Intelligent management methods, devices, and media for knowledge graph-based building systems

Abstract

This invention discloses a knowledge graph-based intelligent management method for building systems. The building intelligent management system receives currently input operational data. The system includes a building knowledge graph and a building knowledge application database. The building knowledge graph includes multiple control rules for regulating the building system. Based on the operational data, the building knowledge graph determines the target control rule to be invoked and, based on the target control rule and the operational data, determines a target control strategy. The building intelligent management system then regulates the building system according to the target control strategy. This knowledge graph-based intelligent management method for building systems solves the problem of low processing efficiency in existing technologies when abnormal situations occur, effectively improving the processing efficiency when abnormal situations arise.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of building engineering technology, and in particular to a smart management method, device and medium for building systems based on knowledge graphs. Background Technology

[0002] Existing technologies for the management and control of smart buildings generally rely on platforms such as BIM combined with IoT technology to aggregate data from various subsystems within a building or building complex, such as database systems, building equipment monitoring systems, and equipment control systems. The data on the integrated platform is used to achieve automated monitoring of each part of the system and to provide a basis for judgment for human control or automated control under certain rules, so as to realize multiple functions such as building status monitoring and energy-saving optimization control.

[0003] However, in existing building management technologies, the data and functional modules of each subsystem within a building system are relatively independent. This necessitates user intervention to connect, link, and manage these data and modules. The weak connectivity between modules makes it difficult to quickly identify the cause of anomalies and potential chain reactions, resulting in low efficiency in handling abnormal situations. Summary of the Invention

[0004] This invention provides a method, device, and medium for intelligent management of building systems based on knowledge graphs, which can solve the problem of low processing efficiency when abnormal situations occur in the prior art and can effectively improve the processing efficiency when abnormal situations occur.

[0005] The first aspect of this invention provides a smart management method for building systems based on knowledge graphs, comprising:

[0006] The building intelligent management system receives currently input operational data. The building intelligent management system includes a building knowledge graph and a building knowledge application database. The building knowledge graph includes multiple control rules for regulating the building system. The building knowledge application database includes historical data of the building system. The historical data is used to provide a basis for constructing the control rules in the knowledge graph.

[0007] The building knowledge graph determines the target control rules to be invoked based on the operational data, and determines the target control strategy based on the target control rules and the operational data.

[0008] The building intelligent management system regulates the building system according to the target regulation strategy.

[0009] Optional, also includes:

[0010] The building intelligent management system receives user input;

[0011] Based on the question, determine whether the data stored in the architectural knowledge graph is sufficient to return the answer to the question;

[0012] If the determination result is yes, the architectural knowledge graph obtains data locally and generates an answer; otherwise, the architectural knowledge graph obtains data from the architectural knowledge application database and generates an answer through a preset interface between itself and the architectural knowledge application database.

[0013] Optional, also includes:

[0014] The building intelligent management system is constructed based on a pre-established building knowledge graph and a building knowledge application database. The knowledge used to construct the building knowledge graph includes at least one of the following: building system operation knowledge, building system analysis knowledge, and building system control knowledge. The data used to construct the building knowledge application database includes at least one of the following: historical query data, historical call data, and historical optimization data of the building system.

[0015] Optionally, the steps for constructing the architectural knowledge graph include:

[0016] Based on the system architecture of the building system and monitoring data related to the operating status of each subsystem within the building system, acquire operational knowledge of the building system; and / or, based on system analysis methods within the building system, acquire analytical knowledge of the building system; and / or, based on system regulation and control methods within the building system, acquire regulatory knowledge of the building system; and,

[0017] Based on the knowledge of building system operation, and / or the knowledge of building system analysis, and / or the knowledge of building system regulation, construct the building knowledge graph.

[0018] Optionally, obtaining the building system operation knowledge based on the system architecture of the building system and monitoring data related to the operating status of each subsystem in the building system includes:

[0019] Based on the connection relationship between devices in each subsystem of the building system, obtain the correspondence between the various data in the monitoring data;

[0020] Based on the system architecture and the correspondence between various data points in the monitoring data, the operational knowledge of the building system is constructed; and

[0021] The step of acquiring building system analysis knowledge based on the system analysis method in the building system includes:

[0022] Based on the system analysis method, the building system analysis knowledge is obtained, wherein the system analysis method includes a system status monitoring method, an equipment fault diagnosis method, and a system energy consumption prediction method; and

[0023] The step of acquiring building system regulation knowledge based on the system regulation and control method in the building system includes:

[0024] According to the system regulation and control method, the building system regulation and control knowledge is obtained, wherein the system regulation and control method includes a fault handling method and an equipment control parameter optimization method.

