A dynamic recommendation method and device based on LBS water-related information

Abstract

This invention provides a method and apparatus for dynamic recommendation of water-related information based on location-based services (LBS). The method includes: acquiring at least one water-related data item; determining a water conservancy object model and a water conservancy theme model; dividing a preset area to obtain a water-related information grid model; determining a water conservancy event model; forming multiple theme knowledge graphs based on water-related knowledge data in the water-related knowledge database corresponding to the water conservancy object model, the water conservancy theme model, the water-related information grid model, and the water conservancy event model; obtaining the target theme knowledge graph corresponding to the target water-related information grid from the multiple theme knowledge graphs based on the target water-related information grid to which the target object's location belongs; and obtaining at least one target-pushed water-related data based on the target theme knowledge graph and pushing it to the target object's client. This invention has the advantage of improving the effectiveness and timeliness of water-related information push.

Description

Technical Field

[0001] This invention relates to the field of computer information processing technology, and also to a method and apparatus for dynamic recommendation of water-related information based on LBS. Background Technology

[0002] Mobile services providing water-related information such as water conservancy and water affairs knowledge to the public mainly include WeChat official accounts, water-related mini-programs, and water-related mobile applications. The functions built into the business application layer of these services, and the water conservancy or water affairs information they push, are passive and ubiquitous, lacking strong relevance to the public and not reflecting public interest or desire. To achieve precise delivery of water conservancy and water affairs information and services that the public cares about, a reconstruction of the data resource pool and application support layer is necessary. Currently, the construction of the data resource layer and application support layer fails to aggregate and correlate data based on ontology (audience), theme, and physical mechanisms. It lacks theme-ontology and event-ontology connections, failing to support refined, user-centric water conservancy public services. The services built do not meet public expectations and cannot push water conservancy information based on user location. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and apparatus for dynamic recommendation of water-related information based on LBS, so as to improve the effectiveness and timeliness of pushing water-related information.

[0004] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0005] A first aspect of the present invention provides a dynamic recommendation method based on LBS-based water-related information, comprising:

[0006] Obtain at least one water-related data item;

[0007] Based on the at least one water-related data item, determine the water conservancy object model and the water conservancy theme model;

[0008] The preset area is divided according to the smallest spatial grid unit of each water-related theme in the water conservancy theme model to obtain the water-related information grid model.

[0009] Based on the water conservancy object model, the water conservancy theme model, and the water-related information grid model, determine the water conservancy event model;

[0010] Based on the water-related knowledge data in the water-related knowledge databases corresponding to the water conservancy object model, the water conservancy theme model, the water-related information grid model, and the water conservancy event model, multiple theme knowledge graphs are formed.

[0011] Based on the target water-related information grid to which the target object's location belongs, obtain the target topic knowledge graph corresponding to the target water-related information grid from the multiple topic knowledge graphs;

[0012] Based on the target topic knowledge graph, at least one type of target-push water-related data is obtained;

[0013] The target water-related data is pushed to the target client.

[0014] Optionally, at least one water-related data item may be acquired, including:

[0015] Obtain a resource catalog library containing preset water conservancy data;

[0016] The object class data of the resource catalog is parsed to obtain at least one water-related data item.

[0017] Optionally, based on the at least one water-related data item, a water conservancy object model and a water conservancy theme model are determined, including:

[0018] Based on the attributes of at least one water-related data item, determine the water conservancy object model;

[0019] Based on the relationship between different data items of the at least one water-related data item, subcategories of data items are determined, and water conservancy theme models are determined based on the major category to which the subcategories belong.

[0020] Optionally, the preset area is divided according to the smallest spatial grid unit of each water-related theme in the water conservancy theme model to obtain a water-related information grid model, including:

[0021] Obtain the grid cell partitioning parameters corresponding to each water-related theme in the water conservancy theme model;

[0022] According to the grid cell division parameters, determine the minimum spatial grid cell for each water-related theme;

[0023] The preset area is divided according to the smallest spatial grid unit of each water-related theme to obtain the water-related information grid model corresponding to each water-related theme.

[0024] Optionally, based on the water conservancy object model, the water conservancy theme model, and the water-related information grid model, a water conservancy event model is determined, including:

[0025] Based on the water-related information grid model, at least one target data item of the water conservancy object model corresponding to each water-related information grid is determined;

[0026] Based on the water conservancy theme model, determine the target water-related theme corresponding to at least one target data item;

[0027] Obtain water-related events related to the target water-related topic and determine the water-related event model.

[0028] Optionally, based on the water-related knowledge data in the water-related knowledge databases corresponding to the water conservancy object model, the water conservancy theme model, the water-related information grid model, and the water conservancy event model, multiple theme knowledge graphs are formed, including:

[0029] Knowledge extraction is performed on the water-related knowledge data corresponding to the water conservancy object model to obtain the first entity data;

[0030] Knowledge extraction is performed on the water-related knowledge data corresponding to the water-related information grid model to obtain the second entity data;

[0031] Knowledge extraction is performed on the water-related knowledge data corresponding to the water conservancy theme model to obtain third entity data;

[0032] Knowledge extraction is performed on the water-related knowledge data corresponding to the water conservancy event model to obtain the fourth entity data;

[0033] The first entity data, the second entity data, the third entity data, and the fourth entity data are fused together to obtain fused entity data.

[0034] Based on the fused entity data, multiple topic knowledge graphs are formed.

