are generated may also be different. Therefore, when performing the first abnormal feature and the second abnormal feature through the abnormal event judgment model, it is necessary to perform feature matching in chronological order.

[0109] For the first abnormal feature and the second abnormal feature that are matched as belonging to the same abnormal event, time series association is performed according to the order of time nodes at which the corresponding first data information and second data information are generated.

[0110] For example, for abnormal event X, the matched abnormal features are the first abnormal features A1 and A2 and the second abnormal features B2 and B3. The time nodes for generating the first data information corresponding to A1 and A2 are T1 and T2, and the time nodes for generating the second data information corresponding to B2 and B3 are T3 and T4. The sequence of the time nodes is T3-T4-T1-T2, and the features after time series association are B2-B3-A1-A2.

[0111] After matching and associating all first abnormal features and second abnormal features in chronological order, it is necessary to store the filtered valuable data.

[0112] Step S106: adding an event tag to the first data information according to the result of feature matching and storing the event tag.

[0113] Since the first data information is generated by the smart lamp pole and the second data information is obtained from other systems, the main consideration is the storage of the first data information.

[0114] Based on the result of feature matching, the first data information is added with an event tag in a corresponding manner and stored. Specifically, it can be divided into the following situations, which will be explained in detail below.

[0115] As a preferred implementation, step S106 further specifically includes:

[0116] If there is a logical association between the first abnormal feature and the second abnormal feature, obtaining an abnormal event generation event label according to the abnormal event judgment model;

[0117] Adding an event label to the first data information corresponding to the first abnormal feature;

[0118] The first data information to which the event tag is added and the second data information corresponding to the second abnormal feature are bound and stored together.

[0119] For the first case, it is to find an abnormal event that matches the first abnormal feature and the second abnormal feature, indicating that in the abnormal event, the first abnormal feature and the second abnormal feature have a logical association relationship. At this time, after association based on the above-mentioned time series association method, the event label of the abnormal event is added to the first data information to be associated. Then the first data information and the second data information corresponding to the first abnormal feature and the second abnormal feature to be associated are stored in the order of time series association. Since the event label is added, these stored associated data information can be searched and used by using the event label as a keyword. If you need to retrieve and call the data related to this type of abnormal event in the future, you can easily find it by retrieval.

[0120] As a preferred implementation, step S106 further specifically includes:

[0121] If there is no logical association between the first abnormal feature and the second abnormal feature, the abnormal event judgment model obtains the abnormal event only according to the first abnormal feature and generates a corresponding event label;

[0122] An event label is added to the first data information corresponding to the first abnormal feature and stored.

[0123] For the second case, the abnormal event cannot match the first abnormal feature and the second abnormal feature, indicating that there is no logical association between the first abnormal feature and the second abnormal feature. At this time, the abnormal event judgment model matches the abnormal event associated only with the first abnormal feature and generates a corresponding event label. In this case, it means that the abnormality of some data in the multi-source heterogeneous data of the smart lamp pole is caused by its own reasons and has no impact on other intelligent perception systems. At this time, only the data and time itself need to be recorded.

[0124] Based on the second case above, there is another type of data that needs to be saved. The specific steps are as follows:

[0125] If there is no logical association between the first abnormal feature and the second abnormal feature, the abnormal event judgment model obtains the abnormal event only according to the second abnormal feature and generates a corresponding event label;

[0126] Extracting third data information centered on the time node when the second data information was generated and within the time threshold from the multi-source heterogeneous data;

[0127] An event tag is added to the third data information, and the third data information is bound to the second data information and stored together.

[0128] That is, when there is no logical association between the first abnormal feature and the second abnormal feature, the multi-source heterogeneous data generated by the smart light pole at the corresponding time point, i.e., the third data information, is synchronously saved for the second data information with the second abnormal feature. In this way, when other intelligent perception systems analyze the abnormal second data information, they can apply to the database that stores the data information to call the third data information generated by the smart light pole at the time point when the second data information is generated, as a reference or benchmark data for analysis, which can also reflect the partial value of the multi-source heterogeneous data generated by the smart light pole.

[0129] In actual use, when it is necessary to perform data analysis on abnormal events that have occurred, the time-series correlation data when the abnormal event occurred can be quickly and accurately retrieved through the keywords of the event label in the database that stores multi-source heterogeneous data of smart lamp poles, which facilitates the subsequent use of the data in different analysis demand scenarios.