[0025] Optionally, the steps for constructing the architectural knowledge application database include:

[0026] Based on the acquired historical query data, query task knowledge is obtained; and / or, based on the acquired historical call data, analysis task knowledge is obtained; and / or, based on the acquired historical optimization data, optimization task knowledge is obtained; and,

[0027] The architectural knowledge application database is constructed based on the query task knowledge, the analysis task knowledge, and / or the optimization task knowledge.

[0028] Optionally, obtaining query task knowledge based on the acquired historical query data includes:

[0029] The historical query data is categorized, and a standard query question is set for the categorized historical query data.

[0030] Based on the standard query question corresponding to each type of query data, the query task knowledge is generated; and

[0031] The step of acquiring analysis task knowledge based on the obtained historical call data includes:

[0032] Based on the acquired historical call data, the analysis task knowledge is obtained, wherein the historical call data includes system status call data and system parameter call data of the building system; and,

[0033] The step of obtaining the analysis task knowledge based on the acquired historical call data includes:

[0034] Based on the system status call data and the system parameter call data, obtain the analysis task corresponding to each call of data;

[0035] Each analysis task corresponding to the call is categorized to obtain the analysis task for each category;

[0036] Based on each category of analysis task, establish the knowledge of the analysis task; and

[0037] The step of acquiring optimization task knowledge based on the obtained historical optimization data includes:

[0038] Based on the historical optimization data, determine the optimization object corresponding to the historical optimization data;

[0039] Find the parameter indicators for each optimization object from the historical optimization data;

[0040] The optimization task knowledge is created based on the parameter indicators of each optimization object.

[0041] A second aspect of this invention provides an intelligent management device for a knowledge graph-based building system, comprising:

[0042] The data acquisition unit is used by the building intelligent management system to receive the currently input operational data. The building intelligent management system includes a building knowledge graph and a building knowledge application database. The building knowledge graph includes multiple control rules for regulating the building system. The building knowledge application database includes historical data of the building system. The historical data is used to provide a basis for constructing the control rules in the knowledge graph.

[0043] The control strategy acquisition unit uses the building knowledge graph to determine the target control rule to be invoked based on the operational data, and to determine the target control strategy based on the target control rule and the operational data.

[0044] The control unit is used by the building intelligent management system to control the building system according to the target control strategy.

[0045] A third aspect of the present invention provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the method steps of the intelligent management method for a knowledge graph-based building system as described in the first aspect.

[0046] A fourth aspect of the present invention provides a device including at least one processor, and at least one memory and bus connected to the processor;

[0047] The processor and memory communicate with each other through the bus;

[0048] The processor is used to invoke program instructions in the memory to execute the steps of the first aspect of the intelligent management method for a knowledge graph-based building system.

[0049] The beneficial effects of the embodiments of the present invention are as follows:

[0050] Based on the above technical solution, since the building intelligent management system is constructed according to a pre-established building knowledge graph and building knowledge application database, it can determine the target control rules to be invoked after acquiring the operating data of the building intelligent management system, and determine the target control strategy based on the target control rules and operating data; finally, it can control the building system according to the target control strategy. In this way, the target control strategy can be determined to control the building system based on the operating data and target control rules. Since the building intelligent management system includes a building knowledge graph and a building knowledge application database, the building knowledge graph includes multiple control rules for controlling the building system, and the building knowledge application database includes historical data of the building system. The historical data is used to provide a basis for the construction of control rules in the knowledge graph, making the determined target control strategy more compatible with the operating data. Thus, when abnormal situations occur in the operating data, the corresponding target control strategy can be quickly determined and processed according to the target control strategy, thereby effectively improving the processing efficiency when abnormal situations occur. Attached Figure Description

[0051] Figure 1 This is a flowchart of the first method of the intelligent management method for a building system based on knowledge graphs in this invention.

[0052] Figure 2 This is a flowchart illustrating the steps involved in constructing a building knowledge graph in an embodiment of the present invention.

