Knowledge graph construction method and device based on multilevel structured address
By obtaining and dividing the multi-level address information and business attribute information of customers in the power industry, establishing association relationships and building a knowledge graph of multi-level structured addresses, the problem of inability to fully represent the relationship between customers and addresses in the existing technology is solved, and more accurate and sufficient association representation is achieved.
Patent Information
- Application Number
- CN202411935741.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-26
- Publication Date
- 2025-03-14
Smart Images
Figure CN119623602A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of knowledge graph construction, and in particular to a method and device for constructing a knowledge graph based on a multi-level structured address. Background Art
[0002] With the continuous development of science and technology, knowledge graph, as a structured semantic knowledge base, organizes complex knowledge in a structured way to facilitate computer program understanding, storage and retrieval. In addition, in recent years, with the development and application of artificial intelligence technology, knowledge graph, as one of the key technologies, has been widely used in intelligent search, intelligent question and answer, personalized recommendation and content distribution.
[0003] As for the customer information knowledge graph of the power industry, on the one hand, the existing knowledge graph only contains address information corresponding to the customer's registered address, and does not contain other address information associated with the customer (for example, the address information of the equipment used by the customer and the address information of the customer's electricity meter, etc.). Therefore, the data information contained in the knowledge graph is incomplete and cannot accurately represent the relationship between the customer and the corresponding address. On the other hand, for customers, since the supported business priorities are different and the corresponding address information levels are also different, the knowledge graph finally constructed needs to be able to fully represent the relationship between addresses at all levels and businesses of different priorities.
[0004] Currently, no effective solution has been proposed to the technical problem that the data information contained in the knowledge graph in the above-mentioned prior art is incomplete and cannot accurately and fully represent the relationship between customers and corresponding addresses. Summary of the invention
[0005] The embodiments of the present disclosure provide a method and device for constructing a knowledge graph based on a multi-level structured address, so as to at least solve the technical problems existing in the prior art that the data information contained in the knowledge graph is incomplete and cannot accurately and fully represent the association relationship between customers and corresponding addresses.
[0006] According to one aspect of an embodiment of the present disclosure, a method for constructing a knowledge graph based on a multi-level structured address is provided, including: obtaining multiple first business attribute information corresponding to each customer; determining the priority corresponding to the multiple first business attribute information of each customer according to a preset priority classification standard; obtaining multiple target address information related to each customer, and determining the level corresponding to the multiple target address information of each customer according to a preset address level classification standard; determining the second business attribute information corresponding to the multiple target address information of each customer, and matching the multiple second business attribute information of each customer with the multiple first business attribute information of each priority, thereby establishing an association relationship between business attribute information of different priorities and address information of each level; and constructing a knowledge graph based on each customer, the multiple target address information corresponding to each customer, and the association relationship.
[0007] According to another aspect of an embodiment of the present disclosure, a storage medium is further provided, the storage medium including a stored program, wherein when the program is running, a processor executes any one of the methods described above.
[0008] According to another aspect of the embodiments of the present disclosure, there is also provided a knowledge graph construction device based on a multi-level structured address, including: a first business attribute information acquisition module, used to obtain multiple first business attribute information corresponding to each customer; a priority determination module, used to determine the priority corresponding to the multiple first business attribute information of each customer according to a preset priority classification standard; an address level determination module, used to obtain multiple target address information related to each customer, and determine the level corresponding to the multiple target address information of each customer according to a preset address level classification standard; an association relationship establishment module, used to determine the second business attribute information corresponding to the multiple target address information of each customer, and match the multiple second business attribute information of each customer with the multiple first business attribute information of each priority, so as to establish an association relationship between business attribute information of different priorities and address information of each level; and a knowledge graph construction module, used to construct a knowledge graph based on each customer, the multiple target address information corresponding to each customer, and the association relationship.
[0009] According to another aspect of the embodiments of the present disclosure, there is also provided a knowledge graph construction device based on a multi-level structured address, including: a processor; and a memory, connected to the processor, for providing the processor with instructions for processing the following processing steps: obtaining multiple first business attribute information corresponding to each customer respectively; determining the priority corresponding to the multiple first business attribute information of each customer according to a preset priority classification standard; obtaining multiple target address information related to each customer, and determining the level corresponding to the multiple target address information of each customer according to a preset address level classification standard; determining the second business attribute information corresponding to the multiple target address information of each customer respectively, and matching the multiple second business attribute information of each customer with the multiple first business attribute information of each priority, thereby establishing an association relationship between business attribute information of different priorities and address information of each level; and constructing a knowledge graph based on each customer, the multiple target address information corresponding to each customer, and the association relationship.