[0035] Optionally, based on the target water-related information grid to which the target object's location belongs, the target topic knowledge graph corresponding to the target water-related information grid is obtained from the plurality of topic knowledge graphs, including:

[0036] Obtain the geographical location of the target object;

[0037] Based on the geographical location of the target object, determine the target water-related information grid to which the geographical location belongs;

[0038] From the multiple topic knowledge graphs, obtain the target topic knowledge graph corresponding to the target water-related information grid.

[0039] A second aspect of the present invention provides a dynamic recommendation device based on LBS-based water-related information, comprising:

[0040] The acquisition module is used to acquire at least one water-related data item;

[0041] The processing module is configured to: determine a water conservancy object model and a water conservancy theme model based on at least one water-related data item; divide a preset area according to the smallest spatial grid unit of each water-related theme in the water conservancy theme model to obtain a water-related information grid model; determine a water conservancy event model based on the water conservancy object model, the water conservancy theme model, and the water-related information grid model; form multiple theme knowledge graphs based on water-related knowledge data in the water-related knowledge databases corresponding to the water conservancy object model, the water conservancy theme model, the water-related information grid model, and the water conservancy event model; obtain a target theme knowledge graph corresponding to the target water-related information grid from the multiple theme knowledge graphs based on the target water-related information grid to which the target object's location belongs; obtain at least one target-pushed water-related data based on the target theme knowledge graph; and push the target-pushed water-related data to the target object's client.

[0042] A third aspect of the present invention provides a computing device, comprising: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method described in the first aspect.

[0043] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method as described in the first aspect.

[0044] The above-described solution of the present invention has at least the following beneficial effects:

[0045] The above-mentioned solution of the present invention obtains at least one water-related data item, determines a water conservancy object model and a water conservancy theme model, then divides a preset area according to the smallest spatial grid unit of each water-related theme in the water conservancy theme model to obtain a water-related information grid model, and then determines a water conservancy event model based on the water conservancy object model, the water conservancy theme model, and the water-related information grid model. Furthermore, based on the water-related knowledge data in the water-related knowledge database corresponding to the water conservancy object model, the water conservancy theme model, the water-related information grid model, and the water conservancy event model, multiple theme knowledge graphs are formed. Based on the target water-related information grid to which the target object's location belongs, the target theme knowledge graph corresponding to the target water-related information grid is obtained from the multiple theme knowledge graphs. Based on the target theme knowledge graph, at least one target-pushed water-related data is obtained, and the target-pushed water-related data is pushed to the target object's client. This not only pushes water-related data to the target object based on its location, but also ensures that the pushed water-related data has high completeness and relevance, thus improving the effectiveness and timeliness of water-related data push. Attached Figure Description

[0046] Figure 1This is a flowchart illustrating the dynamic recommendation method for water-related information based on LBS in an embodiment of the present invention.

[0047] Figure 2 This is a schematic diagram of a spatial grid cell in an embodiment of the present invention;

[0048] Figure 3 This is a schematic diagram of the process of constructing a topic knowledge graph in an embodiment of the present invention;

[0049] Figure 4 This is a schematic diagram of the data layer and pattern layer of the knowledge graph in an embodiment of the present invention;

[0050] Figure 5 This is a schematic diagram of the structure of the LBS-based dynamic recommendation device for water-related information in an embodiment of the present invention. Detailed Implementation

[0051] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0052] like Figure 1 As shown, an embodiment of the present invention proposes a dynamic recommendation method based on LBS water-related information, comprising the following steps:

[0053] Step 101: Obtain at least one water-related data item;

[0054] Step 102: Determine the water conservancy object model and the water conservancy theme model based on the at least one water-related data item;

[0055] Step 103: Divide the preset area according to the smallest spatial grid unit of each water-related theme in the water conservancy theme model to obtain the water-related information grid model.

[0056] Step 104: Determine the water conservancy event model based on the water conservancy object model, the water conservancy theme model, and the water-related information grid model;

[0057] Step 105: Based on the water-related knowledge data in the water-related knowledge database corresponding to the water conservancy object model, the water conservancy theme model, the water-related information grid model, and the water conservancy event model, multiple theme knowledge graphs are formed.

[0058] Step 106: Based on the target water-related information grid to which the location of the target object belongs, obtain the target topic knowledge graph corresponding to the target water-related information grid from the multiple topic knowledge graphs;

[0059] Step 107: Obtain at least one type of target-push water-related data based on the target topic knowledge graph;

[0060] Step 108: Push the target water-related data to the target object's client.

[0061] The LBS-based dynamic recommendation method for water-related information in this invention obtains at least one water-related data item, determines a water conservancy object model and a water conservancy theme model, then divides a preset area according to the smallest spatial grid unit of each water-related theme in the water conservancy theme model to obtain a water-related information grid model, and then determines a water conservancy event model based on the water conservancy object model, water conservancy theme model, and water-related information grid model. Subsequently, based on the water-related knowledge data in the water-related knowledge database corresponding to the water conservancy object model, water conservancy theme model, water-related information grid model, and water conservancy event model, multiple theme knowledge graphs are formed. Based on the target water-related information grid to which the target object's location belongs, the target theme knowledge graph corresponding to the target water-related information grid is obtained from the multiple theme knowledge graphs. Based on the target theme knowledge graph, at least one target-pushed water-related data is obtained and pushed to the target object's client. This method not only pushes water-related data to the target object based on its location, but also ensures that the pushed water-related data has high completeness and relevance, thus improving the effectiveness and timeliness of water-related data push.

[0062] Here, LBS is short for Location Based Services, which uses various types of positioning technologies to obtain the current location of a positioning device and provides information resources and basic services to the positioning device via the mobile internet. In this application, water-related data can be pushed to the target object based on its location.