[0053] Figure 3 This is a flowchart of the second method of the intelligent management method for building systems based on knowledge graphs in this invention.

[0054] Figure 4 This is a schematic diagram of the structure of the intelligent management device for a knowledge graph-based building system in an embodiment of the present invention;

[0055] Figure 5 This is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. Detailed Implementation

[0056] To better understand the above technical solutions, the technical solutions of the embodiments of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of the present invention, rather than limitations on the technical solutions of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0057] In this specification, a knowledge graph is a structured semantic knowledge base used to describe concepts and their relationships in the physical world in symbolic form. Its basic building blocks are "entity-relationship-entity" triples, as well as entities and their associated attribute value pairs. Entities are interconnected through relationships, forming a network-like knowledge structure. A building knowledge graph, on the other hand, is a structured knowledge base for building systems.

[0058] like Figure 1 As shown, this embodiment of the invention provides an intelligent management method for building systems based on knowledge graphs, including the following steps:

[0059] S101. The building intelligent management system receives the currently input operating data, wherein the building intelligent management system includes a building knowledge graph and a building knowledge application database. The building knowledge graph includes multiple control rules for regulating the building system, and the building knowledge application database includes historical data of the building system. The historical data is used to provide a basis for constructing the control rules in the knowledge graph.

[0060] S102. The building knowledge graph determines the target control rules to be invoked based on the operational data, and determines the target control strategy based on the target control rules and the operational data.

[0061] S103, The building intelligent management system regulates the building system according to the target regulation strategy.

[0062] In step S101, the building intelligent management system is first constructed based on a pre-established building knowledge graph and a building knowledge application database. The knowledge used to construct the building knowledge graph includes at least one of the following: building system operation knowledge, building system analysis knowledge, and building system control knowledge. The data used to construct the building knowledge application database includes at least one of the following: historical query data, historical call data, and historical optimization data of the building system.

[0063] Specifically, when constructing a building knowledge graph, one or more of the following are required: knowledge of building system operation, knowledge of building system analysis, and knowledge of building system regulation. Preferably, the building knowledge graph should be constructed based on knowledge of building system operation, knowledge of building system analysis, and knowledge of building system regulation.

[0064] Specifically, when constructing a building knowledge graph based on knowledge of building system operation, building system analysis, and building system regulation, such as... Figure 2 As shown, the steps for constructing a building knowledge graph include:

[0065] S201. Based on the system architecture of the building system and the monitoring data related to the operating status of each subsystem in the building system, obtain the operating knowledge of the building system;

[0066] S202. Obtain the building system analysis knowledge according to the system analysis method in the building system;

[0067] S203. Obtain the building system regulation knowledge according to the system regulation and control method in the building system;

[0068] S204. Construct the building knowledge graph based on the building system operation knowledge, the building system analysis knowledge, and the building system control knowledge.

[0069] In step S201, the connection relationships between devices in each subsystem of the building system can be obtained first, and then the correspondence between various data in the monitoring data can be obtained based on the connection relationships between devices in each subsystem of the building system; the building system operation knowledge can be constructed based on the system architecture and the correspondence between various data in the monitoring data.

[0070] The building system in this specification includes a database system, a building equipment monitoring system, and an equipment control system. This allows us to obtain the connection relationships between each monitoring device in the building equipment monitoring system, as well as the connection relationships between each control device in the equipment control system.

[0071] Specifically, the system structure of each subsystem within the building system is analyzed, along with monitoring data related to the operational status of each subsystem. The connection relationships between devices in each subsystem are obtained. Then, based on the obtained monitoring data and the connection relationships, the correspondence between individual data points in the monitoring data is derived. This correspondence is obtained from the connection relationships between devices. For example, device A is sequentially connected to devices B and C. Monitoring data A1 from device A corresponds to monitoring data B1 from device B, and B1 corresponds to monitoring data C1 from device C.

[0072] Next, step S202 is executed. Steps S201 and S202 can be executed simultaneously, or step S202 can be executed first and then step S201. This specification does not impose specific restrictions.

[0073] Specifically, commonly used analysis methods for building systems can be acquired as the system analysis methods. Based on each acquired analysis method, the building system analysis knowledge can be obtained. The system analysis methods include system status monitoring methods, equipment fault diagnosis methods, and system energy consumption prediction methods.

