Urban carbon metering method, prediction method and device based on mapping knowledge domain

Abstract

The invention provides an urban carbon metering method, prediction method and device based on a knowledge graph, which can be applied to the field of low-carbon treatment. The method comprises the steps that an initial knowledge graph of carbon activity content in a city is constructed for a city area, carbon activity attribute data and time attribute data of initial subject attribute nodes are acquired according to the initial knowledge graph, and the time attribute data correspond to time nodes; executing a carbon emission calculation task according to the carbon activity attribute data, the time attribute data and carbon emission calculation parameters related to the carbon activity nodes to obtain main carbon emission information; and according to the main carbon emission information, updating the initial carbon emission information node having the attribute relationship with the carbon activity node to obtain a target knowledge graph, and according to the target knowledge graph, obtaining an urban carbon metering result. The method can be used for recording, storage and relation analysis of urban carbon activity multi-dimensional mesh information, can realize a carbon emission prediction function of regions such as cities and the like, and realizes high-efficiency low-carbon treatment.

Description

Technical Field

[0001] The present disclosure relates to the field of low-carbon governance, and more specifically to a knowledge graph-based urban carbon measurement method, prediction method and device. Background Art

[0002] Urban carbon emissions are the main source of global carbon emissions. Studying the characteristics of communities and traffic attributes and their carbon emissions during urban operation is the key to revealing the mechanism of urban carbon emissions and achieving urban carbon reduction and control. The inventors found that the current low-carbon city governance is mainly limited to the total carbon emissions accounting and has a strong lag. It fails to integrate and associate the urban built environment and urban operation activity types and their relationships from the perspective of all factors such as the subject, form, time, and spatial location of urban carbon emission activities from the bottom up. It is difficult to finely characterize and trace the carbon activities of specific subjects, making it impossible to express the complex mapping relationship between carbon activities and urban spatial elements in multiple dimensions. Therefore, it is necessary to conduct refined intelligent modeling and analysis based on urban carbon emission data, and then reveal the mapping relationship and influencing mechanism between the urban built environment and carbon emissions. Summary of the invention

[0003] In view of the above problems, the present disclosure provides a city carbon measurement method, prediction method and device based on knowledge graph.

[0004] According to a first aspect of the present disclosure, a method for urban carbon measurement based on a knowledge graph is provided, comprising: for an urban area, constructing an initial knowledge graph of carbon activity content in the city, wherein the initial knowledge graph comprises an initial carbon emission subject subgraph, an initial activity information subgraph, an initial carbon emission subgraph and a time information subgraph, the initial carbon emission subject subgraph comprises a subject root node representing four types of carbon emission subjects, and an initial subject attribute node having an attribute relationship with the subject root node, the four types of carbon emission subjects comprise a plot information subject, a function information subject, a location information subject and a mobile information subject, the initial activity information subgraph comprises carbon activity nodes related to the carbon emission subjects, the time information subgraph comprises time nodes representing the time or period when the carbon activity occurs, and the initial carbon emission subgraph comprises The carbon emission nodes related to the activities, the main root nodes of each of the initial knowledge graph subgraphs have an attribute relationship, and the attribute relationship includes at least one of the following: contain, generate, be located in, be connected, time, and attribute; according to the initial knowledge graph, the carbon activity attribute data and time attribute data of the initial main attribute node are obtained, and the time attribute data corresponds to the time node; according to the carbon activity attribute data and time attribute data of the initial main attribute node, and the carbon emission calculation parameters related to the carbon activity node, the carbon emission calculation task is performed to obtain the main carbon emission information related to the initial main attribute node; according to the main carbon emission information, the initial carbon emission information node having an attribute relationship with the carbon activity node is updated to obtain the target knowledge graph; according to the target knowledge graph, the city carbon measurement result is obtained.

[0005] According to a second aspect of the present disclosure, a carbon emission prediction method based on a target knowledge graph is provided, comprising: determining a target knowledge graph related to the content of carbon activities in a city, the target knowledge graph comprising a carbon emission subject subgraph, an activity information subgraph, a carbon emission subgraph and a time information subgraph, the nodes of the time information subgraph represent time attribute data related to the carbon emission activities of the city, the nodes of the carbon emission subject subgraph comprise subject root nodes related to a plot information subject, a function information subject, a location information subject and a mobile information subject, and subject attribute nodes having an attribute relationship with the subject root nodes, the carbon emission subgraph The nodes represent the main carbon emission information related to the carbon emission subject, the nodes of the activity information subgraph represent the carbon activity attribute data related to the carbon emission subject, and the carbon emission subject is related to the time attribute data; determine the triples in the target knowledge graph, the triples include the target carbon emission subject node, the target carbon activity node and the target carbon emission information node with attribute relationship, the target carbon activity node represents the carbon activity attribute data of the carbon emission subject, and the target carbon emission information node represents the main carbon emission information of the carbon emission subject; input the graph structure corresponding to the triples into the prediction model, and output the carbon emission prediction results of the city.

[0006] The third aspect of the present disclosure provides an urban carbon metering device based on a knowledge graph, including: a construction module for constructing an initial knowledge graph of carbon activity content in the city for the urban area, wherein the initial knowledge graph includes an initial carbon emission subject subgraph, an initial activity information subgraph, an initial carbon emission subgraph and a time information subgraph, the initial carbon emission subject subgraph includes a subject root node representing four types of carbon emission subjects, and an initial subject attribute node having an attribute relationship with the subject root node, the four types of carbon emission subjects include a plot information subject, a function information subject, a location information subject and a mobile information subject, the initial activity information subgraph includes carbon activity nodes related to the carbon emission subjects, the time information subgraph includes a time node representing the time or period of the carbon activity, the initial carbon emission subgraph includes carbon emission amount nodes related to the carbon activity, and the initial knowledge graph subgraphs each have a subject root node and a function information subject. There is an attribute relationship between the body root nodes, and the attribute relationship includes at least one of the following: contain, generate, be located in, be connected, time, and attribute; an acquisition module is used to acquire the carbon activity attribute data and time attribute data of the initial subject attribute node according to the initial knowledge graph, and the time attribute data corresponds to the time node; a subject carbon emission information acquisition module is used to perform the carbon emission calculation task according to the carbon activity attribute data and time attribute data of the initial subject attribute node, and the carbon emission calculation parameters related to the carbon activity node, and obtain the subject carbon emission information related to the initial subject attribute node; and a target knowledge graph acquisition module is used to update the initial carbon emission information node having an attribute relationship with the carbon activity node according to the subject carbon emission information, and obtain the target knowledge graph; a city carbon measurement result acquisition module is used to obtain the city carbon measurement result according to the target knowledge graph.

[0007] The fourth aspect of the present disclosure provides a carbon emission prediction device based on a target knowledge graph, including: a processing module, which is used to determine a target knowledge graph related to the content of carbon activities in a city, the target knowledge graph includes a carbon emission subject subgraph, an activity information subgraph, a carbon emission subgraph and a time information subgraph, the nodes of the time information subgraph represent time attribute data related to urban carbon emission activities, the nodes of the carbon emission subject subgraph include subject root nodes related to a plot information subject, a function information subject, a location information subject and a mobile information subject, and subject attribute nodes having an attribute relationship with the subject root node, the nodes of the carbon emission subgraph represent the carbon emission The subject carbon emission information related to the subject, the nodes of the activity information subgraph represent the carbon activity attribute data related to the carbon emission subject, and the carbon emission subject is related to the time attribute data; the triple determination module is used to determine the triples in the target knowledge graph, the triples include the target carbon emission subject node, the target carbon activity node and the target carbon emission information node with attribute relationship, the target carbon activity node represents the carbon activity attribute data of the carbon emission subject, and the target carbon emission information node represents the subject carbon emission information of the carbon emission subject; the prediction result output module is used to input the graph structure corresponding to the triple into the prediction model and output the carbon emission prediction result of the city.