[0010] The present application discloses a method for constructing a knowledge graph based on a multi-level structured address. First, the processor obtains multiple first business attribute information corresponding to each customer. Then, the processor determines the priority corresponding to the multiple first business attribute information of each customer according to a preset priority classification standard. Further, the processor obtains multiple target address information related to each customer, and determines the level corresponding to the multiple target address information of each customer according to a preset address level classification standard. After that, the processor determines the second business attribute information corresponding to the multiple target address information of each customer, and matches the multiple second business attribute information of each customer with the multiple first business attribute information of each priority, thereby establishing an association relationship between business attribute information of different priorities and address information of each level. Finally, the processor constructs a knowledge graph based on each customer, the multiple target address information corresponding to each customer, and the association relationship.
[0011] Referring to the above content, it can be known that the multiple target address information obtained in this application is not only the customer's registered place information, but all address information associated with the customer. Therefore, the data information contained in the knowledge graph finally constructed is more complete.
[0012] Secondly, from the above content, it can be seen that the present application determines the priority relationship corresponding to multiple first business attribute information of each customer through a pre-set priority classification standard, and also determines the level relationship corresponding to multiple second business attribute information of each customer through a pre-set address level classification standard, wherein the multiple second business attribute information of each customer corresponds to the corresponding target address information respectively.
[0013] Furthermore, after determining the priority relationship corresponding to multiple first business attribute information of each customer and the level relationship corresponding to multiple second business attribute information of each customer, the multiple second business attribute information of each customer is further matched with the multiple first business attribute information of each priority level, so that the address level can be associated with the business priority, and the association relationship between the customer-associated address and the supported business can be determined.
[0014] In summary, the knowledge graph constructed based on each customer, multiple target address information corresponding to each customer, and the association relationship corresponding to each customer can more accurately and fully represent the association relationship between the customer and the corresponding address in a structured and visual manner. This solves the technical problem that the knowledge graph in the prior art contains incomplete data information and cannot accurately and fully represent the association relationship between the customer and the corresponding address. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure. In the drawings:
[0016] Figure 1 is a hardware structure block diagram of a computing device for implementing the method according to Embodiment 1 of the present application;
[0017] Figure 2 It is a schematic diagram of a knowledge graph construction system based on a multi-level structured address according to Example 1 of the present application;
[0018] Figure 3 It is a flowchart of the method for constructing a knowledge graph based on a multi-level structured address according to Example 1 of the present application;
[0019] Figure 4 It is a schematic diagram of a knowledge graph construction device based on a multi-level structured address according to Example 2 of the present application;
[0020] Figure 5 It is a schematic diagram of a knowledge graph construction device based on a multi-level structured address as described in Example 3 of the present application. DETAILED DESCRIPTION
[0021] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.
[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.
[0023] Example 1
[0024] According to this embodiment, a method embodiment of constructing a knowledge graph based on a multi-level structured address is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0025] The method embodiment provided in this embodiment can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computing device for implementing a knowledge graph construction method based on a multi-level structured address. Figure 1 As shown, the computing device may include one or more processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory for storing data, a transmission device for communication functions, and an input / output interface. The memory, the transmission device, and the input / output interface are connected to the processor via a bus. In addition, it may also include: a display, a keyboard, and a cursor control device connected to the input / output interface. A person skilled in the art can understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1More or fewer components as shown, or with Figure 1 Different configurations shown.
[0026] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components of the computing device. As involved in the embodiments of the present disclosure, the data processing circuitry acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).
[0027] The memory can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the knowledge graph construction method based on multi-level structured addresses in the embodiment of the present disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the knowledge graph construction method based on multi-level structured addresses of the above-mentioned application is realized. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories can be connected to the computing device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0028] The transmission device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computing device. In one example, the transmission device includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.
[0029] The display may be, for example, a touch screen liquid crystal display (LCD) that may enable a user to interact with a user interface of the computing device.
[0030] It should be noted that, in some optional embodiments, the above Figure 1 The computing device shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware elements and software elements. Figure 1This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computing devices described above.
[0031] Figure 2 Schematic diagram of a knowledge graph construction system based on multi-level structured addresses according to this embodiment. Figure 2 As shown, the system includes: a data acquisition module, a priority division module, a level division module, a matching module and a knowledge graph construction module.
[0032] The data acquisition module obtains multiple first business attribute information corresponding to each customer from the data center. The data acquisition module is also used to obtain multiple target address information related to each customer and second business attribute information corresponding to the corresponding target address information from the data center. The target address information includes, for example, the address information of the customer's registered address, the address information of the customer's equipment, and the location information of the customer's electricity meter. The first business attribute information and the second business attribute information include, for example, the amount of electricity purchased, the frequency of electricity purchase, the scene of electricity use, the electricity bill payment method, and the electricity purchase transaction cycle.