[0074] Specifically, each commonly used analysis method in building systems can be organized and standardized application forms can be constructed. For example, it can be constructed based on system status monitoring methods, equipment fault diagnosis methods, system energy consumption prediction methods, etc., to obtain the building system analysis knowledge.

[0075] Next, step S203 is executed. Steps S203 and S202 can be executed simultaneously, or step S203 can be executed first and then step S202. This specification does not impose specific restrictions.

[0076] Specifically, the system regulation and control method can be obtained first, and then the building system regulation and control knowledge can be obtained based on the system regulation and control method. The system regulation and control method includes fault handling method and equipment control parameter optimization method.

[0077] Specifically, firstly, commonly used system regulation and control methods in building systems are compiled to obtain the system regulation and control methods. Then, standardized application forms are constructed based on the obtained system regulation and control methods. For example, they can be constructed based on fault handling methods and equipment control parameter optimization methods to obtain the building system regulation and control knowledge.

[0078] Next, step S204 is executed. In this step, after obtaining the building system operation knowledge, the building system analysis knowledge, and the building system control knowledge through steps S201-S203, the building knowledge graph is constructed based on the obtained building system operation knowledge, building system analysis knowledge, and building system control knowledge. Alternatively, the building knowledge graph can be constructed based on one or more of the obtained building system operation knowledge, building system analysis knowledge, and building system control knowledge.

[0079] Specifically, the architectural knowledge graph stores structured control rules, which can be models trained on historical data. As the system continues to run, real-time data can be stored in the database to continuously enrich the historical data, and the models in the knowledge graph can be iteratively updated according to the updated historical data at certain intervals.

[0080] Furthermore, in practical applications, the building knowledge graph can input real-time data into the model based on the current operating conditions to determine how to adjust the system. If the model in the knowledge graph is insufficient to determine the appropriate adjustment, historical data stored in the database can be retrieved via an interface. For example, inputting the current operating conditions into the corresponding model in the building knowledge graph can calculate that the current temperature is too high and the cooling capacity needs to be increased to ensure that the current temperature remains within the set range. Alternatively, it can calculate whether to reduce the cooling capacity, change the cooling mode, increase the heating capacity, or decrease the heating capacity.

[0081] Thus, after constructing the architectural knowledge graph, its powerful graphical display capabilities can be leveraged to intuitively represent the working principles of intelligent building management and the relationships between its various components. Furthermore, the strong relevance of the architectural knowledge graph allows for quick retrieval of all information related to a specific piece of knowledge.

[0082] Furthermore, the aforementioned building knowledge graph enables the fusion of independently stored multi-source knowledge related to smart buildings. This not only allows for more efficient management of all knowledge but also facilitates knowledge sharing, which is beneficial for system analysis and modeling. The building knowledge graph format also helps to standardize processes for system analysis and control, thereby reducing modeling costs and improving efficiency. Managing knowledge through knowledge graph tools also facilitates knowledge modification and updates.

[0083] In another embodiment of this specification, when constructing a building knowledge graph based on building system operation knowledge, the construction can be performed according to steps S201 and S204, where step S204 involves constructing the building knowledge graph based on building system operation knowledge. Similarly, when constructing a building knowledge graph based on building system analysis knowledge, the construction can be performed according to steps S202 and S204, where step S204 involves constructing the building knowledge graph based on building system analysis knowledge. Of course, when constructing a building knowledge graph based on building system regulation knowledge, the construction can be performed according to steps S203 and S204, where step S204 involves constructing the building knowledge graph based on building system regulation knowledge. Thus, the steps for constructing a building knowledge graph can be determined based on one or more types of knowledge used to construct the knowledge graph, and a building knowledge graph can be constructed based on any combination of one or more of the above-mentioned knowledge. This specification does not impose specific limitations.

[0084] Furthermore, the powerful implicit knowledge mining and reasoning capabilities of the building knowledge graph can be utilized to deduce more reasonable management suggestions based on actual operating conditions during the intelligent management of buildings, thereby achieving automatic adjustment of management strategies.

[0085] In the embodiments of this specification, when constructing the architectural knowledge application database, it is necessary to construct an architectural knowledge graph based on one or more of historical query data, historical call data, and historical optimization data. Preferably, it is necessary to construct an architectural knowledge graph based on historical query data, historical call data, and historical optimization data. The historical data includes one or more of historical query data, historical call data, and historical optimization data.