[0008] According to the embodiments of the present disclosure, for urban areas, an initial knowledge graph of carbon activity content in the city can be constructed. The initial knowledge graph may include an initial carbon emission subject subgraph, an initial activity information subgraph, an initial carbon emission subgraph and a time information subgraph. The initial carbon emission subject subgraph may include a subject root node representing four types of carbon emission subjects, and an initial subject attribute node having an attribute relationship with the subject root node. The four types of carbon emission subjects may include a plot information subject, a function information subject, a location information subject and a mobile information subject. The initial activity information subgraph may include a carbon activity node related to the carbon emission subject. The time information subgraph may include a time node representing the time or period when the carbon activity occurs. The initial carbon emission subgraph may include a carbon emission amount node related to the carbon activity. The subject root nodes of the initial knowledge graph subgraphs have an attribute relationship, and the attribute relationship may include at least one of the following: contain, generate, be located in, be connected, time, and attribute. According to the initial knowledge graph, the initial subject attribute node may be obtained. The carbon activity attribute data and time attribute data of the initial subject attribute node are obtained, and the time attribute data corresponds to the time node; the carbon emission calculation task is performed according to the carbon activity attribute data and time attribute data of the initial subject attribute node, and the carbon emission calculation parameters related to the carbon activity node, so as to obtain the subject carbon emission information related to the initial subject attribute node; the initial carbon emission information node having an attribute relationship with the carbon activity node is updated according to the subject carbon emission information, so as to obtain the target knowledge graph, and the urban carbon measurement result is obtained according to the target knowledge graph. The constructed target knowledge graph efficiently integrates the process information such as time, space, subject and so on related to the carbon activities in the city, and forms a multi-dimensional network knowledge structure through the mutual connection of relationships, and represents and stores various elements related to carbon activities in the form of a directed graph, which improves the accuracy and efficiency of automatic measurement of carbon emissions, realizes the comprehensive expression of the mapping relationship between carbon emissions and planning, contributes to the accurate traceability of carbon measurement results, and provides efficient support for carbon reduction and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0010] Figure 1 A flow chart of a method for measuring urban carbon based on a knowledge graph according to an embodiment of the present disclosure is shown;

[0011] Figure 2 A schematic diagram of a target knowledge graph according to an embodiment of the present disclosure is shown;

[0012] Figure 3 A flowchart of a carbon emission prediction method based on a target knowledge graph according to an embodiment of the present disclosure is shown;

[0013] Figure 4A structural block diagram of a city carbon metering device based on a knowledge graph according to an embodiment of the present disclosure is shown;

[0014] Figure 5 A structural block diagram of a carbon emission prediction device based on a target knowledge graph according to an embodiment of the present disclosure is shown; and

[0015] Figure 6 A block diagram of an electronic device suitable for implementing a knowledge graph-based urban carbon measurement method and prediction method according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0016] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0017] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0018] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0019] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0020] Urban carbon emissions are the main source of global carbon emissions. Studying the characteristics of communities and traffic attributes and their carbon emissions during urban operation is the key to revealing the mechanism of urban carbon emissions and achieving urban carbon reduction and control. The inventors found that the current low-carbon city governance is mainly limited to the total carbon emissions accounting and has a strong lag. It fails to integrate and associate the urban built environment and urban operation activity types and their relationships from the perspective of all factors such as the subject, form, time, and spatial location of urban carbon emission activities from the bottom up. It is difficult to finely characterize and trace the carbon activities of specific subjects, making it impossible to express the complex mapping relationship between carbon activities and urban spatial elements in multiple dimensions. Therefore, it is necessary to conduct refined intelligent modeling and analysis based on urban carbon emission data, and then reveal the mapping relationship and influencing mechanism between the urban built environment and carbon emissions.

[0021] In view of this, the present disclosure provides a method for urban carbon measurement based on a knowledge graph, including: for an urban area, constructing an initial knowledge graph of carbon activity content in the city, the initial knowledge graph including an initial carbon emission subject subgraph, an initial activity information subgraph, an initial carbon emission subgraph and a time information subgraph, the initial carbon emission subject subgraph including a subject root node representing four types of carbon emission subjects, and an initial subject attribute node having an attribute relationship with the subject root node, the four types of carbon emission subjects including a plot information subject, a function information subject, a location information subject and a mobile information subject, the initial activity information subgraph including carbon activity nodes related to the carbon emission subjects, the time information subgraph including time nodes representing the time or period of occurrence of carbon activities, the initial carbon emission subgraph including The carbon emission nodes of the initial knowledge graph subgraphs have an attribute relationship between the main root nodes, and the attribute relationship includes at least one of the following: contain, generate, be located in, be connected, time, and attribute; according to the initial knowledge graph, the carbon activity attribute data and time attribute data of the initial main attribute node are obtained, and the time attribute data corresponds to the time node; according to the carbon activity attribute data and time attribute data of the initial main attribute node, and the carbon emission calculation parameters related to the carbon activity node, the carbon emission calculation task is performed to obtain the main carbon emission information related to the initial main attribute node; according to the main carbon emission information, the initial carbon emission information node having an attribute relationship with the carbon activity node is updated to obtain the target knowledge graph, and according to the target knowledge graph, the city carbon measurement result is obtained.

[0022] In the technical solution of the present disclosure, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0023] Figure 1 A flow chart of a city carbon measurement method based on a knowledge graph according to an embodiment of the present disclosure is shown.

[0024] like Figure 1 As shown, the urban carbon measurement method based on the knowledge graph of this embodiment includes operations S110 to S150.

[0025] In operation S110, for an urban area, an initial knowledge graph of carbon activity content within the city is constructed.

[0026] In operation S120, carbon activity attribute data and time attribute data of the initial subject attribute node are obtained according to the initial knowledge graph, and the time attribute data corresponds to the time node.

[0027] In operation S130, a carbon emission calculation task is performed according to the carbon activity attribute data and time attribute data of the initial subject attribute node and the carbon emission calculation parameters related to the carbon activity node to obtain subject carbon emission information related to the initial subject attribute node.

[0028] In operation S140, the initial carbon emission information node having an attribute relationship with the carbon activity node is updated according to the subject carbon emission information to obtain a target knowledge graph.

[0029] In operation S150, a city carbon measurement result is obtained according to the target knowledge graph.

[0030] According to an embodiment of the present disclosure, the initial knowledge graph may include an initial carbon emission subject subgraph, an initial activity information subgraph, an initial carbon emission subgraph, and a time information subgraph. The initial carbon emission subject subgraph may include a subject root node representing four types of carbon emission subjects, and an initial subject attribute node having an attribute relationship with the subject root node. For example, the subject root node is a plot node representing the plot information subject, and the initial subject attribute node may include a plot ratio node, a number of people node, etc. The initial subject attribute node may be a leaf node in the initial carbon emission subject subgraph except the subject root node.

[0031] According to the embodiments of the present disclosure, the four types of carbon emission subjects may include a plot information subject, a function information subject, a location information subject, and a mobile information subject, but are not limited thereto, and the present disclosure does not limit this. The initial activity information subgraph may include carbon activity nodes related to the carbon emission subject, and the carbon activity nodes may include waste treatment nodes, industrial process nodes, land use nodes, energy activity nodes, etc., but are not limited thereto, and the embodiments of the present disclosure do not limit this. The time information subgraph may include time nodes that characterize the time or time period when the carbon activity occurs, and the time nodes may include year nodes, month nodes, day nodes, etc., but are not limited thereto, and the embodiments of the present disclosure do not limit this. The initial carbon emission subgraph may include carbon emission nodes related to carbon activities.

[0032] Optionally, the nodes in the initial knowledge graph are not filled with specific data. The nodes in the initial knowledge graph include data parameters that need to be obtained, such as "area parameter", "window-to-wall ratio parameter", etc. There is an attribute relationship between the main root nodes of each subgraph of the initial knowledge graph. The attribute relationship includes at least one of the following: include, generate, located in, connected, time, attribute, but is not limited to this. The embodiments of the present disclosure do not specifically limit the attribute relationship.