[0063] In an optional embodiment of the present invention, step 101 includes:

[0064] Step 1011: Obtain the resource catalog of preset water conservancy data;

[0065] Step 1012: Parse the object class data of the resource catalog library to obtain at least one water-related data item.

[0066] Specifically, the pre-set resource catalog of water conservancy data can be formed as shown in Table 1, using water-related data items from public services. This resource catalog can include databases for water conservancy projects, water supply, urban flooding, rainfall, water conservation, rivers, disaster prevention, drainage, water-related services, and spatial data. The water conservancy project database stores information on surrounding reservoirs, sluices, pumping stations, weirs, ponds, irrigation areas, as well as water conservancy scenic areas and water conservancy project management boundaries. The water supply database stores data on water tank cleaning, water quality testing, water outage notices, water supply restoration, secondary water supply, water usage suspension reports, pipe burst information, and water supply failure data. The urban flooding database stores locations of urban flooding, water depth, water level, and video data related to urban flooding. The rainfall database stores real-time and forecast rainfall data. The water conservation database stores data on water-saving appliances, water conservation guidelines, and water conservation rewards from water administration departments. The river database stores data on water quality monitoring of surrounding rivers, river health levels, river water levels during flood season, and early warning information. Disaster avoidance data primarily stores major disaster relief sites and nearby rescue points during flood season and urban flooding. Drainage data mainly stores the distribution of surrounding drainage networks, storm and sewage manhole covers, and storm and sewage manhole cover services currently under repair or requiring attention. The social services database stores water-related service organizations (payment points, repair points), surrounding water service authorities, etc. By accessing a pre-defined resource catalog of water conservancy data, it is convenient to directly extract relevant data items, providing a foundation for subsequently pushing water-related data based on the location of target objects.

[0067] The object classes in Tables 1 to 4 include data items related to each object. Therefore, at least one water-related data item can be obtained directly from the object class data in the resource catalog.

[0068] Table 1 Resource Catalog 1

[0069]

[0070] Table 2 Resource Catalog 2

[0071]

[0072] Table 3 Resource Catalog 3

[0073]

[0074] Table 4 Resource Catalog 4

[0075]

[0076] In an optional embodiment of the present invention, step 102 includes:

[0077] Step 1021: Determine the water conservancy object model based on the attributes of the at least one water-related data item;

[0078] Specifically, data item attributes include at least one of the following: basic, spatial, operational, and temporal attributes. The water conservancy object model describes object attributes according to the object classes in the resource catalog, including basic, spatial, operational, and temporal attributes. Basic attributes include name, code, type (e.g., reservoir, river, pumping station), and administrative affiliation. Spatial attributes include latitude and longitude coordinates, watershed range, and grid cell number. Operational attributes include function (flood control, irrigation, water supply), design standards, and operational status (normal / maintained). Temporal attributes include construction time, update cycle, and data acquisition timestamp.

[0079] Step 1022: Based on the relationship between different data items of the at least one water-related data item, determine the sub-category of the data item, and determine the water conservancy theme model based on the major category to which the sub-category belongs.

[0080] Specifically, the relationships between different data items can be topological, such as upstream-downstream relationships (e.g., the confluence of rivers and reservoirs), or inclusion relationships (e.g., a watershed contains sub-watersheds); they can also be business-related, such as dependency relationships (e.g., a pumping station depends on the power grid), or impact range relationships (e.g., damage to a dike affects surrounding farmland). Based on the relationships between different data items and the resource catalog shown in Table 1, corresponding subcategories and major categories can be determined, and each major category corresponds to a water conservancy theme model. Here, the steps for determining the water conservancy theme model may include:

[0081] Aggregate subcategories. Subcategories belonging to the same major category are grouped into the corresponding themes (e.g., "Nature", "Engineering and Facilities", and "Main Functional Zones" are grouped into "Water Conservancy Projects").

[0082] Define the relationships between topics. For example, a dependency relationship: the disaster avoidance data topic depends on the water security data of the river (lake) topic; an impact relationship: the gate scheduling of the drainage information topic affects the water security data of the river (lake) topic (such as upstream water release).

[0083] Create a thematic view. This could be a dynamic view: a real-time water level-flow curve (used for urban flooding early warning information); or a static view: rainfall forecast-drainage information (used for water resource allocation).

[0084] Thematic model and grid model integration. Spatial aggregation: statistical analysis of thematic data by grid unit (e.g., "average rainfall in grid A"); hierarchical drill-down: drill down from thematic overview (e.g., provincial water quality compliance rate) to grid details (e.g., COD concentration within a specific grid).

[0085] In an optional embodiment of the present invention, step 103 includes:

[0086] Step 1031: Obtain the grid cell partitioning parameters corresponding to each water-related theme in the water conservancy theme model;

[0087] Specifically, each water-related theme corresponds to a grid unit division parameter. Based on different types of water-related themes, spatial grids are defined separately for themes such as water supply, flooding, rainfall, water conservation, rivers, and disaster relief. The grid unit division parameters for each water-related theme are as follows: For water conservancy projects, the network unit is the area within a radius of 5 to 10 kilometers of the target location. For water supply themes, the smallest grid unit is the water supply area controlled by the valves of the water supply network. For flooding themes, the grid unit is by default the area within a 5-kilometer radius of the target location, but can also be the route taken to the destination. For rainfall themes, the grid unit is the smallest administrative division of the target location. For water conservation, the grid unit is the administrative division. For rivers (including all water bodies) and disaster relief sites, no grid units are required; the distance to the target location is the primary factor.