[0086] Specifically, when constructing a building knowledge application database based on historical query data, historical call data, and historical optimization data, the construction steps of the building knowledge application database include: acquiring query task knowledge based on the acquired historical query data; acquiring analysis task knowledge based on the acquired historical call data; acquiring optimization task knowledge based on the acquired historical optimization data; and constructing the building knowledge application database based on the query task knowledge, the analysis task knowledge, and the optimization task knowledge. Alternatively, the building knowledge application database can be constructed based on one or more of the query task knowledge, the analysis task knowledge, and the optimization task knowledge.

[0087] In this embodiment of the specification, a large amount of query data from users regarding the building system is collected, and all the collected query data is used as the historical query data. After obtaining the historical query data, the historical query data is classified, and a standard query question is set for each classified historical query data. In this way, each category of query data corresponds to a standard query question. Then, based on the standard query question corresponding to each category of query data, the query task knowledge is generated, so that the query task knowledge includes the standard query question corresponding to each category of query data.

[0088] Specifically, when collecting a large amount of query data from users regarding the building system, the data corresponding to the user's query behavior stored in the database containing user behavior data can be used as the query data.

[0089] In this embodiment of the specification, when acquiring analysis task knowledge, the analysis task knowledge can be acquired based on the acquired historical call data, wherein the historical call data includes the system status call data and system parameter call data of the building system.

[0090] Specifically, when acquiring analysis task knowledge, the system status call data and the system parameter call data can be acquired. Based on the system status call data and the system parameter call data, the analysis task corresponding to each call is obtained. The analysis tasks corresponding to each call are classified to obtain analysis tasks of each category. Based on the analysis tasks of each category, the analysis task knowledge is established. In this way, after the user inputs data, the analysis task knowledge can be used to find the analysis task of the target category corresponding to the user input data.

[0091] In this embodiment of the specification, when acquiring optimization task knowledge, the historical optimization data can be acquired first, and the optimization object corresponding to the historical optimization data can be determined based on the historical optimization data. The parameter indicators corresponding to each optimization object can be found from the historical optimization data. Based on the parameter indicators of the optimization object, the optimization task knowledge can be created. Thus, after creating the optimization task knowledge and obtaining the target object to be optimized input by the user, the parameter indicators corresponding to the target object can be found based on the optimization task knowledge.

[0092] After constructing the building intelligent management system based on the building knowledge graph and building knowledge application database, the system acquires the building system's operational data and then transmits the acquired operational data to the building intelligent management system, thereby enabling the building intelligent management system to receive the operational data.

[0093] After receiving the running data, proceed to step S102.

[0094] In this step, the building knowledge graph analyzes the operational data to obtain target control rules; then, based on the target control rules and operational data, it determines the target control strategy.

[0095] Specifically, a control rule corresponding to the operational data is determined from multiple control rules in the building knowledge graph as the target control rule; then, the target control strategy is determined based on the target control rule and the operational data.

[0096] And after determining the target control strategy, step S103 is executed.

[0097] In this step, after determining the target control strategy, the target control strategy is executed to regulate the building system. This allows the building intelligent management system to obtain and execute the target control strategy based on operational data, thereby achieving automatic control and significantly improving the timeliness of control.

[0098] For example, when the operating data corresponds to the cooling rule among multiple control rules, the cooling rule is used as the target control rule, and the target control strategy is determined based on the cooling rule and the operating data. If the cooling rule is a cooling model, the operating data is input into the cooling model for calculation. If the operating temperature corresponding to the operating data is determined to be higher than the set temperature range, the target control strategy is to increase the cooling capacity to ensure that the operating temperature is within the set temperature range.

[0099] In another embodiment of this specification, after creating the building intelligent management system, as follows: Figure 3 As shown, it also includes:

[0100] S301, The building intelligent management system receives user input;

[0101] S302. Determine whether the data stored in the architectural knowledge graph is sufficient to return the answer to the question based on the question.

[0102] S303. If the judgment result is yes, the architectural knowledge graph obtains data locally and generates an answer; otherwise, the architectural knowledge graph obtains data from the architectural knowledge application database and generates an answer through a preset interface between itself and the architectural knowledge application database.