[0033] The priority division module is in communication connection with the data acquisition module, and is used for dividing the priority of the plurality of first business attribute information of each customer according to a preset priority division standard.
[0034] The grading module is in communication with the data acquisition module and is used to grade the multiple target address information of each customer according to a preset address grade classification standard.
[0035] The matching module is communicated with the priority division module and the level division module respectively, and is used to match multiple second business attribute information of each customer with multiple first business attribute information of each priority, and establish an association relationship between the first business attribute information of different priorities of each customer and the address information of each level.
[0036] The knowledge graph construction module is communicatively connected to the matching module, and is used to construct a knowledge graph based on each customer, multiple target address information corresponding to each customer, and the association relationship corresponding to each customer.
[0037] In addition, the system further comprises a service attribute information base, wherein the service attribute information base is respectively connected to the priority division module and the level division module. And the priority division module can determine the first coding information corresponding to the plurality of first service attribute information of each customer based on the service attribute information base. The level division module can determine the second coding information corresponding to the plurality of second service attribute information of each customer based on the service attribute information base.
[0038] In the above operating environment, according to the first aspect of this embodiment, a method for constructing a knowledge graph based on a multi-level structured address is provided. Figure 2 The system implementation shown in . Figure 3 A schematic diagram showing the process of the method is shown in FIG. Figure 3 As shown, the method includes:
[0039] S302: Acquire multiple first business attribute information corresponding to each customer respectively;
[0040] S304: Determine the priority corresponding to the plurality of first business attribute information of each customer according to a preset priority classification standard;
[0041] S306: Acquire multiple target address information related to each customer, and determine the level corresponding to the multiple target address information of each customer according to a preset address level classification standard;
[0042] S308: Determine the second business attribute information corresponding to the multiple target address information of each customer, and match the multiple second business attribute information of each customer with the multiple first business attribute information of each priority level, thereby establishing an association relationship between the first business attribute information of different priorities and the address information of each level; and
[0043] S310: Construct a knowledge graph based on each customer, multiple target address information corresponding to each customer, and the association relationship corresponding to each customer.
[0044] Specifically, first, the data collection module obtains multiple first business attribute information corresponding to each customer (S302). The data collection module can, for example, collect multiple first business attribute information corresponding to each customer from the data center. And the first business attribute information includes the amount of electricity purchased, the frequency of electricity purchase, the electricity usage scenario, the electricity payment method, and the electricity purchase transaction cycle.
[0045] For example, the data collection module obtains multiple first business attribute information corresponding to customer 1 Multiple first business attribute information corresponding to customer 2 Multiple first business attribute information corresponding to customer 3 Multiple first business attribute information corresponding to customer n
[0046] It is worth noting that the above example uses the same number of first business attribute information corresponding to each customer collected by the data acquisition module. Those skilled in the art should note that the number of first business attribute information corresponding to each customer collected by the data acquisition module may be different, which will not be elaborated here.
[0047] Then, the data collection module sends the multiple first business attribute information corresponding to each customer to the priority division module, so that the priority division module determines the priority corresponding to the multiple first business attribute information of each customer according to the preset priority division standard (S304). Among them, a preset priority comparison table is set in the priority division module. Table 1 shows the priority comparison table.
[0048] Table 1
[0049]
[0050] As shown in reference table 1, the priority comparison table shows the priority corresponding to each service attribute information. For example, service attribute information 1, service attribute information 3 and service attribute information 5 correspond to priority 1, service attribute information 1 and service attribute information 6 correspond to priority 2, and service attribute information 4 and service attribute information 7 correspond to priority 3.
[0051] Therefore, when the priority division module receives multiple first service attribute information corresponding to each customer, the priority corresponding to the multiple first service attribute information of each customer can be determined respectively. And wherein, the first business attribute information Corresponding to the service attribute information 2, the priority division module can determine the first service attribute information of customer 1 Corresponding to priority 2; first service attribute information Corresponding to business attribute information 1, the priority division module can determine the first business attribute information of customer 1 Corresponding to priority 1. Similarly, the priority division module can determine the first business attribute information related to customer 1 The corresponding priority.
[0052] Therefore, based on the same method as above, the priority classification module can determine the priorities respectively corresponding to the multiple first service attribute information of customers 2 to n.
[0053] At the same time, the data collection module obtains multiple target address information related to each customer, and determines the level corresponding to the multiple target address information of each customer according to the preset address level classification standard (S306). The data collection module can, for example, collect multiple target address information related to each customer from the data center. And the target address information includes, for example, the address information of the customer's registration, the address information of the customer's equipment, and the location information of the customer's electric meter.
[0054] For example, the data collection module obtains multiple target address information corresponding to customer 1 Multiple target address information corresponding to customer 2 Multiple target address information corresponding to customer 3 Multiple target address information corresponding to customer n
[0055] It is worth noting that the above example uses the same number of target address information corresponding to each customer collected by the data collection module. Those skilled in the art should note that the number of target address information corresponding to each customer collected by the data collection module may be different, which will not be elaborated here.