[0033] Optionally, according to the initial knowledge graph, the carbon activity attribute data and time attribute data of the initial subject attribute node can be obtained, and the time attribute data corresponds to the time node. Specifically, the carbon activity attribute data may include specific parameters, such as room parameters, building parameters, vehicle parameters, travel parameters, road parameters, etc. Travel parameters may include travel time, driving speed, etc. Road parameters may include road length, road grade, etc. Here, the carbon activity attribute data are not listed one by one.

[0034] Optionally, the carbon emission calculation task can be performed according to the carbon activity attribute data and time attribute data of the initial subject attribute node and the carbon emission calculation parameters related to the carbon activity node to obtain the subject carbon emission information related to the initial subject attribute node. The subject carbon emission information is, for example, the carbon emission information of each vehicle, the carbon emission information of each room, and the like.

[0035] According to the embodiments of the present disclosure, to obtain carbon activity attribute data, it is necessary to clean the original data obtained at the beginning, remove noise and outliers. The present disclosure adopts the bottom-up carbon emission accounting method proposed by the authoritative report, that is, the carbon emission factor method (carbon emission calculation parameters) to carry out accounting, as shown in Table 1. Taking travel as an example, the carbon emission information of the travel subject related to the travel carbon emission node can be equal to the travel distance of the vehicle multiplied by the carbon emission factor per unit distance.

[0036] Table 1 Carbon emission measurement formula

[0037]

[0038] According to an embodiment of the present disclosure, a target knowledge graph can be obtained by updating an initial carbon emission information node having an attribute relationship with a carbon activity node based on the subject carbon emission information, and a city carbon metering result can be calculated based on the obtained target knowledge graph. The city carbon metering result can represent the result after measuring and counting the city's carbon emissions.

[0039] It should be noted that the carbon metering involved in the embodiments of the present disclosure can be understood as carbon emission metering. For example, carbon metering can include carbon emission information such as carbon emission in a preset time period, and the embodiments of the present disclosure will not be described in detail here.

[0040] According to the embodiments of the present disclosure, for urban areas, an initial knowledge graph of carbon activity content in the city can be constructed. The initial knowledge graph may include an initial carbon emission subject subgraph, an initial activity information subgraph, an initial carbon emission subgraph and a time information subgraph. The initial carbon emission subject subgraph may include a subject root node representing four types of carbon emission subjects, and an initial subject attribute node having an attribute relationship with the subject root node. The four types of carbon emission subjects may include a plot information subject, a function information subject, a location information subject and a mobile information subject. The initial activity information subgraph may include a carbon activity node related to the carbon emission subject. The time information subgraph may include a time node representing the time or period when the carbon activity occurs. The initial carbon emission subgraph may include a carbon emission amount node related to the carbon activity. The subject root nodes of the initial knowledge graph subgraphs have an attribute relationship, and the attribute relationship may include at least one of the following: contain, generate, be located in, be connected, time, and attribute. According to the initial knowledge graph, the initial subject attribute node may be obtained. The carbon activity attribute data and time attribute data of the initial subject attribute node are obtained, and the time attribute data corresponds to the time node; the carbon emission calculation task is performed according to the carbon activity attribute data and time attribute data of the initial subject attribute node, and the carbon emission calculation parameters related to the carbon activity node, so as to obtain the subject carbon emission information related to the initial subject attribute node; the initial carbon emission information node having an attribute relationship with the carbon activity node is updated according to the subject carbon emission information, so as to obtain the target knowledge graph, and the urban carbon measurement result is obtained according to the target knowledge graph. The constructed target knowledge graph efficiently integrates the process information such as time, space, subject and so on related to the carbon activities in the city, and forms a multi-dimensional network knowledge structure through the mutual connection of relationships, and represents and stores various elements related to carbon activities in the form of a directed graph, which improves the accuracy and efficiency of automatic measurement of carbon emissions, realizes the comprehensive expression of the mapping relationship between carbon emissions and planning, contributes to the accurate traceability of carbon measurement results, and provides efficient support for carbon reduction and control.

[0041] According to an embodiment of the present disclosure, the carbon emission subject subgraph of the target knowledge graph includes a plot information subgraph, a function information subgraph, a location information subgraph and a mobile information subgraph; the main root node of the plot information subgraph is a plot node representing the main body of the plot information, and the main attribute nodes of the plot information subgraph include plot attribute nodes having an attribute relationship with the plot nodes, and the plot attribute nodes include at least one of the following: an area node, a number of people node, a floor area ratio node, a building height node, and a building density node, wherein the plot node has a generation relationship with the carbon activity node in the activity information subgraph.

[0042] For the plot information sub-graph, different plot characteristics will also affect the carbon emissions of the city. Different plot characteristics will directly affect the carbon emissions of the city. Therefore, the plot factors can be selected from area, number of people, volume ratio, number of people, building height, building density, etc., but are not limited to this. The present disclosure does not limit the plot factors. The calculation method of the relevant attributes of the plot factors, building factors, etc. is shown in Table 2.

[0043] Table 2 Parameter calculation method

[0044]

[0045] According to an embodiment of the present disclosure, a mobile information subgraph may include a travel node representing a mobile information subject, the subject attribute node of the mobile information subgraph may include a vehicle node having a generation relationship with the travel node, and the vehicle attribute node having an attribute relationship with the vehicle node may include at least one of the following: a fuel type node, a type node, and a displacement node; the travel node and the plot node may have an inclusion relationship, the travel node and the time node in the time subgraph may have a time relationship, and the vehicle node and the energy activity node in the activity information subgraph may have a generation relationship.

[0046] According to the embodiments of the present disclosure, the mobile information subgraph may include travel nodes, and vehicle nodes that have a generation relationship with the travel nodes. The difference in the technical parameters of the vehicle itself is closely related to the total amount and intensity of traffic carbon emissions. Therefore, in order to explore the correlation between different technical parameters of the vehicle and its carbon activities, and also to further study the relationship between these technical data and the driving and carbon emissions of the vehicle, the vehicle attribute node may include at least one of the following: fuel type node, emission standard node, vehicle age node, vehicle total mass node, etc., but not limited to this, and the embodiments of the present disclosure do not limit this. Secondly, the travel activities of the vehicle are also the root cause of carbon emissions. The travel attribute nodes that have an attribute relationship with the travel nodes in the present disclosure may include at least one of the following: driving speed node, passing section node and travel time node, but not limited to this, and the embodiments of the present disclosure do not limit this.

[0047] According to an embodiment of the present disclosure, the functional information subgraph includes a land use type node representing the functional information subject, and the type attribute node having an attribute relationship with the land use type node includes at least one of the following: an industrial land node, a warehousing land node, a green space node, a transportation land node, a commercial and service land node, a public service land node and a residential land node; the land use type node has an attribute relationship with the plot node.

[0048] For the functional information subgraph, the land use type nodes in the functional information subgraph have an attribute relationship with the plot nodes in the plot information subgraph. The type attributes of the plot land will also affect the city's carbon emissions. The type attribute nodes can also include industrial land nodes, warehousing land nodes, green space nodes, transportation land nodes, commercial and service land nodes, public service land nodes and residential land nodes, etc., but are not limited to this. The present disclosure does not specifically limit the attributes of the land use type.

[0049] According to an embodiment of the present disclosure, a location information subgraph may include a road segment node representing a main body of location information, and nodes having a location relationship with the road segment node may include at least one of the following: an administrative district node and a road node, and road segment attribute nodes having an attribute relationship with the road segment node may include at least one of the following: a road segment length node, a road segment level node, and a road segment width node; administrative district attribute nodes having a containment relationship with the administrative district node may include at least one of the following: a district node and a street node; road attribute nodes having an attribute relationship with the road node may include a road name node; nodes having a connection relationship with the road segment node may include an intersection node, and intersection attribute nodes having an attribute relationship with the intersection node may include at least one of the following: a longitude node and a latitude node; road segment nodes may have a location relationship with travel nodes, and road segment nodes and plot nodes may have an adjacent relationship.