[0103] In step S301, when a user needs to inquire about certain issues, the user inputs the questions into the building intelligence system, allowing the building intelligence system to receive the user's input. For example, a user might submit a complaint after accessing the corresponding page of the building intelligence system via their mobile phone, and the complaint content can be used as the user's input question.

[0104] After receiving the user's input question, proceed to step S302.

[0105] In this step, the question is first used as the search condition to search the data stored in the architectural knowledge graph to determine whether the data stored in the architectural knowledge graph is sufficient to return the answer to the question.

[0106] Next, proceed to step S303.

[0107] In this step, if step S302 determines that the data stored in the architectural knowledge graph is sufficient to return the answer to the question, then the architectural knowledge graph retrieves the data locally, generates the answer, and displays the answer to the user. If it determines that the data stored in the architectural knowledge graph is insufficient to return the answer to the question, then the architectural knowledge graph retrieves the data from the architectural knowledge application database through its preset interface with the architectural knowledge application database, generates the answer, and displays the answer to the user.

[0108] For example, when a user needs to check whether a certain monitoring device D is turned on normally, the monitoring ID of monitoring device D can be obtained from the building knowledge graph; then, based on the monitoring ID, the monitoring device corresponding to the monitoring ID can be found from the building knowledge graph, and the operating parameters of the monitoring device corresponding to the monitoring ID can be returned to the user, so that the user can know whether the monitoring device D is running normally.

[0109] For example, when a user needs to query the energy consumption of corridor lights in a building, the system can first search the building knowledge graph to see if the energy consumption data for corridor lights in that building exists. If it does not exist, the system can call a preset interface to retrieve the corridor light energy consumption data from the building knowledge application database and display the corridor light energy consumption data to the user.

[0110] Thus, after acquiring the query task knowledge, the analysis task knowledge, and the optimization task knowledge, the building knowledge application database is constructed. This allows the system to determine whether the data stored in the building knowledge graph is sufficient to generate a corresponding answer after receiving a user's input question. If sufficient, the system retrieves data from the building knowledge graph locally and generates an answer; otherwise, it retrieves the corresponding answer from the building knowledge application database. This enables the building intelligent management system to automatically respond to user-input questions, improving the accuracy and efficiency of the obtained answers and making it more convenient for users.

[0111] The beneficial effects of the embodiments of the present invention are as follows:

[0112] Based on the above technical solution, since the building intelligent management system is constructed according to a pre-established building knowledge graph and building knowledge application database, it can determine the target control rules to be invoked after acquiring the operating data of the building intelligent management system, and determine the target control strategy based on the target control rules and operating data; finally, it can control the building system according to the target control strategy. In this way, the target control strategy can be determined to control the building system based on the operating data and target control rules. Since the building intelligent management system includes a building knowledge graph and a building knowledge application database, the building knowledge graph includes multiple control rules for controlling the building system, and the building knowledge application database includes historical data of the building system. The historical data is used to provide a basis for the construction of control rules in the knowledge graph, making the determined target control strategy more compatible with the operating data. Thus, when abnormal situations occur in the operating data, the corresponding target control strategy can be quickly determined and processed according to the target control strategy, thereby effectively improving the processing efficiency when abnormal situations occur.

[0113] like Figure 4 As shown, based on the same inventive concept, this embodiment of the invention provides an intelligent management device for a knowledge graph-based building system, comprising the following units:

[0114] The data acquisition unit 401 is used by the building intelligent management system to receive the currently input operational data. The building intelligent management system includes a building knowledge graph and a building knowledge application database. The building knowledge graph includes multiple control rules for regulating the building system. The building knowledge application database includes historical data of the building system. The historical data is used to provide a basis for constructing the control rules in the knowledge graph.

[0115] The control strategy acquisition unit 402 is used to determine the target control rule to be invoked based on the operating data, and to determine the target control strategy based on the target control rule and the operating data.

[0116] The control unit 403 is used by the building intelligent management system to control the building system according to the target control strategy.

[0117] In one alternative embodiment, the device further includes:

[0118] The question receiving unit in the building intelligent management system is used to receive questions input by users.

