Electricity handling data auditing method and device based on knowledge graph, equipment and medium

Abstract

The invention relates to the technical field of electricity marketing, and discloses a knowledge graph-based electricity handling data auditing method, which comprises the following steps of: acquiring customer data of a customer to be handled, and judging whether the customer data is text data or image data; if the customer data is literal data, directly obtaining the literal data from the literal data to obtain power handling data; if the customer data are image data, character data in the image data are obtained through optical character recognition, and power handling data are obtained; acquiring preset historical electricity handling data, and constructing an electricity handling data graph according to the historical electricity handling data; and extracting the features of the power handling object in the power handling data to obtain the features of the power handling data, analyzing the features of the power handling data through the power handling data atlas, and auditing the power handling data to obtain an auditing result. The invention further provides an electricity handling data auditing device and equipment based on the knowledge graph and a storage medium. According to the invention, the development speed of the electricity handling service can be improved, and the auditing speed of the electricity handling data is improved.

Description

Technical Field

[0001] The present invention relates to the field of power marketing technology, and in particular to a method, device, equipment and medium for reviewing power application materials based on a knowledge graph. Background Art

[0002] In recent years, with the continuous increase in the number of power users within the service scope of power companies, a large amount of data related to power services has been accumulated. And with the improvement of power services, the existing power services processing speed is low, which brings a bad service experience to users, and due to the long processing cycle of power services, it brings considerable inconvenience to users' production and life.

[0003] However, the existing electricity application business is still in the manual stage and cannot give full play to the advantages of relevant data obtained in the electricity application service. Therefore, there is an urgent need for an intelligent automatic review method for electricity application information, focusing on the scenario of electricity application information review, and quickly identifying whether the electricity application information is complete and correct, so as to solve the problem of slow review of electricity application information. Summary of the invention

[0004] The present invention provides a method, device, equipment and medium for reviewing electricity application documents based on knowledge graph, the main purpose of which is to improve the review speed of electricity application documents.

[0005] To achieve the above purpose, the present invention provides a method for reviewing electricity application materials based on knowledge graph, comprising:

[0006] Obtaining customer information of the customer to be connected to the service, and determining whether the customer information is text information or image information;

[0007] If the customer information is text information, then directly obtain text data from the text information to obtain the electricity application data;

[0008] If the customer information is image information, the text data in the image information is obtained by optical character recognition to obtain the electricity application data;

[0009] Obtaining preset historical power supply data, and constructing a power supply data map based on the historical power supply data;

[0010] The electricity application object features in the electricity application data are extracted to obtain the electricity application data features, and the electricity application data features are analyzed through the electricity application data map, and the electricity application data is audited to obtain the audit results.

[0011] Optionally, the acquiring text data in the image data by optical character recognition to obtain electricity application data includes:

[0012] Gray-scaling, binarization and denoising are performed on the image data, and tilt correction is performed to obtain standard image data;

[0013] Detecting the text portion in the standard image data by a texture feature detection method to obtain a detected text area;

[0014] The characters in the detected character area are recognized by optical character recognition to obtain electricity processing data.

[0015] Optionally, the detecting the text portion in the standard image data by a texture feature detection method to obtain a detected text area includes:

[0016] Extract features from the standard image data through a pre-trained VGG16 model to obtain a power supply feature map;

[0017] By setting a sliding window on the power supply feature map and extracting a feature vector through the sliding window, a power supply feature vector is obtained;

[0018] Inputting the electricity-handling feature vector into a bidirectional long short-term memory network and processing it to obtain an electricity-handling feature relationship;

[0019] Based on the preset output layer, the initial text detection area is obtained according to the power supply feature vector and the power supply feature relationship, and the repeated detection areas are removed by non-maximum suppression to obtain the detected text area.

[0020] Optionally, constructing a power supply data map according to the historical power supply data includes:

[0021] Performing dimension reduction and clustering on the historical electricity application data to obtain a cluster distribution of the electricity application data;

[0022] By extracting the electricity service field terms from the cluster distribution of the electricity service data, a term list of the electricity service field is obtained;

[0023] Constructing a word embedding model word2vec, and performing feature extraction and fusion on the term list in the power supply field through the word embedding model word2vec to obtain a power supply word embedding matrix;

[0024] The electricity service term embedding matrix is ​​subjected to dimensionality reduction and clustering to obtain a cluster distribution of electricity service terminology, and an electricity service data map is constructed through the cluster distribution of electricity service terminology.