[0050] According to an embodiment of the present disclosure, the target knowledge graph may also include a location information subgraph, the main root node of the location information subgraph is a road segment node, and a road segment attribute node having an attribute relationship with the road segment node, and the road segment attribute node includes at least one of the following: a road segment length node, a road segment level node, and a road segment width node.

[0051] According to an embodiment of the present disclosure, the administrative district attribute node having a containment relationship with the administrative district node may include at least one of the following: a district node and a street node, but is not limited thereto, and the embodiment of the present disclosure does not limit this. The road attribute node having an attribute relationship with the road node may include a road name node, the node having a connection relationship with the road section node may include an intersection node, and the intersection attribute node having an attribute relationship with the intersection node may include at least one of the following: a longitude node and a latitude node, the road section node and the travel node may have a location relationship, and the road section node and the plot node may have an adjacent relationship.

[0052] According to an embodiment of the present disclosure, the carbon activity node of the activity information subgraph may include at least one of the following: a waste treatment node, a land use node, an industrial process node and an energy activity node, and the energy activity node may include at least one of the following: a gas consumption node, a water consumption node, a fuel consumption node and an electricity consumption node; the carbon emission subgraph may include carbon emission nodes related to carbon activities, the carbon emission nodes and the carbon activity nodes may have an inclusion relationship, and the carbon emission nodes and the time nodes may have a time relationship; the time subgraph may include multiple time nodes representing different carbon activity attributes, and the time attribute data related to the carbon emission activities is stored in the data layer of the time nodes.

[0053] For the activity information subgraph, the land parcel nodes in the land parcel information subgraph have a production relationship with the carbon activity nodes in the activity information subgraph. The relevant operations on the land parcels will generate relevant carbon activities, such as waste treatment, land use, and industrial processes, etc. At the same time, the relevant operations on the land parcels will also generate relevant energy activities, and energy activities will bring corresponding carbon emissions, such as gas consumption, fuel consumption, electricity consumption, and water consumption, etc. These energy consumptions will directly or indirectly affect the city's carbon emissions.

[0054] For the time information subgraph, the relevant carbon emissions will be emitted in a certain period of time, and the carbon emissions can be determined according to the specific time of the specific event. The time nodes in the time information subgraph may include time attribute nodes, such as year nodes, month nodes, day nodes, moment nodes, and event nodes, etc., but are not limited to this, and the embodiments of the present disclosure are not limited to this.

[0055] Figure 2 A schematic diagram of a target knowledge graph according to an embodiment of the present disclosure is shown.

[0056] like Figure 2 As shown, the target knowledge graph of this embodiment includes a plot information subgraph 210 , a function information subgraph 220 , an activity information subgraph 230 , a time information subgraph 240 , a movement information subgraph 250 , a location information subgraph 260 and a carbon emission subgraph 270 .

[0057] According to an embodiment of the present disclosure, the plot information subgraph 210 may include plot nodes, and the plot attribute nodes having attribute relationships with the plot nodes may represent the plot-related data of the urban area, for example, area nodes, number of people nodes, floor area ratio nodes, building height nodes, building density nodes, etc. The plot attribute nodes also have corresponding attribute values.

[0058] According to an embodiment of the present disclosure, the function information subgraph 220 may include a land type node, wherein the type attribute nodes related to the land type node include an industrial land node, a storage land node, a green land node, a transportation land node, a commercial service land node, a public service land node, and a residential land node, and the type attribute nodes related to the land type node also have corresponding attribute values. In addition, the land type node and the plot node have an attribute relationship.

[0059] According to an embodiment of the present disclosure, the activity information subgraph 230 may include a carbon activity node, and the carbon activity attribute nodes having a containment relationship with the carbon activity node may include a waste treatment node, a land use node, an industrial process node, and an energy activity node. The energy consumption nodes having a containment relationship with the energy activity node may include a gas consumption node, a fuel consumption node, an electricity consumption node, and a water consumption node. The energy consumption node carbon activity attribute nodes all have corresponding attribute values, and have a generation relationship with the carbon activity node and the plot node.

[0060] According to an embodiment of the present disclosure, the time information subgraph 240 may include time nodes. Time attribute nodes connected to the time nodes may represent the time data of carbon emissions related to the urban area, such as year nodes, month nodes, day nodes, moment nodes and event nodes.

[0061] According to an embodiment of the present disclosure, the mobile information subgraph 250 may include a travel node, a vehicle node having a generation relationship with the travel node, and a vehicle attribute node having an attribute relationship with the vehicle node. The vehicle attribute node connected to the vehicle node may represent relevant attribute information related to the vehicle. The vehicle attribute node may include a fuel type node, a type node, and a displacement node, and the vehicle attribute node has a corresponding attribute value. The travel node has a containment relationship with the plot node, and the travel node has a located relationship with the road section node.

[0062] According to an embodiment of the present disclosure, the location information subgraph 260 may include a road segment node representing the main body of the location information, and the nodes having a location relationship with the road segment node include at least one of the following: an administrative district node and a road node, and the road segment attribute nodes having an attribute relationship with the road segment node include at least one of the following: a road segment length node, a road segment level node, and a road segment width node; the administrative district attribute nodes having a containment relationship with the administrative district node may include at least one of the following: a district node and a street node; the road attribute nodes having an attribute relationship with the road node may include a road name node; the nodes having a connection relationship with the road segment node may include an intersection node, and the intersection attribute nodes having an attribute relationship with the intersection node may include at least one of the following: a longitude node and a latitude node; the road segment node may have a location relationship with the travel node, and the road segment node and the plot node may have an adjacent relationship.

[0063] According to an embodiment of the present disclosure, the carbon emission subgraph 270 includes carbon emission nodes, which have a time relationship with the time nodes in the time information subgraph 240. The carbon emission nodes in the carbon emission subgraph can represent a series of carbon emissions generated by relevant activities in the urban area.

[0064] Figure 3 A flowchart of a carbon emission prediction method based on a target knowledge graph according to an embodiment of the present disclosure is shown.

[0065] like Figure 3 As shown, the carbon emission prediction method based on the target knowledge graph of this embodiment includes operations S310 to S330.

[0066] In operation S310 , a target knowledge graph related to carbon activity content within a city is determined.

[0067] In operation S320, triples in the target knowledge graph are determined.

[0068] In operation S330, the graph structure corresponding to the triple is input into the prediction model, and the carbon emission prediction result of the city is output.

[0069] According to an embodiment of the present disclosure, the target knowledge graph may include a carbon emission subject subgraph, an activity information subgraph, a carbon emission subgraph and a time information subgraph. The nodes of the time information subgraph may represent time attribute data related to urban carbon emission activities. The nodes of the carbon emission subject subgraph may include subject root nodes related to plot information subjects, function information subjects, location information subjects and mobile information subjects, and subject attribute nodes having attribute relationships with the subject root nodes. The nodes of the carbon emission subgraph may represent subject carbon emission information related to carbon emission subjects. The nodes of the activity information subgraph may represent carbon activity attribute data related to carbon emission subjects. Carbon emission subjects are related to time attribute data.

[0070] According to the embodiment of the present disclosure, taking a certain urban area as an example, the relevant data of the urban area can be collected from authoritative statistical departments, energy companies, utility companies, scientific research institutions, etc., and the collected data mainly include various data related to urban communities and vehicle travel trajectories in a certain urban area, including but not limited to urban community resource consumption data and data reflecting the material environment and social and economic characteristics of the community, which can include building outline data, land use data, point of interest data (POI), vehicle travel trajectory data, social and economic data, climate data, etc. As shown in Table 3.