[0119] A judgment unit is used to determine whether the data stored in the architectural knowledge graph is sufficient to return the answer to the question;

[0120] If the judgment result is yes, the building knowledge graph obtains data locally and generates an answer; otherwise, the building knowledge graph obtains data from the building knowledge application database and generates an answer through a preset interface between itself and the building knowledge application database.

[0121] In one alternative embodiment, the device further includes:

[0122] The system construction unit is used to construct the intelligent building management system based on a pre-established building knowledge graph and a building knowledge application database. The knowledge used to construct the building knowledge graph includes at least one of the following: building system operation knowledge, building system analysis knowledge, and building system control knowledge. The data used to construct the building knowledge application database includes at least one of the following: historical query data, historical call data, and historical optimization data of the building system.

[0123] In one alternative embodiment, the device further includes:

[0124] The knowledge graph construction unit is used to acquire building system operation knowledge based on the system architecture of the building system and monitoring data related to the operating status of each subsystem in the building system; and / or, acquire building system analysis knowledge based on the system analysis methods in the building system; and / or, acquire building system regulation knowledge based on the system regulation and control methods in the building system; and, based on the building system operation knowledge, and / or the building system analysis knowledge, and / or the building system regulation knowledge, construct the building knowledge graph.

[0125] In one optional implementation, the knowledge graph construction unit is configured to: obtain the correspondence between various data in the monitoring data based on the connection relationships between devices in each subsystem of the building system; construct the building system operation knowledge based on the system architecture and the correspondence between various data in the monitoring data; obtain the building system analysis knowledge based on the system analysis method, wherein the system analysis method includes a system status monitoring method, an equipment fault diagnosis method, and a system energy consumption prediction method; and obtain the building system regulation knowledge based on the system regulation and control method, wherein the system regulation and control method includes a fault handling method and an equipment control parameter optimization method.

[0126] In one alternative embodiment, the device further includes:

[0127] An application database construction unit is configured to acquire query task knowledge based on the acquired historical query data; and / or acquire analysis task knowledge based on the acquired historical call data; and / or acquire optimization task knowledge based on the acquired historical optimization data; and construct the architectural knowledge application database based on the query task knowledge, the analysis task knowledge, and / or the optimization task knowledge.

[0128] In one optional implementation, the application database construction unit is configured to classify the historical query data, define a standard query question for the classified historical query data, generate query task knowledge based on the standard query question corresponding to each type of query data, and acquire analysis task knowledge based on the acquired historical call data, wherein the historical call data includes system status call data and system parameter call data of the building system; and acquire the analysis task corresponding to each call based on the system status call data and the system parameter call data; classify the analysis tasks corresponding to each call to obtain analysis tasks of each category; establish analysis task knowledge based on each category of analysis tasks; determine the optimization object corresponding to the historical optimization data based on the historical optimization data; find the parameter indicators of each optimization object from the historical optimization data; and create optimization task knowledge based on the parameter indicators of each optimization object.

[0129] This invention provides a storage medium storing a program that, when executed by a processor, implements the intelligent management method for the knowledge graph-based building system.

[0130] This invention provides a device, such as... Figure 5 As shown, device 50 includes at least one processor 501, at least one memory 502 connected to processor 501, and a bus 503; wherein, processor 501 and memory 502 communicate with each other through bus 503; processor 501 is used to call program instructions in memory 502 to execute the above-described method for constructing a business graph based on a source tracing graph and the method for source tracing retrieval. The device in this article can be a server, PC, PAD, mobile phone, etc.

[0131] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 Devices that specify the functions in one or more boxes.