[0088] Step 1032: Determine the minimum spatial grid unit for each water-related theme according to the grid unit division parameters.

[0089] Specifically, the minimum spatial grid unit for each water-related theme can be directly extracted from the grid unit division parameters. Taking water-related themes in water conservancy projects as an example, the corresponding minimum spatial grid unit is 5 to 10 kilometers.

[0090] Step 1033: Divide the preset area according to the smallest spatial grid unit of each water-related theme to obtain the water-related information grid model corresponding to each water-related theme.

[0091] Specifically, the preset area can be a map of a city or a country, and its scope can be set according to specific needs. The preset area is divided into multiple minimum spatial grid units according to the minimum spatial grid unit corresponding to each water-related theme in the grid unit division parameters. It should be noted that the minimum spatial grid units of multiple water-related themes can be displayed on the same map (each minimum spatial grid unit of each water-related theme has a different color for differentiation), or each minimum spatial grid unit of a water-related theme can correspond to a unique map, depending on the actual situation. After the preset area is divided, a water-related information grid model corresponding to the water-related theme is obtained. This model can be a map with spatial grid units containing at least one water-related theme. When dividing the preset area, rectangular or circular grids can be used. In practice, irregular shapes, such as polygons, can also be used.

[0092] Here, when dividing the preset region into spatial grid cells, if the preset region is not rectangular (such as a polygon), the grid needs to be calculated first based on the circumscribed rectangle, and then the grid cells within the polygon are retained by clipping; if the preset region is rectangular, in the Cartesian coordinate system, the region boundary coordinates are: the minimum x-coordinate (left boundary) is... The maximum x-coordinate (right boundary) is The minimum y-coordinate (lower boundary) is The maximum y-coordinate (upper boundary) is The size of the preset area is: width (length in the x-direction) W. The calculated height (length in the y-direction) H is obtained through... Calculated.

[0093] For the i-th column ( i ∈[0, n col -1] ), row j ( j∈[0,n row -1] The spatial grid cell has the following coordinate range:

[0094] x direction ( i ∈[0, n col -1] ): [ X min +i∙dx,min( X min +(i+1)∙dx, X m ax )] If the last column exceeds If so, then cut it off;

[0095] y direction ( j∈[0,n row -1] ): [ Y min +j∙dy,min( Y min +(j+1)∙dy, Y m ax )] If the last line exceeds If so, then cut it off;

[0096] The width dx and height dy of each grid cell must be calculated using the following formula to determine the minimum number of rows and columns required to cover the entire area (rounded up to avoid incomplete coverage):

[0097] Minimum number of columns (Number of units in the x-direction) through Calculated minimum number of rows (Number of units in the y-direction) through Calculations show that This is a rounding function; for example, if the region width is 10m and the cell width is 3m, then... Take 4 columns.

[0098] like Figure 2 As shown, taking water supply and water-related themes as an example, the preset area 1 is divided according to the water supply area 3 (circle in the figure) controlled by the water supply network valve 2 as the smallest spatial grid unit.

[0099] In an optional embodiment of the present invention, step 104 includes:

[0100] Step 1041: Based on the water-related information grid model, determine at least one target data item of the water conservancy object model corresponding to each water-related information grid;

[0101] Specifically, such as Figure 3 As shown, by establishing a many-to-many mapping relationship between the water conservancy object model and the water-related information grid model, each water-related information grid in the water-related information grid model corresponds to at least one target data item in the water conservancy object model. For example, a water-related information grid corresponds to data items such as reservoirs, rivers, water plants, and water supply networks in the water conservancy object model.

[0102] Step 1042: Based on the water conservancy theme model, determine the target water-related theme corresponding to at least one target data item;

[0103] Specifically, the target water-related themes corresponding to different target data items can be determined from the water conservancy theme model. For example, if the target data items include reservoir data, river data, water plant data, and water supply network data, then the target water-related themes corresponding to reservoir data and river data can be found from the water conservancy theme model to be water conservancy engineering water-related themes, and the target water-related themes corresponding to water plant data and water supply network data to be water supply water-related themes.

[0104] Step 1043: Obtain the water conservancy events related to the target water-related topic and determine the water conservancy event model.

[0105] Specifically, the system acquires real-time data on water-related events occurring under the target water theme, such as urban rainstorms, public exposure, and water pollution. It determines event attributes, including event ID, name, occurrence time, duration, and severity (e.g., rainstorm level, pollution level), as well as spatial attributes, such as the affected grid range (based on geographic grids or administrative grids) and key facility coordinates (e.g., drainage outlets, monitoring stations). It also determines operational attributes, such as associated objects (e.g., rivers, pumping stations), triggering conditions (e.g., rainfall > 50 mm / h), and handling status (unprocessed / processing / resolved). Then, based on preset event triggering standards (e.g., "continuous 2-hour rainfall ≥ 30 mm triggers a rainstorm warning"), it constructs an event association network (e.g., "rainstorm → drainage network overload → road flooding → traffic paralysis → public exposure"). Finally, it retrieves corresponding handling plans from historical water-related event handling plans to form a water-related event model. This facilitates subsequent event identification, association analysis, spatial positioning, impact assessment, and handling recommendations based on occurring water-related events.