[0056] Then, the data collection module sends the multiple target address information corresponding to each customer to the level classification module, so that the level classification module determines the level corresponding to the multiple target address information of each customer according to the preset address level classification standard. Among them, the level classification module is provided with a preset level comparison table. Table 2 shows the level comparison table.
[0057] Table 2
[0058] Level 1 Address information 2 Address information 5 Address information 4 ... Level 2 Address information 1 Address information7 ... Level 3 Address information 3 Address Information6 ...
[0059] As shown in Table 2, the level comparison table shows the priority corresponding to each address information. For example, address information 2, address information 5 and address information 4 correspond to level 1, address information 1 and address information 7 correspond to level 2, and address information 3 and address information 6 correspond to level 3.
[0060] Thus, when the level classification module receives multiple target address information corresponding to each customer, the level corresponding to the multiple target address information of each customer can be determined respectively.
[0061] And the target address information Corresponding to address information 2, the grading module can determine the target address information of customer 1 Corresponds to level 1; target address information Corresponding to address information 1, the grading module can determine the target address information of customer 1 Corresponding to level 1. Similarly, the prioritization module can determine the target address information of customer 1 The corresponding level.
[0062] Therefore, based on the same method as above, the grade classification module can determine the grades corresponding to the target address information of customers 2 to n respectively.
[0063] Then, the matching module determines the second business attribute information corresponding to the multiple target address information of each customer, and matches the multiple second business attribute information of each customer with the multiple first business attribute information of each priority, thereby establishing the association relationship between the first business attribute information of different priorities and the address information of each level (S308). Specifically, first, the allocation module receives the second business attribute information corresponding to the multiple target address information of each customer sent by the level division module. For example, customer 1 corresponds to multiple target address information And with the target address information The corresponding target address has the corresponding second service attribute information With target address information The corresponding target address has the corresponding second service attribute information With target address information The corresponding target address has the corresponding second service attribute information And so on; with the target address information The corresponding target address has the corresponding second service attribute information
[0064] Therefore, based on the same method as above, the second business attribute information of multiple target address information corresponding to customers 2-n can be determined.
[0065] Furthermore, when determining the second business attribute information corresponding to the multiple target address information of each customer, the multiple second business attribute information of each customer is matched with the multiple first business attribute information of each priority. Specifically, since the multiple first business attribute information corresponding to each customer has its own priority, the multiple first business attribute information and priority corresponding to each customer can be expressed as: customer-first business attribute information-priority. Similarly, since the multiple second attribute information corresponding to the multiple target address information of each customer has its own level, the multiple second business attribute information and level corresponding to each customer can be expressed as: customer-target address information-level-second business attribute information.
[0066] For example, customer 1 has multiple first business attribute information And the first business attribute information Corresponding to priority 2. Therefore, the association relationship between the first business attribute information and the priority can be expressed as: Customer 1 - first business attribute information —Priority 2. Similarly, customer 1 has multiple target address information And the target address information Corresponds to level 1, with target address information The corresponding target address has the corresponding second service attribute information Therefore, the association relationship between the target address information and the level and the second business attribute information can be expressed as: Customer 1 - target address information —Level 1—Second service attribute information
[0067] The matching module performs matching based on the above two association relationships. Specifically, first, the matching module determines the first coding information corresponding to the multiple first business attribute information of each customer. Then, the matching module determines the second coding information corresponding to the multiple second business attribute information of each customer. Finally, the matching module matches the first coding information corresponding to the multiple first business attribute information of each customer and the second coding information corresponding to the multiple second business attribute information of each customer, and establishes an association relationship. The above content will be described in detail later, so it will not be repeated here.
[0068] Finally, the matching module constructs a knowledge graph of multi-level structured addresses using the customer information corresponding to each customer, the multiple target address information corresponding to each customer, and the association relationship corresponding to each customer (S310).
[0069] As described in the background technology, for the customer information knowledge graph of the power industry, on the one hand, since the existing knowledge graph only contains address information corresponding to the customer's registered address, and does not contain other address information associated with the customer (for example, the address information of the equipment used by the customer and the address information of the customer's electricity meter, etc.), the data information contained in the knowledge graph is incomplete and cannot accurately represent the relationship between the customer and the corresponding address. On the other hand, for customers, since the supported business priorities are different and the corresponding address information levels are also different, the knowledge graph finally constructed needs to be able to fully represent the relationship between addresses at all levels and businesses of different priorities.