[0071] Table 3 Data list

[0072]

[0073] According to the embodiments of the present disclosure, the target knowledge graph is based on the characterization of urban communities and the mechanism of carbon emissions from travel, and the construction of the target knowledge graph may include the construction of a model layer and a data layer. In terms of the model layer, the present disclosure completes the construction of the model layer of the urban target knowledge graph from top to bottom based on expert experience, that is, starting from a high-level abstract concept or domain knowledge, gradually refining and expanding the construction of the knowledge graph model layer, and determining the reasonable abstract level and relationship structure of the entity based on domain experts. The constructed model layer may include six categories, namely, a plot information subgraph, a function information subgraph, a mobile information subgraph, an activity information subgraph, a time information subgraph, and a location information subgraph. These six subgraphs also include two structures, "entity-relationship-entity" and "entity-attribute-attribute value", and define the ontology and its attribute characteristics and the attribute relationship between entities in these six subgraphs. Attribute relationships may include inclusion, generation, location, connection, time, attributes, etc., but are not limited to this, and the embodiments of the present disclosure do not specifically limit this. Among them, the attribute characteristics of different types of ontologies are defined for six types of subgraphs, namely, plot information subgraph, function information subgraph, movement information subgraph, activity information subgraph, time information subgraph, and location information subgraph, as shown in Table 4.

[0074] Table 4 Target knowledge graph ontology and its description

[0075]

[0076] According to the embodiment of the present disclosure, the construction of the data layer of the city target knowledge graph is carried out under the guidance of the model layer. The data layer uses fact triples as units to save specific data information, where each entity in the triple has its own attributes and attribute values. Table 5 shows the structure of the target knowledge graph.

[0077] Table 5 Knowledge graph structure

[0078]

[0079] According to the embodiment of the present disclosure, a graph database reflecting the attribute characteristic index system of the ontology can be extracted to construct the graph database of urban communities and travel carbon emissions, wherein the graph database includes graph data of the community and its attribute information, graph data of community building information, image data of community resident information, graph data of urban climate information, graph data of attribute information of vehicles and their travel trajectories, and graph data of urban carbon emissions. After collecting the relevant data of the urban area, it is necessary to clean the data, remove noise and outliers, and standardize the data to ensure that data from different sources are comparable. Then, the construction of the target knowledge graph is completed through knowledge extraction and knowledge fusion. The present disclosure can carry out knowledge extraction based on structured data, that is, structured tabular data has clear field definitions, and relationship extraction is realized through mapping fields and entities and connecting tables, so that the relevant entity names, attribute information, and attribute relationships (that is, edge relationships between nodes) can be obtained from the database. Among them, attribute relationship extraction is the key to linking various entities together to form rich knowledge. The second is knowledge fusion, that is, different types of heterogeneous data after knowledge extraction are integrated under a unified model framework, as shown in Table 6. Through manual proofreading, the extracted data units are merged into similar items, ambiguous, and unified, including entity alignment, relationship alignment, and attribute alignment. A graph database can be used to store the target knowledge graph.

[0080] Table 6 Comparison before and after knowledge fusion

[0081]

[0082] According to an embodiment of the present disclosure, the target knowledge graph may include a plot information subgraph, a function information subgraph, an activity information subgraph and a time information subgraph. The plot nodes in the plot information subgraph and the land use type nodes in the function information subgraph have an attribute relationship. The plot nodes in the plot information subgraph and the carbon activity nodes in the activity information subgraph have a generation relationship. The nodes of the time information subgraph represent time attribute data related to urban carbon emission activities. The nodes of the plot information subgraph represent the plot attribute data of the city. The nodes of the function information subgraph represent the land use type attribute data of the city. The nodes of the activity information subgraph represent carbon activity attribute data related to carbon emission subjects. The carbon emission subjects are related to the time attribute data.

[0083] According to an embodiment of the present disclosure, a triple in a target knowledge graph may be determined. The triple may include a target carbon emission subject node, a target carbon activity node, and a target carbon emission information node having an attribute relationship, wherein the target carbon activity node may represent the carbon activity attribute data of the carbon emission subject, and the target carbon emission information node may represent the subject carbon emission information of the carbon emission subject.

[0084] According to the embodiments of the present disclosure, entity relationship extraction can be used to extract nodes from the target knowledge graph. A triple is an ordered set of three elements, and its structure is clear and concise, which can fully reflect the entities and relationships and the semantic associations between them. For example, community-located-street, vehicle-generated-travel trajectory, community-characteristic parameter-floor area ratio value, etc.

[0085] According to an embodiment of the present disclosure, a graph structure corresponding to a triple is input into a prediction model to output a prediction result of urban carbon emissions. Each triple can be converted into a graph structure, in which a node is an entity, an edge is a relationship, the node data includes an entity serial number identifier, an entity type, etc., and the edge data includes an entity relationship type, etc.

[0086] According to the embodiments of the present disclosure, the present disclosure associates multiple sets of relationships such as the time when carbon emission activities occur and the specific form of spatial activities in the form of triples. Embedding multiple triples in the knowledge graph forms a complete database of carbon emission measurement records. In the constructed target knowledge graph, the space, time and subject can be traced through the target knowledge graph, which is a bottom-up method. The triples obtained by tracing can effectively analyze the causes of carbon emissions and provide new ideas for carbon reduction and control.

[0087] According to an embodiment of the present disclosure, a target knowledge graph related to the content of carbon activities in a city can be determined. The target knowledge graph may include a carbon emission subject subgraph, an activity information subgraph, a carbon emission subgraph, and a time information subgraph. The nodes of the time information subgraph may represent time attribute data related to the city's carbon emission activities. The nodes of the carbon emission subject subgraph may include subject root nodes related to a plot information subject, a function information subject, a location information subject, and a mobile information subject, as well as subject attribute nodes having an attribute relationship with the subject root nodes. The nodes of the carbon emission subgraph may represent subject carbon emission information related to the carbon emission subject. The nodes of the activity information subgraph may represent carbon activity attribute data related to the carbon emission subject. The carbon emission subject is related to the time attribute data. Triples in the target knowledge graph may be determined. The triples may include a target carbon emission subject node, a target carbon activity node, and a target carbon emission information node having an attribute relationship. The target carbon activity node may represent carbon The carbon activity attribute data of the emission subject, the target carbon emission information node can represent the main carbon emission information of the carbon emission subject; the graph structure corresponding to the triplet is input into the prediction model to output the carbon emission prediction result of the city, and the entity-relationship-entity triplet is defined at the micro level, which improves the accuracy of the automatic measurement and evaluation of urban carbon emissions, and provides decision support for the management of urban carbon activities. By combining the target knowledge graph with the carbon emission related data of the urban area, the inherent correlation of multidimensional data is demonstrated, and the accuracy of urban carbon emission prediction is improved. Data is aggregated from aspects such as carbon emission time, space and cause, which improves the accuracy and professionalism of the matching between the target knowledge graph and the urban carbon emission prediction model, and solves the problems of high data cost, complex knowledge construction and difficult to guarantee prediction effect in urban carbon control planning, and improves the matching degree between the output content and the actual results, so as to effectively capture the useful information in the target knowledge graph for carbon emission prediction.

[0088] According to an embodiment of the present disclosure, the time attribute data includes multiple, the multiple time attribute data are arranged in time series, the multiple time attribute data correspond one-to-one to the multiple target knowledge graphs, and the prediction model includes a graph neural network and a time series network; the graph structure corresponding to the triple is input into the prediction model, and the carbon emission prediction result of the city is output, including: inputting the graph structure corresponding to the time attribute data into the graph neural network, and outputting a graph embedding feature matrix, wherein there is a time series relationship between the multiple graph embedding feature matrices, and the time series relationship is determined based on the time attribute data corresponding to each of the multiple graph structures; inputting multiple graph embedding feature matrices with a time series relationship into the time series network, and outputting the carbon emission prediction result of the city.

[0089] According to an embodiment of the present disclosure, the time attribute data may include multiple, and the multiple time attribute data are arranged in time sequence. The multiple time attribute data may correspond one-to-one to multiple target knowledge graphs, and the prediction model may include a graph neural network and a time series network.