[0106] In an optional embodiment of the present invention, step 105 includes:

[0107] Step 1051: Extract knowledge from the water-related knowledge data corresponding to the water conservancy object model to obtain the first entity data;

[0108] Step 1052: Extract knowledge from the water-related knowledge data corresponding to the water-related information grid model to obtain the second entity data;

[0109] Step 1053: Extract knowledge from the water-related knowledge data corresponding to the water conservancy theme model to obtain the third entity data;

[0110] Step 1054: Extract knowledge from the water-related knowledge data corresponding to the water conservancy event model to obtain the fourth entity data;

[0111] Step 1055: Perform fusion processing on the first entity data, the second entity data, the third entity data, and the fourth entity data to obtain fused entity data;

[0112] Specifically, knowledge extraction can be performed on the water-related knowledge data corresponding to the water conservancy object model, water-related information grid model, water conservancy theme model, and water conservancy event model in the following ways to obtain the first entity data, the second entity data, the third entity data, and the fourth entity data:

[0113] Multiple entities (such as water conservancy object entities including specific objects like rivers, reservoirs, and pumping stations; attribute and indicator entities including attributes and values ​​like water level, flow rate, and water quality; event and phenomenon entities including events like rainstorms, urban flooding, and dam failures; and time and space entities including event occurrence time and geographical location) are extracted from water-related knowledge data to form an entity set. ,in, For a single entity, such as identifying entities like "Reservoir A" (reservoir category) and "water level" (indicator category) from the text information "Reservoir A's water level exceeds the warning level" in water-related knowledge data. Multiple entities can be identified from the water-related knowledge data using regular expressions. Relationship extraction is performed using open information extraction methods, such as extracting the relationship "Reservoir A - flood discharge affects - River B" from "Reservoir A's flood discharge affects River B". Attribute extraction is performed using keyword matching, template filling, and table parsing, such as extracting the attribute "total capacity = 39.3 billion cubic meters" from "Reservoir A's total capacity is 39.3 billion cubic meters". Entity data here can include entities, relationships, and attributes identified from the water-related knowledge data.

[0114] Based on preset ontologies, such as entity type (e.g., reservoir, river, monitoring station), relationship type (e.g., "located in," "belongs to," "monitoring"), and attribute type (e.g., numerical, text, date), conflict resolution is performed on the descriptions of the same entity in the first, second, third, and fourth entity data (e.g., "reservoir capacity: 39.3 billion cubic meters and 40 billion cubic meters"). This can be done by adhering to official data sources. Then, the relationship expressions are unified, such as merging "water supply to" and "flow direction" into "water supply relationship," resulting in merged entity data.

[0115] Step 1056: Based on the fused entity data, form multiple topic knowledge graphs.

[0116] Specifically, entity data is stored and fused using triples (subject, attribute, value, or subject, relation, object) to obtain an initial knowledge graph. Then, the consistency of the graph is verified based on logical rules. If the verification passes, the initial knowledge graph is used as a topic knowledge graph. The topic knowledge graph is then divided according to different water-related topics, resulting in multiple topic knowledge graphs such as water conservancy object knowledge graph, water conservancy engineering knowledge graph, water supply knowledge graph, drainage knowledge graph, urban flooding knowledge graph, rainfall knowledge graph, water conservation knowledge graph, and event knowledge graph. This not only provides knowledge graphs corresponding to each water-related topic but also improves query efficiency. Here, taking the selection of a graph database to store fused entity data to obtain an initial knowledge graph as an example, firstly, attributes are added to the nodes and relationships in the fused entity data. For example, if a node is "river", its attribute is its specific length; if a relationship is "inflow", its attribute is the specific inflow amount. The fused entity data is then processed into JSON (an open standard file format and data exchange format) to reduce real-time parsing overhead. The JSON-formatted fused entity data is then imported into a preset attribute graph model to obtain the initial knowledge graph, which enables the search for data related to an entity by entity.

[0117] Based on the water-related theme, various data items are stored in relevant databases, including water conservancy project databases, water supply databases, urban flooding databases, rainfall databases, water conservation databases, river databases, disaster prevention databases, drainage data, water-related services, and spatial databases. The water conservancy project database stores information on surrounding reservoirs, sluices, pumping stations, weirs, ponds, irrigation areas, as well as water conservancy scenic areas and water conservancy project management boundaries. The water supply database stores data on water tank cleaning, water quality testing, water outage notices, water supply restoration, secondary water supply, water usage suspension reports, pipe burst information, and water supply failure data. The urban flooding database stores locations of urban flooding, water depth, severity of flooding, and video data related to urban flooding. The rainfall database stores real-time and forecast rainfall data. The water conservation database stores data on water-saving appliances, water conservation guidelines, and water conservation rewards from water administration departments. The river database stores data on water quality testing of surrounding rivers, river health levels, river water levels during flood season, and river early warning information. Disaster evacuation data is primarily used to store major evacuation sites and nearby rescue points during flood season and urban flooding. Drainage data is mainly used to store the distribution of surrounding drainage pipe networks, storm and sewage manhole covers, and storm and sewage manhole cover services that are under repair or require attention. The social services database stores water-related service providers (payment points, repair points), surrounding water service authorities, etc.

[0118] Water-related knowledge data under different water-related themes are described according to object classes in the data catalog, including basic, spatial, business, and temporal attributes. Determining the relationships between objects requires establishing a one-to-one mapping with the knowledge graph corresponding to the water-related theme type. The grid is mainly divided according to the major categories in the water resources data catalog service specifications. The theme model organizes data based on different service items, such as water supply and drainage. The event model needs to form a multi-dimensional, dynamic, and integrated data view based on specific events, such as urban rainstorms, exposure, and water pollution, and the mapping relationship between the knowledge engine and the grid.