[0070] In view of this, the present application provides a method for constructing a knowledge graph based on a multi-level structured address. And referring to the above content, it can be seen that the multiple target address information obtained in the present application is not only the customer's registered place information, but all address information associated with the customer. Therefore, the data information contained in the knowledge graph finally constructed is more complete.
[0071] Secondly, from the above content, it can be seen that the present application determines the priority relationship corresponding to multiple first business attribute information of each customer through a pre-set priority classification standard, and also determines the level relationship corresponding to multiple second business attribute information of each customer through a pre-set address level classification standard, wherein the multiple second business attribute information of each customer corresponds to the corresponding target address information respectively.
[0072] Furthermore, after determining the priority relationship corresponding to multiple first business attribute information of each customer and the level relationship corresponding to multiple second business attribute information of each customer, the multiple second business attribute information of each customer is further matched with the multiple first business attribute information of each priority level, so that the address level can be associated with the business priority, and the association relationship between the customer-associated address and the supported business can be determined.
[0073] In summary, the knowledge graph constructed based on each customer, multiple target address information corresponding to each customer, and the association relationship corresponding to each customer can more accurately and fully represent the association relationship between the customer and the corresponding address in a structured and visual manner. This solves the technical problem that the knowledge graph in the prior art contains incomplete data information and cannot accurately and fully represent the association relationship between the customer and the corresponding address.
[0074] Optionally, the operation of matching multiple second business attribute information of each customer with multiple first business attribute information of each priority level includes: determining first coding information corresponding to multiple first business attribute information of each customer; determining second coding information corresponding to multiple second business attribute information of each customer; and matching the first coding information corresponding to each first business attribute information and the second coding information corresponding to each second business attribute information, and establishing an association relationship.
[0075] Specifically, refer to Figure 2 As shown, when the priority division module determines the priorities corresponding to the multiple first business attribute information of each customer according to the preset priority division standard, the priority division module determines the first coding information corresponding to the multiple first business attribute information of each customer from the preset business attribute information library. The business attribute information library includes multiple business attribute information samples collected in advance and coding information corresponding to each business attribute information sample.
[0076] For example, the data collection module obtains multiple first business attribute information corresponding to customer 1 And the priority division module determines the first plurality of business attribute information corresponding to customer 1. In the case of a priority level, the priority division module determines from the business attribute information library a plurality of first business attribute information related to customer 1 The first coding information corresponding to each Among them, the first business attribute information of customer 1 The corresponding first coded information is First business attribute information with customer 1 The corresponding first coded information is First business attribute information with customer 1 The corresponding first coded information is
[0077] Thus, based on the same method as above, the priority division module can determine the multiple first business attribute information related to customer 2 The corresponding first coding information
[0078] And so on.
[0079] The priority division module can determine multiple first business attribute information related to customer n The corresponding first coding information
[0080] When the grading module determines the grades corresponding to multiple target address information of each customer according to a preset address grading standard, the grading module determines second coding information corresponding to multiple second business attribute information of each customer from a preset business attribute information library.
[0081] For example, the data collection module obtains multiple target address information corresponding to customer 1 And with the target address information The corresponding target address has the corresponding second service attribute information With target address information The corresponding target address has the corresponding second service attribute information With target address information The corresponding target address has the corresponding second service attribute information And so on; with the target address information The corresponding target address has the corresponding second service attribute information
[0082] The classification module then determines the target address information from the business attribute information database. Multiple second business attribute information The corresponding second attribute information Among them, the target address information Second business attribute information The corresponding second coded information is With target address information Second business attribute information The corresponding second coded information is With target address information Second business attribute information The corresponding second coded information is
[0083] Thus, based on the same method as above, the level classification module can determine the target address information Multiple second business attribute information Corresponding second attribute information
[0084] And so on.
[0085] The classification module can determine the target address information Multiple second business attribute information The corresponding first coding information
[0086] It is worth noting that the above is taken as an example of customer 1, and the method for determining the multiple second coding information corresponding to the multiple second service attribute information of customers 2 to n is the same as above.
[0087] Therefore, when the priority division module determines the first coding information corresponding to the multiple first business attribute information of each customer, the first coding information corresponding to the multiple first business attribute information of each priority can be further determined.
[0088] For example, multiple first business attribute information corresponding to customer 1 And the priority division module determines the first service attribute information Then, the priority division module can determine the first service attribute information Corresponding to priority 1, first service attribute information Corresponding to priority 1, first service attribute information Corresponding to priority 1, first service attribute information Corresponding to priority 2, first service attribute information Corresponding to priority 2. Thus, the priority division module can determine the multiple first service attribute information corresponding to priority 1 Multiple first service attribute information corresponding to priority 2
[0089] Thus, referring to the same method as above, the priority classification module can determine the first service attribute information corresponding to each priority.