[0132] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction device, which is implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0133] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0134] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0135] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A smart management method for building systems based on knowledge graphs, characterized in that, include: The building intelligent management system receives currently input operational data. The building intelligent management system includes a building knowledge graph and a building knowledge application database. The building knowledge graph includes multiple control rules for regulating the building system. The building knowledge application database includes historical data of the building system. The historical data is used to provide a basis for constructing the control rules in the knowledge graph. The building knowledge graph determines the target control rules to be invoked based on the operational data, and determines the target control strategy based on the target control rules and the operational data. The building intelligent management system regulates the building system according to the target regulation strategy; The steps for constructing the architectural knowledge graph include: Based on the system architecture of the building system and monitoring data related to the operating status of each subsystem within the building system, acquire operational knowledge of the building system; and / or, based on system analysis methods within the building system, acquire analytical knowledge of the building system; and / or, based on system regulation and control methods within the building system, acquire regulatory knowledge of the building system; and, Based on the knowledge of building system operation, and / or the knowledge of building system analysis, and / or the knowledge of building system regulation, construct the building knowledge graph; The process of acquiring operational knowledge of the building system based on the system architecture and monitoring data related to the operational status of each subsystem within the building system includes: Based on the connection relationship between devices in each subsystem of the building system, obtain the correspondence between the various data in the monitoring data; Based on the system architecture and the correspondence between various data points in the monitoring data, the operational knowledge of the building system is constructed; and The step of acquiring building system analysis knowledge based on the system analysis method in the building system includes: Based on the system analysis method, the building system analysis knowledge is obtained, wherein the system analysis method includes a system status monitoring method, an equipment fault diagnosis method, and a system energy consumption prediction method; and The step of acquiring building system regulation knowledge based on the system regulation and control method in the building system includes: According to the system regulation and control method, the building system regulation and control knowledge is obtained, wherein the system regulation and control method includes a fault handling method and an equipment control parameter optimization method; The steps for constructing the architectural knowledge application database include: Based on the acquired historical query data, query task knowledge is obtained; and / or, based on the acquired historical call data, analysis task knowledge is obtained; and / or, based on the acquired historical optimization data, optimization task knowledge is obtained; and, The architectural knowledge application database is constructed based on the query task knowledge, the analysis task knowledge, and / or the optimization task knowledge. The step of obtaining query task knowledge based on the acquired historical query data includes: The historical query data is categorized, and a standard query question is set for the categorized historical query data. Based on the standard query question corresponding to each type of query data, the query task knowledge is generated; and The step of acquiring analysis task knowledge based on the obtained historical call data includes: Based on the acquired historical call data, the analysis task knowledge is obtained, wherein the historical call data includes system status call data and system parameter call data of the building system; and, The step of obtaining the analysis task knowledge based on the acquired historical call data includes: Based on the system status call data and the system parameter call data, obtain the analysis task corresponding to each call of data; Each analysis task corresponding to the call is categorized to obtain the analysis task for each category; Based on each category of analysis task, establish the knowledge of the analysis task; and The step of acquiring optimization task knowledge based on the obtained historical optimization data includes: Based on the historical optimization data, determine the optimization object corresponding to the historical optimization data; Find the parameter indicators for each optimization object from the historical optimization data; The optimization task knowledge is created based on the parameter indicators of each optimization object.

2. The method according to claim 1, characterized in that, Also includes: The building intelligent management system receives user input; Based on the question, determine whether the data stored in the architectural knowledge graph is sufficient to return the answer to the question; If the determination result is yes, the architectural knowledge graph obtains data locally and generates an answer; otherwise, the architectural knowledge graph obtains data from the architectural knowledge application database and generates an answer through a preset interface between itself and the architectural knowledge application database.

3. The method according to claim 1, characterized in that, Also includes: The building intelligent management system is constructed based on a pre-established building knowledge graph and a building knowledge application database. The knowledge used to construct the building knowledge graph includes at least one of the following: building system operation knowledge, building system analysis knowledge, and building system control knowledge. The data used to construct the building knowledge application database includes at least one of the following: historical query data, historical call data, and historical optimization data of the building system.

4. A smart management device for a knowledge graph-based building system, the device being used to implement the steps of the method as described in any one of claims 1-3, characterized in that, include: The data acquisition unit is used by the building intelligent management system to receive the currently input operational data. The building intelligent management system includes a building knowledge graph and a building knowledge application database. The building knowledge graph includes multiple control rules for regulating the building system. The building knowledge application database includes historical data of the building system. The historical data is used to provide a basis for constructing the control rules in the knowledge graph. The control strategy acquisition unit uses the building knowledge graph to determine the target control rule to be invoked based on the operational data, and to determine the target control strategy based on the target control rule and the operational data. The control unit is used by the building intelligent management system to control the building system according to the target control strategy.

5. A storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1-3.

6. A device, characterized in that, It includes at least one processor, and at least one memory and bus connected to the processor; The processor and memory communicate with each other through the bus; The processor is used to invoke program instructions in the memory to execute the steps of the intelligent management method for a knowledge graph-based building system as described in any one of claims 1-3.

Images