[0119] Based on existing structured, unstructured, and semi-structured databases, and using a knowledge engine, knowledge is stored as graph data through knowledge modeling, extraction, fusion, and storage. A graph computing engine is used to manage and drive water conservancy knowledge elements, constructing knowledge graphs corresponding to water-related topics, including water conservancy object knowledge graphs, water conservancy engineering knowledge graphs, water supply knowledge graphs, drainage knowledge graphs, urban flooding knowledge graphs, rainfall knowledge graphs, water conservation knowledge graphs, and event knowledge graphs.

[0120] In an optional embodiment of the present invention, step 106 includes:

[0121] Step 1061: Obtain the geographical location of the target object;

[0122] Specifically, the geographical location of a target object can be obtained by receiving its real-time geographical location or the geographical location of its destination.

[0123] Step 1062: Determine the target water-related information grid to which the target location belongs based on the geographical location of the target object;

[0124] Specifically, based on the geographical location of the target object, the spatial grid cell to which the geographical location belongs can be found in the water-related information grid model, i.e., the target water-related information grid. It should be noted that the geographical location of the target object is within the range of the target water-related information grid.

[0125] Step 1063: Obtain the target topic knowledge graph corresponding to the target water-related information grid from the multiple topic knowledge graphs.

[0126] Specifically, there is a mapping relationship between the topic knowledge graph and each spatial grid unit in the water-related information grid model. That is, one spatial grid unit can map to at least one topic knowledge graph. Therefore, at least one corresponding topic knowledge graph, i.e., the target topic knowledge graph, can be determined through the target water-related information grid.

[0127] In an optional embodiment of the present invention, step 107 includes:

[0128] Multiple entities can be extracted from the target topic knowledge graph. Based on the entity and its corresponding attribute relationships, water-related knowledge data corresponding to the entity and its corresponding attribute relationships can be found from the water-related knowledge data corresponding to the water conservancy object model. This water-related data is then pushed to the target object's client wirelessly for the target object to view.

[0129] In this embodiment, the target topic knowledge graph and user location can be used to quickly determine the target water-related data to be pushed, thereby improving the efficiency of water-related data push.

[0130] A specific embodiment of the dynamic recommendation method based on LBS water-related information of the present invention includes:

[0131] Step 111: Obtain at least one water-related data item;

[0132] Based on the resource catalog shown in Table 1, the object class is parsed to obtain at least one water-related data item.

[0133] Step 112: Determine the water conservancy object model and the water conservancy theme model based on the at least one water-related data item;

[0134] Based on the attributes of the data items, the corresponding water conservancy object model is determined; based on the relationship between different data items, the sub-categories of the data items are determined, and then the major category to which the sub-categories belong is determined, i.e., the water conservancy theme model.

[0135] Step 113: Divide the preset area according to the smallest spatial grid unit of each water-related theme in the water conservancy theme model to obtain the water-related information grid model.

[0136] The minimum spatial grid unit is determined based on the preset grid unit division parameters corresponding to the water-related theme. By dividing the preset area, water-related information grid models for different water-related themes are obtained.

[0137] Step 114: Determine the water conservancy event model based on the water conservancy object model, the water conservancy theme model, and the water-related information grid model;

[0138] Based on the water-related information grid model, at least one target data item of the water conservancy object model corresponding to each water-related information grid can be determined; based on the water conservancy theme model, at least one target data item can be determined as the target water-related theme; water conservancy events occurring under the target water-related theme can be acquired in real time, such as urban rainstorms, exposure, water pollution and other water conservancy events, which constitute the water conservancy event model.

[0139] Step 115: Based on the water-related knowledge data in the water-related knowledge database corresponding to the water conservancy object model, the water conservancy theme model, the water-related information grid model, and the water conservancy event model, multiple theme knowledge graphs are formed.

[0140] By extracting entities from multiple models, and then merging and segmenting them according to the water-related theme, multiple topic knowledge graphs can be obtained.

[0141] like Figure 4 As shown, starting from the data base, knowledge base, and external data sources, a series of automatic or semi-automatic technical means can be used to extract water conservancy knowledge elements (i.e., data items) from the data sources and store them in the data layer and schema layer of the knowledge graph library, including knowledge modeling, knowledge extraction, knowledge fusion, knowledge processing, and knowledge storage.

[0142] Step 116: Based on the target water-related information grid to which the location of the target object belongs, obtain the target topic knowledge graph corresponding to the target water-related information grid from the multiple topic knowledge graphs;

[0143] The target water-related information grid to which the target object belongs is determined based on its location. Based on the entities and water-related topics involved in the target water-related information grid, the corresponding target topic knowledge graph can be determined.

[0144] Step 117: Obtain at least one type of target-push water-related data based on the target topic knowledge graph;

[0145] Based on the entities and relationships in the target topic knowledge graph, water-related knowledge data corresponding to the entity and its corresponding attribute relationships is retrieved from water-related knowledge data and used as target-pushed water-related data. Target-pushed water-related data may include: the water supply area, water supply company, service hotline, whether there is a planned water outage / low pressure supply; the nearest public drinking water point, public toilet, water bill payment point, repair point (distance, business hours, telephone number), etc.

[0146] Step 118: Push the target water-related data to the target object's client.

[0147] The target pushes water wading data to the target's client wirelessly for the target to view.

[0148] The LBS-based dynamic recommendation method for water-related information in this invention, based on grid division, can form an ordered knowledge network from a large amount of water-related information, and provide users with accurate and effective water conservancy information according to the location of the target object.