[0090] When determining the first service attribute information corresponding to each priority, the priority division module may associate the first coding information corresponding to each first service attribute information determined above with the first service attribute information corresponding to each priority, thereby determining the first coding information corresponding to the first service attribute information of each priority. —First coded information Priority 2—First business attribute information —First coded information
[0091]
[0092] Similarly, when the level classification module determines the second coding information corresponding to the multiple second business attribute information of each customer, the second coding information corresponding to the multiple second business attribute information of each level can be further determined.
[0093] For example, multiple target address information corresponding to customer 1 And the classification module determines the information of each target address The corresponding level. Then, the level classification module can determine the target address information Corresponding to level 2, target address information Corresponding to level 2, target address information Corresponding to level 2, target address information Corresponding to level 1, target address information Corresponding to level 1. Thus, the level classification module can determine multiple target address information corresponding to level 2 Multiple target address information corresponding to level 1
[0094] Thus, referring to the same manner as described above, the level classification module can determine the target address information corresponding to each level.
[0095] Therefore, when determining the target address information corresponding to each level, the level classification module can associate the second coding information corresponding to each second service attribute information determined above with the target address information corresponding to each level, thereby determining the second coding information corresponding to the second service attribute information of the target address information of each level. —Second service attribute information - Second coded information Level 1—Target address information —Second service attribute information - Second coded information Level 2 - Target Address Information —Second service attribute information - Second coded information Level 2 - Target Address Information —Second service attribute information - Second coded information Level 2 - Target Address Information —Second service attribute information - Second coded information
[0096] Finally, the matching module matches the first coding information corresponding to the multiple first business attribute information of each customer with the multiple second business attribute information of each customer, thereby establishing an association relationship between the first business attribute information of different priorities and the address information of each level.
[0097] For example, if the target address information The second business attribute The corresponding second coding information and, with the first business attribute information The corresponding first coding information If it matches, it indicates the target address information of level 1 The weight value of corresponds to the weight value of priority 1.
[0098] Thus, by establishing the association relationship between the first business attribute information of different priorities and the address information of each level, the technical effect of being able to highlight the association relationship between the first business attribute information of each customer and the address information of each level in a hierarchical manner and ultimately improving the applicability and accuracy of the constructed knowledge graph is achieved.
[0099] Optionally, the operation of determining the first coding information corresponding to the multiple first business attribute information of each customer includes: collecting multiple business attribute information samples and constructing a business attribute information library, wherein each business attribute information sample contains corresponding coding information; and matching the multiple first business attribute information corresponding to each customer with the multiple business attribute information samples in the business attribute information library, and determining the first coding information corresponding to the multiple first business attribute information of each customer. Further optionally, the operation of determining the second coding information corresponding to the multiple second business attribute information of each customer includes: matching the multiple second business attribute information corresponding to each customer with the multiple business attribute information samples in the business attribute information library, and determining the second coding information corresponding to the multiple second business attribute information of each customer.
[0100] Specifically, before the priority division module determines the first coding information corresponding to the plurality of first business attribute information of each customer, the data collection module also needs to pre-build a business attribute information library.
[0101] First, the data collection module collects multiple business attribute information samples and builds a business attribute information library. The business attribute information samples include, for example, the amount of electricity purchased, the frequency of electricity purchased, the electricity usage scenario, the electricity bill payment method, the electricity purchase transaction cycle, the meter model used, and the number of meters used.
[0102] And for each business attribute information sample, the data collection module can also encode it using the pre-trained BERT model, so as to generate encoding information corresponding to each business attribute information sample. For example, for business attribute information sample 1, the data collection module can input it into the BERT model, so as to generate encoding information 1 corresponding to business attribute information sample 1. The encoding information can be, for example, the mean vector obtained by averaging the word vector sequence corresponding to the text of business attribute information sample 1.
[0103] Therefore, the data collection module can encode each service attribute information sample in the same manner as above, and then obtain the encoding information corresponding to each service attribute information sample.
[0104] Afterwards, when the priority division module has determined multiple first business attribute information corresponding to each customer 1~n, the multiple first business attribute information corresponding to each customer 1~n are matched with multiple business attribute information samples in the business attribute information library respectively, so as to determine the first coding information corresponding to the multiple first business attribute information of each customer.
[0105] Similarly, when the level classification module determines multiple second business attribute information corresponding to each customer 1~n, the multiple second business attribute information corresponding to each customer 1~n will be matched with multiple business attribute information samples in the business attribute information library respectively, so as to determine the second coding information corresponding to the multiple second business attribute information of each customer.
[0106] Therefore, according to the first aspect of this embodiment, the association relationship between customers and corresponding addresses can be accurately and fully represented, and the applicability and accuracy of the constructed knowledge graph can be improved.
[0107] In addition, reference Figure 1 As shown, according to the second aspect of this embodiment, a storage medium is provided, wherein the storage medium includes a stored program, wherein when the program is run, a processor executes any one of the above methods.