[0025] Optionally, extracting the electricity application object features in the electricity application data to obtain the electricity application data features includes:

[0026] Performing word segmentation processing on the electricity application data to obtain a plurality of electricity application words;

[0027] By performing word vector mapping on the electricity application word, a word vector matrix corresponding to the electricity application word is obtained, and the word vector matrix is ​​used as the electricity application data feature.

[0028] Optionally, analyzing the characteristics of the electricity application data through the electricity application data map, reviewing the electricity application data, and obtaining the review result includes:

[0029] Calculate the shortest distance between two points in the power supply data map to obtain the power supply distance:

[0030] Based on the electricity service distance, the number of shortest paths passing through a certain point is calculated using the betweenness centrality algorithm, and the importance of the node is calculated using the PageRank algorithm to obtain the relationship between the electricity service data features;

[0031] The electricity application data is reviewed based on the relationship between the electricity application characteristics to obtain a review result.

[0032] Optionally, the determining whether the customer information is text information or image information includes:

[0033] The data format of the customer information is obtained, and according to the data format, it is determined whether the customer information is text information or image information.

[0034] In order to solve the above problems, the present invention also provides a device for reviewing electricity application materials based on a knowledge graph, the device comprising:

[0035] The data acquisition module is used to acquire the customer data of the customer waiting for electricity service and determine whether the customer data is text data or image data;

[0036] A data extraction module, for obtaining text data directly from the text data to obtain electricity application data if the customer information is text information; and for obtaining text data in the image data by optical character recognition to obtain electricity application data if the customer information is image information;

[0037] A graph construction module is used to obtain preset historical power supply data and construct a power supply data graph based on the historical power supply data;

[0038] The audit analysis module is used to extract the electricity application object characteristics in the electricity application data, obtain the electricity application data characteristics, and analyze the electricity application data characteristics through the electricity application data map, audit the electricity application data, and obtain the audit results.

[0039] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0040] at least one processor; and,

[0041] a memory communicatively connected to the at least one processor; wherein,

[0042] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the electricity application document review method based on the knowledge graph as described above.

[0043] In order to solve the above problems, the present invention also provides a computer-readable storage medium, including a data storage area and a program storage area, the data storage area stores created data, and the program storage area stores a computer program; wherein, when the computer program is executed by a processor, the electricity application information review method based on the knowledge graph as described above is implemented.

[0044] The embodiment of the present invention obtains the customer information of the customer who is waiting to apply for electricity, and determines whether the customer information is text information or image information; if the customer information is text information, directly obtains the text data from the text information to obtain the electricity application data; if the customer information is image information, obtains the text data in the image information through optical character recognition to obtain the electricity application data; obtains the preset historical electricity application data, and constructs an electricity application data map based on the historical electricity application data; extracts the electricity application object features in the electricity application data to obtain the electricity application data features, and analyzes the electricity application data features through the electricity application data map, reviews the electricity application data, and obtains the review results. Therefore, the electricity application data review method, device, electronic device and computer-readable storage medium based on the knowledge graph proposed in the present invention fully mine the available components in the historical electricity application service related data, construct a knowledge graph, analyze the data review in the subsequent electricity application business, and improve the review speed of the electricity application data. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A schematic diagram of a flow chart of a method for reviewing electricity application materials based on a knowledge graph provided in one embodiment of the present invention;

[0046] Figure 2 A schematic diagram of a module of a knowledge graph-based electricity application information review device provided by an embodiment of the present invention;

[0047] Figure 3 A schematic diagram of the internal structure of an electronic device for implementing a method for reviewing electricity application materials based on a knowledge graph provided in one embodiment of the present invention.

[0048] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0050] The embodiment of the present application provides a method for reviewing electricity application materials based on a knowledge graph. The execution subject of the method for reviewing electricity application materials based on a knowledge graph includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. Among them, the server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms. In other words, the method for reviewing electricity application materials based on a knowledge graph can be executed by software or hardware installed on a remote device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0051] Reference Figure 1 As shown, it is a flow chart of a method for reviewing electricity application materials based on a knowledge graph provided by an embodiment of the present invention. In this embodiment, the method for reviewing electricity application materials based on a knowledge graph includes the following steps S1-S5:

[0052] S1. Obtain customer information of a customer who is waiting to make an order, and determine whether the customer information is text information or image information.