[0149] like Figure 5As shown, an embodiment of the present invention proposes a dynamic recommendation device 500 based on LBS water-related information, comprising:

[0150] Acquisition module 501 is used to acquire at least one water-related data item;

[0151] The processing module 502 is configured to: determine a water conservancy object model and a water conservancy theme model based on the at least one water-related data item; divide a preset area according to the smallest spatial grid unit of each water-related theme in the water conservancy theme model to obtain a water-related information grid model; determine a water conservancy event model based on the water conservancy object model, the water conservancy theme model, and the water-related information grid model; form multiple theme knowledge graphs based on the water-related knowledge data in the water-related knowledge database corresponding to the water conservancy object model, the water conservancy theme model, the water-related information grid model, and the water conservancy event model; obtain the target theme knowledge graph corresponding to the target water-related information grid from the multiple theme knowledge graphs based on the target water-related information grid to which the target object's location belongs; obtain at least one target-pushed water-related data based on the target theme knowledge graph; and push the target-pushed water-related data to the target object's client.

[0152] Optionally, at least one water-related data item may be acquired, including:

[0153] Obtain a resource catalog library containing preset water conservancy data;

[0154] The object class data of the resource catalog is parsed to obtain at least one water-related data item.

[0155] Optionally, based on the at least one water-related data item, a water conservancy object model and a water conservancy theme model are determined, including:

[0156] Based on the attributes of at least one water-related data item, determine the water conservancy object model;

[0157] Based on the relationship between different data items of the at least one water-related data item, subcategories of data items are determined, and water conservancy theme models are determined based on the major category to which the subcategories belong.

[0158] Optionally, the preset area is divided according to the smallest spatial grid unit of each water-related theme in the water conservancy theme model to obtain a water-related information grid model, including:

[0159] Obtain the grid cell partitioning parameters corresponding to each water-related theme in the water conservancy theme model;

[0160] According to the grid cell division parameters, determine the minimum spatial grid cell for each water-related theme;

[0161] The preset area is divided according to the smallest spatial grid unit of each water-related theme to obtain the water-related information grid model corresponding to each water-related theme.

[0162] Optionally, based on the water conservancy object model, the water conservancy theme model, and the water-related information grid model, a water conservancy event model is determined, including:

[0163] Based on the water-related information grid model, at least one target data item of the water conservancy object model corresponding to each water-related information grid is determined;

[0164] Based on the water conservancy theme model, determine the target water-related theme corresponding to at least one target data item;

[0165] Obtain water-related events related to the target water-related topic and determine the water-related event model.

[0166] Optionally, based on the water-related knowledge data in the water-related knowledge databases corresponding to the water conservancy object model, the water conservancy theme model, the water-related information grid model, and the water conservancy event model, multiple theme knowledge graphs are formed, including:

[0167] Knowledge extraction is performed on the water-related knowledge data corresponding to the water conservancy object model to obtain the first entity data;

[0168] Knowledge extraction is performed on the water-related knowledge data corresponding to the water-related information grid model to obtain the second entity data;

[0169] Knowledge extraction is performed on the water-related knowledge data corresponding to the water conservancy theme model to obtain third entity data;

[0170] Knowledge extraction is performed on the water-related knowledge data corresponding to the water conservancy event model to obtain the fourth entity data;

[0171] The first entity data, the second entity data, the third entity data, and the fourth entity data are fused together to obtain fused entity data.

[0172] Based on the fused entity data, multiple topic knowledge graphs are formed.

[0173] Optionally, based on the target water-related information grid to which the target object's location belongs, the target topic knowledge graph corresponding to the target water-related information grid is obtained from the plurality of topic knowledge graphs, including:

[0174] Obtain the geographical location of the target object;

[0175] Based on the geographical location of the target object, determine the target water-related information grid to which the geographical location belongs;

[0176] From the multiple topic knowledge graphs, obtain the target topic knowledge graph corresponding to the target water-related information grid.

[0177] The LBS-based dynamic recommendation device for water-related information in this invention acquires at least one water-related data item, determines a water conservancy object model and a water conservancy theme model, then divides a preset area according to the smallest spatial grid unit of each water-related theme in the water conservancy theme model to obtain a water-related information grid model, and then determines a water conservancy event model based on the water conservancy object model, the water conservancy theme model, and the water-related information grid model. Subsequently, based on the water-related knowledge data in the water-related knowledge database corresponding to the water conservancy object model, the water conservancy theme model, the water-related information grid model, and the water conservancy event model, multiple theme knowledge graphs are formed. Based on the target water-related information grid to which the target object's location belongs, the target theme knowledge graph corresponding to the target water-related information grid is obtained from the multiple theme knowledge graphs. Based on the target theme knowledge graph, at least one target-pushed water-related data is obtained and pushed to the target object's client. This device not only pushes water-related data to the target object based on its location, but also provides highly complete and relevant water-related data, improving the effectiveness and timeliness of water-related data delivery.

[0178] It should be noted that this device corresponds to the method described above, and all implementations in the method embodiments described above are applicable to the embodiments of this device and can achieve the same technical effect. Further details will not be provided in this embodiment.

[0179] This invention also provides a computing device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method as described in any of the above embodiments. All implementations in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effects. Further details are omitted in this embodiment.

[0180] This invention also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method as described in any of the above embodiments. All implementations in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effects. Further details are omitted in this embodiment.

[0181] It should be noted that in the apparatus and method of the present invention, the components or steps can obviously be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Furthermore, the steps for performing the above series of processes can naturally be performed in the order described and in chronological order, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel, overlapping, or independently of each other.