[0108] Therefore, according to this embodiment, the association relationship between customers and corresponding addresses can be accurately and fully represented, and the applicability and accuracy of the constructed knowledge graph can be improved.
[0109] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.
[0110] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.
[0111] Example 2
[0112] Figure 4 The knowledge graph device 400 based on multi-level structured addresses according to this embodiment is shown, and the device 400 corresponds to the method according to embodiment 1. Figure 4As shown, the device 400 includes: a first business attribute information acquisition module 410, used to acquire multiple first business attribute information corresponding to each customer; a priority determination module 420, used to determine the priority corresponding to the multiple first business attribute information of each customer according to a preset priority classification standard; an address level determination module 430, used to acquire multiple target address information related to each customer, and determine the level corresponding to the multiple target address information of each customer according to a preset address level classification standard; an association relationship establishment module 440, used to determine the second business attribute information corresponding to the multiple target address information of each customer, and match the multiple second business attribute information of each customer with the multiple first business attribute information of each priority, so as to establish an association relationship between the business attribute information of different priorities and the address information of each level; and a knowledge graph construction module 450, used to construct a knowledge graph based on each customer, the multiple target address information corresponding to each customer, and the association relationship.
[0113] Optionally, the association relationship establishment 440 module includes: a first coding information determination module, used to determine the first coding information corresponding to multiple first business attribute information of each customer; a second coding information determination module, used to determine the second coding information corresponding to multiple second business attribute information of each customer; and a first matching module, used to match the first coding information corresponding to each of the multiple first business attribute information and the second coding information corresponding to each of the multiple second business attribute information, and establish an association relationship.
[0114] Optionally, the first coding information determination module includes: an information library construction module, used to collect multiple business attribute information samples and construct a business attribute information library, wherein each business attribute information sample contains corresponding coding information; and a second matching module, used to match multiple first business attribute information corresponding to each customer with multiple business attribute information samples in the business attribute information library, and determine the first coding information corresponding to the multiple first business attribute information of each customer.
[0115] Optionally, the second coding information determination module includes: a third matching module, used to match multiple second business attribute information corresponding to each customer with multiple business attribute information samples in the business attribute information library, and determine the second coding information corresponding to the multiple second business attribute information of each customer.
[0116] Therefore, according to this embodiment, the association relationship between customers and corresponding addresses can be accurately and fully represented, and the applicability and accuracy of the constructed knowledge graph can be improved.
[0117] Example 3
[0118] Figure 5 The apparatus 500 for constructing a knowledge graph based on a multi-level structured address according to the embodiment 1 is shown. The apparatus 500 corresponds to the method according to the embodiment 1. Figure 5 As shown, the device 500 includes: a processor 510; and a memory 520, which is connected to the processor 510 and is used to provide the processor 510 with instructions for processing the following processing steps: obtaining multiple first business attribute information corresponding to each customer respectively; determining the priority corresponding to the multiple first business attribute information of each customer according to a preset priority classification standard; obtaining multiple target address information related to each customer, and determining the level corresponding to the multiple target address information of each customer according to a preset address level classification standard; determining the second business attribute information corresponding to the multiple target address information of each customer respectively, and matching the multiple second business attribute information of each customer with the multiple first business attribute information of each priority, thereby establishing an association relationship between business attribute information of different priorities and address information of each level; and constructing a knowledge graph based on each customer, the multiple target address information corresponding to each customer, and the association relationship.
[0119] Optionally, the operation of matching multiple second business attribute information of each customer with multiple first business attribute information of each priority level includes: determining first coding information corresponding to the multiple first business attribute information of each customer; determining second coding information corresponding to the multiple second business attribute information of each customer; and matching the first coding information corresponding to each of the multiple first business attribute information and the second coding information corresponding to each of the multiple second business attribute information, and establishing an association relationship.
[0120] Optionally, the operation of determining the first coding information corresponding to multiple first business attribute information of each customer includes: collecting multiple business attribute information samples and constructing a business attribute information library, wherein each business attribute information sample contains corresponding coding information; and matching the multiple first business attribute information corresponding to each customer with the multiple business attribute information samples in the business attribute information library, and determining the first coding information corresponding to the multiple first business attribute information of each customer.
[0121] Optionally, the operation of determining the second coding information corresponding to multiple second business attribute information of each customer includes: matching the multiple second business attribute information corresponding to each customer with multiple business attribute information samples in the business attribute information library, and determining the second coding information corresponding to the multiple second business attribute information of each customer.
[0122] Therefore, according to this embodiment, the association relationship between customers and corresponding addresses can be accurately and fully represented, and the applicability and accuracy of the constructed knowledge graph can be improved.
[0123] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0124] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0125] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.