[0090] According to the embodiments of the present disclosure, in a static knowledge graph stored corresponding to a certain time attribute data, the node and relationship definitions are fixed. The target knowledge graph adds a time series on the basis of the static knowledge graph, and expands the static triples into a set of quadruples containing the time dimension, that is, in the time attribute data, The target knowledge graph (UCEKG) is a multi-relational directed label graph, which can be expressed as UCEKG= ,in, , E represents the set of vertices (entities) in the knowledge graph; R represents the set of edges (relationships) in the knowledge graph; Indicates on date The set of facts that exist, namely When there is a node , ∈E, ∈R exists .

[0091] According to an embodiment of the present disclosure, a graph structure corresponding to time attribute data can be input into a graph neural network to output a graph embedding feature matrix. Multiple graph embedding feature matrices have a temporal relationship. The temporal relationship can be determined based on the time attribute data corresponding to each of the multiple graph structures. Multiple graph embedding feature matrices with a temporal relationship can be input into a time series network to output a carbon emission prediction result of a city.

[0092] According to an embodiment of the present disclosure, the time series network may include a long short-term memory network, but is not limited thereto. The embodiment of the present disclosure does not limit the time series network.

[0093] According to an embodiment of the present disclosure, by associating multiple time attribute data with multiple target knowledge graphs, the carbon emissions of a city can be viewed from the timeline. And a fact set is set in the knowledge graph. For example, if there is no use of transportation on a certain day, there is no fact set between the transportation node and the vehicle node. The next stage can be predicted based on the facts existing in the time attribute data to improve the accuracy of the prediction. By using the method provided by the present disclosure, the predicted carbon emissions can be made more accurate. For example, if a certain day is the first day of school, there are many transportation tools used for travel, and the carbon emissions are relatively large. If the carbon emissions of the day are used to predict the carbon emissions of the next day, the predicted results may differ greatly from the actual results. However, if multiple target knowledge graphs of a certain time attribute data are used to predict the carbon emissions of a certain day, the matching results of the output content and the actual results can be greatly improved, and the useful information in the target knowledge graph can be effectively captured for carbon emission prediction.

[0094] According to an embodiment of the present disclosure, a graph neural network includes an input layer, a graph convolution layer, and an output layer, and a graph structure corresponding to the time attribute data is input into the graph convolution neural network, and a graph embedding feature matrix is ​​output. Specifically, the graph structure corresponding to the time attribute data can be processed based on the input layer to obtain a node feature matrix related to the node and an adjacency matrix representing the connection relationship between nodes in the graph structure; the node feature matrix and the adjacency matrix are input into the graph convolution layer for feature aggregation to obtain a spatial feature matrix; the spatial feature matrix is ​​processed based on the output layer to obtain a graph embedding feature matrix.

[0095] According to an embodiment of the present disclosure, a graph neural network may include an input layer, a graph convolution layer, and an output layer. Based on the input layer, the graph structure corresponding to the time attribute data may be processed to obtain a node feature matrix related to the node and an adjacency matrix representing the connection relationship between nodes in the graph structure.

[0096] According to an embodiment of the present disclosure, the node feature matrix and the adjacency matrix can be input into the graph convolution layer for feature aggregation to obtain a spatial feature matrix. The spatial feature matrix can be processed based on the output layer to obtain a graph embedding feature matrix.

[0097] According to an embodiment of the present disclosure, the features of the neighboring nodes of each node can be aggregated by feature aggregation, that is, multiplication of the node feature matrix and the adjacency matrix, so that the input features can be converted into 16-dimensional features. Feature conversion is then used, that is, the aggregated spatial feature matrix is ​​processed through an activation function to generate a new node representation, that is, a graph embedding feature matrix, to convert the 16-dimensional features into the same number of features as the number of categories in the data set.

[0098] According to an embodiment of the present disclosure, the aggregated feature matrix is ​​processed through a linear layer and an activation function. The linear layer is usually a weight matrix used to map features from the input dimension to the hidden layer dimension. The activation function is used to introduce nonlinearity so that the network can learn more complex features. The output of the previous layer is used as the input of the next layer, and the steps of neighbor aggregation and feature conversion are repeated.

[0099] According to an embodiment of the present disclosure, the training process of the prediction model may include defining an optimizer and a loss function, clearing previous gradients, forward propagation, calculating the loss on the training set, back propagation, and optimization. The evaluation process of the prediction model may include setting the model to evaluation mode, disabling gradient calculation, forward propagation, and calculating performance indicators on the test set. The acquired data set may be divided into a training set and a test set, and then the optimizer may be used to adjust the model parameters to minimize the loss, and a context manager may be used to disable gradient calculation when evaluating the model to save memory and computing resources, and finally, a loss function may be used at the output layer to measure the difference between the predicted value and the actual value.

[0100] According to the embodiments of the present disclosure, model evaluation and optimization can use methods such as cross-validation to evaluate the model to ensure the generalization ability of the model. The model is optimized and adjusted according to the evaluation results, and the mean square error (MSE) loss function is used to calculate the average of the square of the error between the predicted value and the actual value of each sample, thereby measuring the prediction performance of the model and improving the prediction accuracy and stability. The MSE loss function is shown in formula (1).

[0101] #timg# （1）

[0102] According to the embodiments of the present disclosure, the target knowledge graph constructed for the measurement and regulation of carbon emissions in cities has a more detailed study on the intrinsic correlation between multidimensional data, and defines entity-relationship-entity triples from a micro level, which improves the accuracy of the city's automatic measurement and evaluation of carbon emissions, and provides decision support for the management of the city's carbon activities. The constructed structured triples realize the unified expression of multimodal data knowledge and the visual display of interrelationships, collect data from aspects such as carbon emission time, space, and causes, improve the accuracy and professionalism of the match between the target knowledge graph and the carbon emission prediction model, and solve the problems of high data cost, complex knowledge construction, and difficult to guarantee prediction effect in carbon control planning. The provided carbon emission prediction method is easy to expand and optimize, can improve the matching degree between the output content and the actual results, and can effectively capture useful information in the target knowledge graph for carbon emission prediction.

[0103] Based on the above-mentioned urban carbon measurement method based on knowledge graph, the present disclosure also provides an urban carbon measurement device based on knowledge graph. Figure 4 The device is described in detail.

[0104] Figure 4 A structural block diagram of a city carbon metering device based on a knowledge graph according to an embodiment of the present disclosure is shown.

[0105] like Figure 4 As shown, the urban carbon metering device 400 based on the knowledge graph of this embodiment includes a construction module 410, an acquisition module 420, a subject carbon emission information obtaining module 430, a target knowledge graph obtaining module 440 and an urban carbon metering result obtaining module 450.

[0106] Construction module 410 is used to construct an initial knowledge graph of carbon activity content in the city for the urban area, wherein the initial knowledge graph includes an initial carbon emission subject subgraph, an initial activity information subgraph, an initial carbon emission subgraph and a time information subgraph. The initial carbon emission subject subgraph includes subject root nodes representing four types of carbon emission subjects, and initial subject attribute nodes having attribute relationships with the subject root nodes. The four types of carbon emission subjects include plot information subjects, function information subjects, location information subjects and mobile information subjects. The initial activity information subgraph includes carbon activity nodes related to carbon emission subjects. The time information subgraph includes time nodes representing the time or period of carbon activity. The initial carbon emission subgraph includes carbon emission nodes related to carbon activities. The subject root nodes of the initial knowledge graph subgraphs have attribute relationships, and the attribute relationships include at least one of the following: contain, generate, be located in, be connected, time, and attribute.

[0107] The acquisition module 420 is used to acquire the carbon activity attribute data and time attribute data of the initial subject attribute node according to the initial knowledge graph, and the time attribute data corresponds to the time node.

[0108] The subject carbon emission information obtaining module 430 is used to perform the carbon emission calculation task according to the carbon activity attribute data and time attribute data of the initial subject attribute node and the carbon emission calculation parameters related to the carbon activity node to obtain the subject carbon emission information related to the initial subject attribute node.

[0109] The target knowledge graph obtaining module 440 is used to update the initial carbon emission information node having an attribute relationship with the carbon activity node according to the subject carbon emission information to obtain the target knowledge graph.