[0053] In the embodiment of the present invention, the pending electricity customers refer to customers who have submitted electricity applications but have not completed all electricity application procedures and are waiting for the power supply company to provide them with electricity access services. The pending electricity customers may communicate with the power supply company regularly to understand the progress of the electricity application and solve the problems encountered in the electricity application process to ensure that the electricity application process is completed as soon as possible and electricity is started. With the digital transformation of power services, many power companies provide online inquiry and progress update services, so that pending electricity customers can more conveniently track their application status.

[0054] In the embodiment of the present invention, the customer information of the pending electricity customer refers to a series of documents and information that need to be submitted to the power supply enterprise or relevant management department when applying for power supply or carrying out power facility construction. These materials are used to prove the identity of the applicant, the power demand, the legitimacy of the power address, and compliance with relevant power supply and safety regulations.

[0055] Furthermore, the specific materials that need to be submitted may include but are not limited to valid identification of the electricity user, property rights certificate of the electricity address, electricity application, business license, approval document for electricity engineering project, list of electricity equipment, power of attorney, etc. Among them, the electricity application is used to explain the demand for electricity and the nature of electricity use, and the approval document for the electricity engineering project indicates that the corresponding approval document needs to be provided for the power engineering project.

[0056] In the embodiment of the present invention, the step of determining whether the customer information is text information or image information includes:

[0057] The data format of the customer information is obtained, and according to the data format, it is determined whether the customer information is text information or image information.

[0058] Furthermore, the electricity application form, business license, and list of electricity equipment are usually submitted in the form of text data. The valid identity certificate of the electricity user and the property certificate of the electricity address are usually submitted in the form of image data.

[0059] Among them, since the present invention is used for intelligent online processing, these image data materials are usually converted into electronic image files (such as JPEG, PNG and other formats) by electronic scanning or taking pictures, and then uploaded and submitted through the network platform. As for text data materials, electronic documents can be directly filled in or uploaded in the online system.

[0060] S2. If the customer information is text information, directly obtain text data from the text information to obtain electricity application data.

[0061] In the embodiment of the present invention, it is necessary to determine whether the information submitted by the customer is text information. This may be achieved by checking the data format of the information. For example, documents, PDF, TXT files, etc. usually contain text data. Once it is confirmed that the customer information is in text form, the next step is to extract the text data directly from the text information. This may involve operations such as reading document content and parsing text information.

[0062] In the embodiment of the present invention, when the data is already in text form, the information in the data is directly extracted and used to facilitate the smooth progress of the electricity application process. This step is particularly important in the automated and digitalized electricity application process because it helps reduce the workload of manual data entry and improves the efficiency and accuracy of data processing.

[0063] S3. If the customer information is image information, the text data in the image information is obtained through optical character recognition to obtain the electricity application data.

[0064] In the embodiment of the present invention, the optical character recognition (OCR) is used to automatically recognize and extract printed or handwritten text information from various types of documents (such as scanned paper documents, PDF files, or pictures taken by digital cameras). The OCR technology can convert the text in the image into machine-encoded text, so that the text can be edited, searched, and processed by electronic devices such as computers and smart phones.

[0065] Furthermore, the step of acquiring text data in the image data by optical character recognition to obtain electricity application data includes:

[0066] Gray-scaling, binarization and denoising are performed on the image data, and tilt correction is performed to obtain standard image data;

[0067] Detecting the text portion in the standard image data by a texture feature detection method to obtain a detected text area;

[0068] The characters in the detected character area are recognized by optical character recognition to obtain electricity processing data.

[0069] Furthermore, the detecting of the text part in the standard image data by a texture feature detection method to obtain a detected text area includes:

[0070] Extract features from the standard image data through a pre-trained VGG16 model to obtain a power supply feature map;

[0071] By setting a sliding window on the power supply feature map and extracting a feature vector through the sliding window, a power supply feature vector is obtained;

[0072] Inputting the electricity-handling feature vector into a bidirectional long short-term memory network and processing it to obtain an electricity-handling feature relationship;

[0073] Based on the preset output layer, the initial text detection area is obtained according to the power supply feature vector and the power supply feature relationship, and the repeated detection areas are removed by non-maximum suppression to obtain the detected text area.

[0074] In the embodiment of the present invention, the text information in the image is converted into electronic text by OCR technology so as to be used in the electricity application process. This step is crucial to improve the efficiency of electricity application, reduce manual input errors and speed up information processing.