[0182] It should be noted that in the above embodiments, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments described above is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0183] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A dynamic recommendation method based on LBS (Location-Based Services) for water-related information, characterized in that, include: Obtain at least one water-related data item; Based on the at least one water-related data item, determine the water conservancy object model and the water conservancy theme model; The preset area is divided according to the smallest spatial grid unit of each water-related theme in the water conservancy theme model to obtain the water-related information grid model. Based on the water conservancy object model, the water conservancy theme model, and the water-related information grid model, determine the water conservancy event model; Based on the water-related knowledge data in the water-related knowledge databases corresponding to the water conservancy object model, the water conservancy theme model, the water-related information grid model, and the water conservancy event model, multiple theme knowledge graphs are formed. Based on the target water-related information grid to which the target object's location belongs, obtain the target topic knowledge graph corresponding to the target water-related information grid from the multiple topic knowledge graphs; Based on the target topic knowledge graph, at least one type of target-push water-related data is obtained; The target water-related data is pushed to the target client. Specifically, determining the water conservancy object model and the water conservancy theme model based on at least one water-related data item includes: Based on the attributes of at least one water-related data item, determine the water conservancy object model; Based on the relationship between different data items of the at least one water-related data item, determine the sub-category of the data item, and determine the water conservancy theme model based on the major category to which the sub-category belongs; Specifically, according to the smallest spatial grid unit of each water-related theme in the water conservancy theme model, the preset area is divided to obtain a water-related information grid model, including: Obtain the grid cell partitioning parameters corresponding to each water-related theme in the water conservancy theme model; According to the grid cell division parameters, determine the minimum spatial grid cell for each water-related theme; The preset area is divided according to the smallest spatial grid unit of each water-related theme to obtain the water-related information grid model corresponding to each water-related theme.

2. The dynamic recommendation method for water-related information based on LBS according to claim 1, characterized in that, Obtain at least one water-related data item, including: Resource catalog library for obtaining preset water conservancy data; The object class data of the resource catalog is parsed to obtain at least one water-related data item.

3. The dynamic recommendation method for water-related information based on LBS according to claim 1, characterized in that, Based on the aforementioned water conservancy object model, water conservancy theme model, and water-related information grid model, a water conservancy event model is determined, including: Based on the water-related information grid model, at least one target data item of the water conservancy object model corresponding to each water-related information grid is determined; Based on the water conservancy theme model, determine the target water-related theme corresponding to at least one target data item; Obtain water-related events related to the target water-related topic and determine the water-related event model.

4. The dynamic recommendation method for water-related information based on LBS according to claim 1, characterized in that, Based on the water-related knowledge data in the water-related knowledge databases corresponding to the water conservancy object model, the water conservancy theme model, the water-related information grid model, and the water conservancy event model, multiple theme knowledge graphs are formed, including: Knowledge extraction is performed on the water-related knowledge data corresponding to the water conservancy object model to obtain the first entity data; Knowledge extraction is performed on the water-related knowledge data corresponding to the water-related information grid model to obtain the second entity data; Knowledge extraction is performed on the water-related knowledge data corresponding to the water conservancy theme model to obtain third entity data; Knowledge extraction is performed on the water-related knowledge data corresponding to the water conservancy event model to obtain the fourth entity data; The first entity data, the second entity data, the third entity data, and the fourth entity data are fused together to obtain fused entity data. Based on the fused entity data, multiple topic knowledge graphs are formed.

5. The dynamic recommendation method for water-related information based on LBS according to claim 1, characterized in that, Based on the target water-related information grid to which the target object's location belongs, the target topic knowledge graph corresponding to the target water-related information grid is obtained from the multiple topic knowledge graphs, including: Obtain the geographical location of the target object; Based on the geographical location of the target object, determine the target water-related information grid to which the geographical location belongs; From the multiple topic knowledge graphs, obtain the target topic knowledge graph corresponding to the target water-related information grid.

6. A dynamic recommendation device based on LBS water-related information, characterized in that, include: The acquisition module is used to acquire at least one water-related data item; The processing module is used to determine a water conservancy object model and a water conservancy theme model based on the at least one water-related data item; divide a preset area according to the smallest spatial grid unit of each water-related theme in the water conservancy theme model to obtain a water-related information grid model; determine a water conservancy event model based on the water conservancy object model, the water conservancy theme model, and the water-related information grid model; and form multiple theme knowledge graphs based on the water-related knowledge data in the water-related knowledge database corresponding to the water conservancy object model, the water conservancy theme model, the water-related information grid model, and the water conservancy event model, respectively. Based on the target water-related information grid to which the target object's location belongs, obtain the target topic knowledge graph corresponding to the target water-related information grid from the multiple topic knowledge graphs; based on the target topic knowledge graph, obtain at least one target-push water-related data. The target water-related data is pushed to the target client. Specifically, determining the water conservancy object model and the water conservancy theme model based on at least one water-related data item includes: Based on the attributes of at least one water-related data item, determine the water conservancy object model; Based on the relationship between different data items of the at least one water-related data item, determine the sub-category of the data item, and determine the water conservancy theme model based on the major category to which the sub-category belongs; Specifically, according to the smallest spatial grid unit of each water-related theme in the water conservancy theme model, the preset area is divided to obtain a water-related information grid model, including: Obtain the grid cell partitioning parameters corresponding to each water-related theme in the water conservancy theme model; According to the grid cell division parameters, determine the minimum spatial grid cell for each water-related theme; The preset area is divided according to the smallest spatial grid unit of each water-related theme to obtain the water-related information grid model corresponding to each water-related theme.

7. A computing device, characterized in that, include: A processor, a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The system stores instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 5.

Images