[0130] In summary, the smart lamp pole multi-source heterogeneous data management method provided by the present invention can associate the abnormal features in the multi-source heterogeneous data generated by the smart lamp pole with the abnormal events occurring in the current scene, and filter out the valuable parts for storage based on the association results. This effectively reduces the storage volume of multi-source heterogeneous data on the smart lamp pole, and at the same time, identifies the stored data information through corresponding event tags, which facilitates retrieval and use after storage, and improves the use value of the multi-source heterogeneous data of the smart lamp pole.

[0131] like Figure 2 As shown, the smart lamp pole multi-source heterogeneous data management system provided by the present invention comprises:

[0132] The data acquisition unit 110 is used to acquire multi-source heterogeneous data generated by the smart lamp pole;

[0133] A feature extraction unit 120 is used to classify the acquired data and extract abnormal features according to the sources of the multi-source heterogeneous data to obtain a first abnormal feature;

[0134] The data acquisition unit 110 is further used to acquire data information generated by other intelligent sensing systems of the smart city at corresponding time nodes and locations based on the time node at which the first data information corresponding to the first abnormal feature is generated and the location information of the smart lamp pole;

[0135] The feature extraction unit 120 is further used to extract a second abnormal feature of the acquired data information of other intelligent perception systems, and the data information corresponding to the second abnormal feature is the second data information;

[0136] A feature association unit 130, configured to perform feature matching and time-series association on the first abnormal feature and the second abnormal feature according to the time sequence in which the first data information and the second data information are generated;

[0137] The data storage unit 140 is used to add event tags to the first data information according to the result of feature matching and store the event tags.

[0138] The smart lamp pole multi-source heterogeneous data management system provided in the embodiment of the present invention is used to implement the above-mentioned smart lamp pole multi-source heterogeneous data management method, so the specific implementation method is the same as the above-mentioned method and will not be repeated here.

[0139] It should be noted that the smart lamp pole multi-source heterogeneous data management system provided by the present method embodiment can be implemented through the OpenHarmony system. Depending on the specific usage scenario, it can be set on the hardware system integrated in the smart lamp pole, or it can be set on other hardware devices that have established information communication and data processing capabilities for the smart lamp pole.

[0140] In summary, the present invention provides a method and system for managing multi-source heterogeneous data of smart light poles, which can associate abnormal features in the multi-source heterogeneous data generated by the smart light poles with abnormal events occurring in the current scene, and filter out valuable parts for storage based on the association results. This effectively reduces the storage volume of multi-source heterogeneous data on smart light poles, and at the same time, identifies the stored data information through corresponding event tags, which facilitates retrieval and use after storage, and improves the use value of multi-source heterogeneous data of smart light poles.

[0141] In several embodiments disclosed in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a module, a program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0142] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0143] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

Claims

1. A method for managing multi-source heterogeneous data of smart lamp poles, characterized in that: The method comprises: Acquire multi-source heterogeneous data generated by smart light poles; Classify the acquired data and extract abnormal features according to the sources of the multi-source heterogeneous data to obtain a first abnormal feature; Based on the time node at which the first data information corresponding to the first abnormal feature is generated and the location information of the smart lamp pole, data information generated by other smart sensing systems of the smart city at the corresponding time node and location is obtained; Extracting a second abnormal feature of the acquired data information of other intelligent perception systems, wherein the data information corresponding to the second abnormal feature is the second data information; Performing feature matching and time-series association on the first abnormal feature and the second abnormal feature according to the time sequence of generation of the first data information and the second data information; According to the result of feature matching, an event tag is added to the first data information and stored.

2. The smart lamp pole multi-source heterogeneous data management method according to claim 1 is characterized in that: The step of classifying the acquired data and extracting abnormal features according to the respective sources of the multi-source heterogeneous data to obtain the first abnormal feature specifically includes: Categorize acquired data based on device type; For the classified data, screening abnormal data according to the corresponding device types to obtain first data information; Feature extraction is performed on the screened first data information to obtain a first abnormal feature.