[0075] S4. Obtain preset historical electricity handling data, and construct an electricity handling data map based on the historical electricity handling data.

[0076] In the embodiment of the present invention, the historical electricity handling data refers to various records and information accumulated in the past when handling electricity business at the power supply enterprise or relevant management department. Such data usually includes customer information, electricity application records, approval process records, construction and installation records, electricity consumption and electricity fee records, service request and fault records, contracts and agreements, etc.

[0077] Among them, the approval process record refers to the approval process of electricity application, including approval time, approval results, approval opinions, etc.; service request and fault records refer to the service requests and fault reports raised by customers and the corresponding processing results.

[0078] Furthermore, these historical data are very valuable resources for power companies. They can be used to analyze customer behavior, optimize service processes, improve service quality, predict future electricity demand and trends, and provide reference and reference for new electricity services. By building an electricity data map, power companies can more effectively manage and utilize these historical data, thereby improving the efficiency and quality of business processing.

[0079] In the embodiment of the present invention, the electricity management data map is a tool used by the power industry to manage and analyze electricity business data during the digital transformation process. It integrates and visualizes various types of data related to electricity business (such as customer information, electricity application, power equipment status, etc.) by constructing a map containing multiple entities and relationships, thereby helping power companies to more efficiently manage electricity business processes, improve service quality, optimize resource allocation, and provide data support for decision-making.

[0080] Furthermore, constructing a power supply data map based on the historical power supply data includes:

[0081] Performing dimension reduction and clustering on the historical electricity application data to obtain a cluster distribution of the electricity application data;

[0082] By extracting the electricity service field terms from the cluster distribution of the electricity service data, a term list of the electricity service field is obtained;

[0083] Constructing a word embedding model word2vec, and performing feature extraction and fusion on the term list in the power supply field through the word embedding model word2vec to obtain a power supply word embedding matrix;

[0084] The electricity service term embedding matrix is ​​subjected to dimensionality reduction and clustering to obtain a cluster distribution of electricity service terminology, and an electricity service data map is constructed through the cluster distribution of electricity service terminology.

[0085] In an embodiment of the present invention, the construction of an electricity management data map provides an efficient data management and analysis tool for the power industry. It integrates and visualizes electricity business data from different sources to support intelligent decision-making, optimize customer service, enhance data security, promote cross-departmental collaboration, and drive business innovation, thereby helping power companies to more efficiently manage electricity business processes, improve service quality, optimize resource allocation, and provide data support for decision-making.

[0086] S5. Extract the electricity application object features in the electricity application data to obtain the electricity application data features, analyze the electricity application data features through the electricity application data map, review the electricity application data, and obtain the review results.

[0087] In the embodiment of the present invention, the electricity application object characteristics generally refer to key information extracted from the materials submitted by the customer during the process of handling electricity business, which can represent the core elements of the customer's electricity application and are used by the power supply enterprise to review, process and provide services. Specifically, the electricity application object characteristics may include customer identity characteristics, electricity demand characteristics, electricity address characteristics, electricity equipment characteristics, electricity behavior characteristics, and electricity project characteristics.

[0088] Among them, electricity demand characteristics refer to the customer's electricity demand, including electricity type (such as residential electricity, commercial electricity, industrial electricity, etc.), electricity capacity, electricity time, etc., which are used to evaluate the feasibility and demand of electricity supply; electricity equipment characteristics refer to the information of electricity equipment that the customer plans to use, such as equipment type, power, quantity, etc., which are used to evaluate power load and power supply plan; electricity behavior characteristics refer to the customer's historical electricity behavior, such as electricity consumption, payment records, electricity stability, etc., which are used to evaluate the customer's electricity consumption credit and demand forecast.

[0089] Furthermore, by extracting these characteristics of electricity service objects, power supply companies can more accurately understand customer needs, review and process electricity services more efficiently, and provide data support for the planning and optimization of power systems. In the automated and digitalized electricity service process, the extraction and analysis of these characteristics are crucial to improving service quality and efficiency.

[0090] In the embodiment of the present invention, the step of extracting the electricity application object features from the electricity application data to obtain the electricity application data features includes:

[0091] Performing word segmentation processing on the electricity application data to obtain a plurality of electricity application words;

[0092] By performing word vector mapping on the electricity application word, a word vector matrix corresponding to the electricity application word is obtained, and the word vector matrix is ​​used as the electricity application data feature.