[0126] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0127] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0128] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
[0129] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A method for constructing a knowledge graph based on a multi-level structured address, characterized in that: include: Acquire a plurality of first business attribute information respectively corresponding to each customer; Determining priorities corresponding to the plurality of first business attribute information of each customer according to a preset priority classification standard; Acquire multiple target address information related to each of the customers, and determine the grades corresponding to the multiple target address information of each of the customers according to a preset address grade classification standard; Determine the second business attribute information corresponding to the multiple target address information of each customer, and match the multiple second business attribute information of each customer with the multiple first business attribute information of each priority level, so as to establish an association relationship between the first business attribute information of different priorities and the address information of each level; as well as A knowledge graph is constructed based on the various customers, multiple target address information corresponding to the various customers, and association relationships corresponding to the various customers.
2. The method according to claim 1, characterized in that The operation of matching the plurality of second business attribute information of each customer with the plurality of first business attribute information of each priority level includes: Determine first coding information corresponding to the plurality of first business attribute information of each of the customers respectively; Determine second coding information corresponding to the plurality of second service attribute information of the respective customers; and The first coding information corresponding to each piece of first service attribute information and the second coding information corresponding to each piece of second service attribute information are matched, and the association relationship is established.
3. The method according to claim 2, characterized in that The operation of determining first coding information corresponding to the plurality of first service attribute information of the respective customers includes: Collecting multiple service attribute information samples and constructing a service attribute information library, wherein each service attribute information sample includes corresponding coding information; and The multiple first business attribute information corresponding to the respective customers are matched with the multiple business attribute information samples in the business attribute information library, and the first coding information corresponding to the multiple first business attribute information of the respective customers is determined.
4. The method according to claim 3, characterized in that The operation of determining the second coding information corresponding to the plurality of second service attribute information of the respective customers includes: The plurality of second business attribute information corresponding to the respective customers are matched with the plurality of business attribute information samples in the business attribute information library, and second coding information corresponding to the plurality of second business attribute information of the respective customers is determined.
5. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is run, the processor executes the method according to any one of claims 1 to 4.
6. A knowledge graph construction device based on multi-level structured addresses, characterized in that: include: A first business attribute information acquisition module, used to acquire a plurality of first business attribute information corresponding to each customer; A priority determination module, used to determine the priorities corresponding to the plurality of first business attribute information of each customer according to a preset priority classification standard; An address grade determination module, used to obtain multiple target address information related to each of the customers, and determine the grades corresponding to the multiple target address information of each of the customers according to a preset address grade classification standard; an association relationship establishing module, used for determining the second business attribute information corresponding to the multiple target address information of each customer, and matching the multiple second business attribute information of each customer with the multiple first business attribute information of each priority, thereby establishing an association relationship between the business attribute information of different priorities and the address information of each level; as well as The knowledge graph construction module is used to construct a knowledge graph based on the various customers, the multiple target address information corresponding to the various customers, and the association relationships.
7. The device according to claim 6, characterized in that The module for establishing association relationships includes: A first coding information determination module, used to determine first coding information corresponding to a plurality of first business attribute information of each customer; A second coding information determination module, used to determine second coding information corresponding to a plurality of second business attribute information of each customer respectively; and The first matching module is used to match the first coding information corresponding to each piece of first service attribute information and the second coding information corresponding to each piece of second service attribute information, and establish the association relationship.
8. The device according to claim 7, characterized in that The first coding information determination module includes: An information base construction module, used to collect multiple business attribute information samples and construct a business attribute information base, wherein each business attribute information sample contains corresponding coding information; and The second matching module is used to match the multiple first business attribute information corresponding to the respective customers with the multiple business attribute information samples in the business attribute information library, and determine the first coding information corresponding to the multiple first business attribute information of the respective customers.
9. The device according to claim 8, characterized in that The second coding information determination module includes: The third matching module is used to match the multiple second business attribute information corresponding to the respective customers with the multiple business attribute information samples in the business attribute information library, and determine the second coding information corresponding to the multiple second business attribute information of the respective customers.
10. A knowledge graph construction device based on multi-level structured addresses, characterized in that: include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: Acquire a plurality of first business attribute information respectively corresponding to each customer; Determining priorities corresponding to the plurality of first business attribute information of each customer according to a preset priority classification standard; Acquire multiple target address information related to each of the customers, and determine the grades corresponding to the multiple target address information of each of the customers according to a preset address grade classification standard; Determine the second business attribute information corresponding to the multiple target address information of each customer, and match the multiple second business attribute information of each customer with the multiple first business attribute information of each priority, so as to establish an association relationship between the business attribute information of different priorities and the address information of each level; as well as A knowledge graph is constructed based on the various customers, the multiple target address information corresponding to the various customers, and the association relationships.