3. The method for managing multi-source heterogeneous data of smart lamp poles according to claim 2 is characterized in that: The step of acquiring data information generated by other intelligent sensing systems of the smart city at corresponding time nodes and locations based on the time node at which the first data information corresponding to the first abnormal feature is generated and the location information of the smart lamp pole specifically includes: The time node at which the first data information is generated is taken as the center, and the preset time threshold is taken as the range, as the time interval for acquiring data information of other intelligent perception systems; Taking the position of the smart lamp pole generating the first data information as the center and the preset distance threshold as the range as the position interval for acquiring data information of other intelligent sensing systems; The data information generated by other intelligent sensing systems is acquired according to the time interval and the location interval.

4. The method for managing multi-source heterogeneous data of smart lamp poles according to claim 3 is characterized in that: The step of extracting the second abnormal feature of the acquired data information of other intelligent perception systems specifically includes: Classifying the data information of the other intelligent sensing systems according to device types; For the classified data information, abnormal data is screened according to the corresponding device types to obtain second data information; Feature extraction is performed on the screened second data information to obtain a second abnormal feature.

5. The method for managing multi-source heterogeneous data of smart lamp poles according to claim 3 is characterized in that: The step of extracting the second abnormal feature of the acquired data information of other intelligent perception systems specifically includes: Directly identifying second data information marked as abnormal from the data information of the other intelligent perception system; Feature extraction is performed on the second data information to obtain a second abnormal feature.

6. The smart lamp pole multi-source heterogeneous data management method according to any one of claims 3 or 4, characterized in that: The step of performing feature matching and time-series association on the first abnormal feature and the second abnormal feature according to the time sequence of the generation of the first data information and the second data information specifically includes: According to the time sequence of the generation of the first data information and the second data information, the first abnormal feature and the second abnormal feature are matched by a preset abnormal event judgment model to determine whether there is a logical correlation between the first abnormal feature and the second abnormal feature; If so, the first abnormal feature and the second abnormal feature are temporally correlated in chronological order.

7. The method for managing multi-source heterogeneous data of smart lamp poles according to claim 6, characterized in that: The step of adding an event tag to the first data information according to the result of feature matching and storing the event tag specifically includes: If there is a logical association between the first abnormal feature and the second abnormal feature, obtaining an abnormal event generation event label according to the abnormal event judgment model; Adding an event label to the first data information corresponding to the first abnormal feature; The first data information to which the event tag is added and the second data information corresponding to the second abnormal feature are bound and stored together.

8. The method for managing multi-source heterogeneous data of smart lamp poles according to claim 6 is characterized in that: The step of adding an event tag to the first data information according to the result of feature matching and storing the event tag further includes: If there is no logical association between the first abnormal feature and the second abnormal feature, the abnormal event judgment model obtains the abnormal event only according to the first abnormal feature and generates a corresponding event label; An event label is added to the first data information corresponding to the first abnormal feature and stored.

9. The method for managing multi-source heterogeneous data of smart lamp poles according to claim 6, characterized in that: The method further comprises: If there is no logical association between the first abnormal feature and the second abnormal feature, the abnormal event judgment model obtains the abnormal event only according to the second abnormal feature and generates a corresponding event label; Extracting third data information centered on the time node when the second data information was generated and within the time threshold from the multi-source heterogeneous data; An event tag is added to the third data information, and the third data information is bound to the second data information and stored together.

10. A smart lamp pole multi-source heterogeneous data management system, characterized in that: include: A data acquisition unit, used to acquire multi-source heterogeneous data generated by the smart light pole; A feature extraction unit, used to classify the acquired data and extract abnormal features according to the sources of the multi-source heterogeneous data, to obtain a first abnormal feature; The data acquisition unit is further used to acquire data information generated by other intelligent sensing systems of the smart city at corresponding time nodes and locations based on the time node at which the first data information corresponding to the first abnormal feature is generated and the location information of the smart lamp pole; The feature extraction unit is further used to extract a second abnormal feature of the acquired data information of other intelligent perception systems, and the data information corresponding to the second abnormal feature is the second data information; A feature association unit, configured to perform feature matching and time-series association on the first abnormal feature and the second abnormal feature according to the time sequence in which the first data information and the second data information are generated; A data storage unit is used to add an event tag to the first data information according to the result of feature matching and store it.

Images