[0110] The city carbon measurement result obtaining module 450 is used to obtain the city carbon measurement result according to the target knowledge graph.

[0111] According to the embodiments of the present disclosure, for urban areas, an initial knowledge graph of carbon activity content in the city can be constructed. The initial knowledge graph may include an initial carbon emission subject subgraph, an initial activity information subgraph, an initial carbon emission subgraph and a time information subgraph. The initial carbon emission subject subgraph may include a subject root node representing four types of carbon emission subjects, and an initial subject attribute node having an attribute relationship with the subject root node. The four types of carbon emission subjects may include a plot information subject, a function information subject, a location information subject and a mobile information subject. The initial activity information subgraph may include a carbon activity node related to the carbon emission subject. The time information subgraph may include a time node representing the time or period when the carbon activity occurs. The initial carbon emission subgraph may include a carbon emission amount node related to the carbon activity. The subject root nodes of the initial knowledge graph subgraphs have an attribute relationship, and the attribute relationship may include at least one of the following: contain, generate, be located in, be connected, time, and attribute. According to the initial knowledge graph, the initial subject attribute node may be obtained. The carbon activity attribute data and time attribute data of the initial subject attribute node are obtained, and the time attribute data corresponds to the time node; the carbon emission calculation task is performed according to the carbon activity attribute data and time attribute data of the initial subject attribute node, and the carbon emission calculation parameters related to the carbon activity node, so as to obtain the subject carbon emission information related to the initial subject attribute node; the initial carbon emission information node having an attribute relationship with the carbon activity node is updated according to the subject carbon emission information, so as to obtain the target knowledge graph, and the urban carbon measurement result is obtained according to the target knowledge graph. The constructed target knowledge graph efficiently integrates the process information such as time, space, subject and so on related to the carbon activities in the city, and forms a multi-dimensional network knowledge structure through the mutual connection of relationships, and represents and stores various elements related to carbon activities in the form of a directed graph, which improves the accuracy and efficiency of automatic measurement of carbon emissions, realizes the comprehensive expression of the mapping relationship between carbon emissions and planning, contributes to the accurate traceability of carbon measurement results, and provides efficient support for carbon reduction and control.

[0112] Based on the above-mentioned carbon emission prediction method based on target knowledge graph, the present disclosure also provides a carbon emission prediction device based on target knowledge graph. Figure 5 The device is described in detail.

[0113] Figure 5 A structural block diagram of a carbon emission prediction device based on a target knowledge graph according to an embodiment of the present disclosure is shown.

[0114] like Figure 5 As shown, the carbon emission prediction device 500 based on the target knowledge graph of this embodiment includes a processing module 510, a triple determination module 520 and a prediction result output module 530.

[0115] Processing module 510 is used to determine the target knowledge graph related to the content of carbon activities in the city. The target knowledge graph includes a carbon emission subject subgraph, an activity information subgraph, a carbon emission subgraph and a time information subgraph. The nodes of the time information subgraph represent time attribute data related to the city's carbon emission activities. The nodes of the carbon emission subject subgraph include subject root nodes related to the plot information subject, the function information subject, the location information subject and the mobile information subject, and subject attribute nodes having an attribute relationship with the subject root nodes. The nodes of the carbon emission subgraph represent subject carbon emission information related to the carbon emission subject. The nodes of the activity information subgraph represent carbon activity attribute data related to the carbon emission subject. The carbon emission subject is related to the time attribute data.

[0116] The triple determination module 520 is used to determine the triples in the target knowledge graph, and the triples include a target carbon emission subject node, a target carbon activity node and a target carbon emission information node with attribute relationships. The target carbon activity node represents the carbon activity attribute data of the carbon emission subject, and the target carbon emission information node represents the subject carbon emission information of the carbon emission subject.

[0117] The prediction result output module 530 is used to input the graph structure corresponding to the triple into the prediction model and output the carbon emission prediction result of the city.

[0118] According to an embodiment of the present disclosure, a target knowledge graph related to the content of carbon activities in a city can be determined. The target knowledge graph may include a carbon emission subject subgraph, an activity information subgraph, a carbon emission subgraph, and a time information subgraph. The nodes of the time information subgraph may represent time attribute data related to the city's carbon emission activities. The nodes of the carbon emission subject subgraph may include subject root nodes related to a plot information subject, a function information subject, a location information subject, and a mobile information subject, as well as subject attribute nodes having an attribute relationship with the subject root nodes. The nodes of the carbon emission subgraph may represent subject carbon emission information related to the carbon emission subject. The nodes of the activity information subgraph may represent carbon activity attribute data related to the carbon emission subject. The carbon emission subject is related to the time attribute data. Triples in the target knowledge graph may be determined. The triples may include a target carbon emission subject node, a target carbon activity node, and a target carbon emission information node having an attribute relationship. The target carbon activity node may represent carbon The carbon activity attribute data of the emission subject, the target carbon emission information node can represent the main carbon emission information of the carbon emission subject; the graph structure corresponding to the triplet is input into the prediction model to output the carbon emission prediction result of the city, and the entity-relationship-entity triplet is defined at the micro level, which improves the accuracy of the automatic measurement and evaluation of urban carbon emissions, and provides decision support for the management of urban carbon activities. By combining the target knowledge graph with the carbon emission related data of the urban area, the inherent correlation of multidimensional data is demonstrated, and the accuracy of urban carbon emission prediction is improved. Data is aggregated from aspects such as carbon emission time, space and cause, which improves the accuracy and professionalism of the matching between the target knowledge graph and the urban carbon emission prediction model, and solves the problems of high data cost, complex knowledge construction and difficult to guarantee prediction effect in urban carbon control planning, and improves the matching degree between the output content and the actual results, so as to effectively capture the useful information in the target knowledge graph for carbon emission prediction.

[0119] According to an embodiment of the present disclosure, any multiple modules among the modules, submodules, units, and subunits can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the modules, submodules, units, and subunits can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, at least one of the modules, submodules, units, and subunits can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be executed.

[0120] Figure 6 A block diagram of an electronic device suitable for implementing a knowledge graph-based urban carbon measurement method and prediction method according to an embodiment of the present disclosure is shown.

[0121] like Figure 6 As shown, the electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 to a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0122] In RAM 603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM 602 and RAM 603 are connected to each other via bus 604. Processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0123] According to an embodiment of the present disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 may further include one or more of the following components connected to the I / O interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0124] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0125] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 602 and / or RAM 603 described above and / or one or more memories other than ROM 602 and RAM 603.

[0126] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the urban carbon measurement method and prediction method based on the knowledge graph provided in the embodiment of the present disclosure.

[0127] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 601. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0128] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0129] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, apparatus, module, unit, etc. described above can be implemented by a computer program module.

[0130] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0131] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. 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 boxes represented in succession 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 or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0132] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0133] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for urban carbon measurement based on knowledge graph, characterized in that: include: For urban areas, an initial knowledge graph of carbon activity content in the city is constructed, wherein the initial knowledge graph includes an initial carbon emission subject subgraph, an initial activity information subgraph, an initial carbon emission subgraph and a time information subgraph, the initial carbon emission subject subgraph includes subject root nodes representing four types of carbon emission subjects, and initial subject attribute nodes having attribute relationships with the subject root nodes, the four types of carbon emission subjects include a plot information subject, a function information subject, a location information subject and a mobile information subject, the initial activity information subgraph includes carbon activity nodes related to the carbon emission subjects, the time information subgraph includes a time node representing the time or period of occurrence of carbon activities, the initial carbon emission subgraph includes carbon emission nodes related to carbon activities, and the subject root nodes of the initial knowledge graph subgraphs have attribute relationships, and the attribute relationships include at least one of the following: contain, generate, be located in, be connected, time, attribute; According to the initial knowledge graph, obtaining carbon activity attribute data and time attribute data of the initial subject attribute node, wherein the time attribute data corresponds to the time node; Execute a carbon emission calculation task according to the carbon activity attribute data and time attribute data of the initial subject attribute node and the carbon emission calculation parameters related to the carbon activity node to obtain subject carbon emission information related to the initial subject attribute node; and According to the subject carbon emission information, an initial carbon emission information node having an attribute relationship with the carbon activity node is updated to obtain a target knowledge graph; According to the target knowledge graph, the city carbon measurement result is obtained.

2. The method according to claim 1, characterized in that The carbon emission subject subgraph of the target knowledge graph includes a plot information subgraph, a function information subgraph, a location information subgraph, and a mobility information subgraph; the main root node of the plot information subgraph is a plot node representing the main body of the plot information, the main attribute node of the plot information subgraph includes a plot attribute node having an attribute relationship with the plot node, and the plot attribute node includes at least one of the following: an area node, a number of people node, a floor area ratio node, a building height node, and a building density node; The land parcel node has a generation relationship with the carbon activity node in the activity information subgraph.

3. The method according to claim 2, characterized in that The mobile information subgraph includes a travel node representing a main body of mobile information, the main attribute node of the mobile information subgraph includes a vehicle node having a generation relationship with the travel node, and the vehicle attribute node having an attribute relationship with the vehicle node includes at least one of the following: a fuel type node, a type node, and a displacement node; The travel node has a containment relationship with the plot node, the travel node has a time relationship with the time node in the time subgraph, and the vehicle node has a generation relationship with the energy activity node in the activity information subgraph.

4. The method according to claim 3, characterized in that: The function information subgraph includes a land type node representing the function information subject, and the type attribute node having an attribute relationship with the land type node includes at least one of the following: an industrial land node, a storage land node, a green land node, a transportation land node, a commercial and service land node, a public service land node, and a residential land node; The land use type node has an attribute relationship with the plot node.

5. The method according to claim 4, characterized in that The location information subgraph includes a road section node representing the main body of the location information, the nodes having a location relationship with the road section node include at least one of the following: an administrative district node and a road node, and the road section attribute nodes having an attribute relationship with the road section node include at least one of the following: a road section length node, a road section level node, and a road section width node; The administrative district attribute nodes having a containment relationship with the administrative district node include at least one of the following: district nodes and street nodes; the road attribute nodes having an attribute relationship with the road node include road name nodes; The nodes having a connection relationship with the road segment node include intersection nodes, and the intersection attribute nodes having an attribute relationship with the intersection node include at least one of the following: a longitude node and a latitude node; The road segment node and the travel node have a location relationship, and the road segment node and the plot node have an adjacent relationship.

6. The method according to claim 5, characterized in that The carbon activity node of the activity information subgraph includes at least one of the following: a waste treatment node, a land use node, an industrial process node and the energy activity node, and the energy activity node includes at least one of the following: a gas consumption node, a water consumption node, a fuel oil consumption node and an electricity consumption node; The carbon emission subgraph includes a carbon emission node related to a carbon activity, the carbon emission node has an inclusion relationship with the carbon activity node, and the carbon emission node has a time relationship with the time node; The time subgraph includes a plurality of time nodes representing different carbon activity attributes, and the time attribute data related to the carbon emission activity is stored in the data layer of the time nodes.

7. A carbon emission prediction method based on target knowledge graph, characterized in that: The method comprises: According to the method described in any one of claims 1 to 6, a target knowledge graph related to the content of carbon activities in the city is determined, wherein the target knowledge graph includes a carbon emission subject subgraph, an activity information subgraph, a carbon emission subgraph and a time information subgraph, wherein the nodes of the time information subgraph represent time attribute data related to the city's carbon emission activities, the nodes of the carbon emission subject subgraph include subject root nodes related to a plot information subject, a function information subject, a location information subject and a mobile information subject, and subject attribute nodes having an attribute relationship with the subject root nodes, the nodes of the carbon emission subgraph represent subject carbon emission information related to the carbon emission subject, the nodes of the activity information subgraph represent carbon activity attribute data related to the carbon emission subject, and the carbon emission subject is related to the time attribute data; Determine a triple in the target knowledge graph, the triple comprising a target carbon emission subject node, a target carbon activity node and a target carbon emission information node having an attribute relationship, the target carbon activity node represents the carbon activity attribute data of the carbon emission subject, and the target carbon emission information node represents the subject carbon emission information of the carbon emission subject; The graph structure corresponding to the triplet is input into the prediction model, and the carbon emission prediction result of the city is output.

8. The method according to claim 7, characterized in that There are multiple time attribute data, the multiple time attribute data are arranged in time series, the multiple time attribute data correspond one-to-one to the multiple target knowledge graphs, and the prediction model includes a graph neural network and a time series network; The step of inputting the graph structure corresponding to the triple into the prediction model and outputting the carbon emission prediction result of the city includes: Inputting a graph structure corresponding to the time attribute data into the graph neural network, and outputting a graph embedding feature matrix, wherein a plurality of the graph embedding feature matrices have a temporal relationship, and the temporal relationship is determined based on the time attribute data corresponding to each of the plurality of graph structures; The plurality of graph embedding feature matrices having a time series relationship are input into the time series network, and the carbon emission prediction result of the city is output.

9. A knowledge graph-based urban carbon metering device, characterized in that: include: A construction module is used to construct an initial knowledge graph of carbon activity content in the city for the urban area, wherein the initial knowledge graph includes an initial carbon emission subject subgraph, an initial activity information subgraph, an initial carbon emission subgraph and a time information subgraph, the initial carbon emission subject subgraph includes a subject root node representing four types of carbon emission subjects, and an initial subject attribute node having an attribute relationship with the subject root node, the four types of carbon emission subjects include a plot information subject, a function information subject, a location information subject and a mobile information subject, the initial activity information subgraph includes a carbon activity node related to the carbon emission subject, the time information subgraph includes a time node representing the time or period of occurrence of the carbon activity, the initial carbon emission subgraph includes a carbon emission amount node related to the carbon activity, and the subject root nodes of the initial knowledge graph subgraphs have an attribute relationship, and the attribute relationship includes at least one of the following: contain, generate, be located in, be connected, time, attribute; An acquisition module, configured to acquire carbon activity attribute data and time attribute data of the initial subject attribute node according to the initial knowledge graph, wherein the time attribute data corresponds to the time node; A subject carbon emission information obtaining module, configured to perform a carbon emission calculation task according to the carbon activity attribute data and time attribute data of the initial subject attribute node and the carbon emission calculation parameters related to the carbon activity node, and obtain the subject carbon emission information related to the initial subject attribute node; and A target knowledge graph obtaining module is used to update the initial carbon emission information node having an attribute relationship with the carbon activity node according to the subject carbon emission information to obtain a target knowledge graph; The city carbon measurement result obtaining module is used to obtain the city carbon measurement result according to the target knowledge graph.

10. A carbon emission prediction device based on a target knowledge graph, characterized in that: The device comprises: A processing module, for determining a target knowledge graph related to carbon activity content in a city according to any one of claims 1 to 6, wherein the target knowledge graph includes a carbon emission subject subgraph, an activity information subgraph, a carbon emission subgraph, and a time information subgraph, wherein nodes of the time information subgraph represent time attribute data related to carbon emission activities in the city, nodes of the carbon emission subject subgraph include subject root nodes related to a plot information subject, a function information subject, a location information subject, and a mobile information subject, and subject attribute nodes having an attribute relationship with the subject root nodes, nodes of the carbon emission subgraph represent subject carbon emission information related to a carbon emission subject, nodes of the activity information subgraph represent carbon activity attribute data related to the carbon emission subject, and the carbon emission subject is related to the time attribute data; A triple determination module is used to determine a triple in the target knowledge graph, wherein the triple includes a target carbon emission subject node, a target carbon activity node and a target carbon emission information node having an attribute relationship, wherein the target carbon activity node represents the carbon activity attribute data of the carbon emission subject, and the target carbon emission information node represents the subject carbon emission information of the carbon emission subject; The prediction result output module is used to input the graph structure corresponding to the triple into the prediction model and output the carbon emission prediction result of the city.

Images