[0093] In the embodiment of the present invention, the word meaning corresponding to the word vector matrix is ​​used as the electricity application data feature.

[0094] Furthermore, the power application data characteristics are analyzed through the power application data map, the power application data is audited, and the audit result is obtained, including:

[0095] Calculate the shortest distance between two points in the power supply data map to obtain the power supply distance:

[0096] Based on the electricity service distance, the number of shortest paths passing through a certain point is calculated using the betweenness centrality algorithm, and the importance of the node is calculated using the PageRank algorithm to obtain the relationship between the electricity service data features;

[0097] The electricity application data is reviewed based on the relationship between the electricity application characteristics to obtain a review result.

[0098] Specifically, the Betweenness Centrality algorithm is a graph theory method for measuring the importance of nodes in a network. The centrality of a node is determined by calculating the proportion of the shortest paths of all node pairs in the network that pass through a specific node, thereby identifying key "bridge" nodes in the network. The higher the value, the greater the role and influence of the node in the network information flow.

[0099] Specifically, the PageRank algorithm is used to measure the importance or quality of a web page. It scores web pages based on the structure of all hyperlinks on the Internet and the link relationships between web pages. In the embodiment of the present invention, it is used to measure the importance of entities in the power management data map.

[0100] Furthermore, by analyzing the characteristics of the electricity application data through the electricity application data map, it is possible to review whether the electricity application information is complete and whether the customer information is correct, and to immediately remind electricity users who fail the review to make corrections and supplement the correct electricity application information.

[0101] The embodiment of the present invention obtains the customer information of the customer who is waiting to apply for electricity, and determines whether the customer information is text information or image information; if the customer information is text information, directly obtains the text data from the text information to obtain the electricity application data; if the customer information is image information, obtains the text data in the image information through optical character recognition to obtain the electricity application data; obtains the preset historical electricity application data, and constructs an electricity application data graph based on the historical electricity application data; extracts the electricity application object features in the electricity application data to obtain the electricity application data features, and analyzes the electricity application data features through the electricity application data graph, reviews the electricity application data, and obtains the review results. Therefore, the electricity application data review method, device, electronic device and computer-readable storage medium based on the knowledge graph proposed in the present invention fully mine the available components in the historical electricity application service related data, construct a knowledge graph, analyze the data review in the subsequent electricity application business, and improve the review speed of the electricity application data.

[0102] like Figure 2 The figure shows a module diagram of the electricity application information review device based on the knowledge graph of the present invention.

[0103] The power application document review device 100 based on knowledge graph of the present invention can be installed in an electronic device. According to the functions implemented, the power application document review device based on knowledge graph can include a document acquisition module 101, a data extraction module 102, a graph construction module 103 and an audit analysis module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0104] In this embodiment, the functions of each module / unit are as follows:

[0105] The data acquisition module 101 is used to acquire the customer data of the customer waiting for electricity service and determine whether the customer data is text data or image data;

[0106] The data extraction module 102 is used to directly obtain text data from the text data to obtain the electricity application data if the customer information is text information; if the customer information is image information, obtain the text data in the image information through optical character recognition to obtain the electricity application data;

[0107] A graph construction module 103 is used to obtain preset historical power supply data and construct a power supply data graph according to the historical power supply data;

[0108] The audit analysis module 104 is used to extract the electricity application object features in the electricity application data, obtain the electricity application data features, analyze the electricity application data features through the electricity application data map, audit the electricity application data, and obtain the audit results.

[0109] In detail, each module described in the knowledge graph-based electricity application information review device 100 in the embodiment of the present invention is used in the same manner as described above. Figure 1 The above-mentioned electricity application document review method based on knowledge graph has the same technical means and can produce the same technical effects, so it will not be repeated here.

[0110] like Figure 3 The figure is a schematic diagram of the structure of an electronic device that implements the method for reviewing electricity application materials based on knowledge graph according to the present invention.

[0111] The electronic device may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a knowledge graph-based electricity application document review program.

[0112] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (for example, executing a knowledge graph-based electricity application information review program, etc.), and calls the data stored in the memory 11 to execute various functions of the electronic device and process data.

[0113] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 11 may also include both an internal storage unit of the electronic device and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device, such as the code of the electricity application information review program based on the knowledge graph, but also can be used to temporarily store data that has been output or is to be output.

[0114] The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0115] The communication interface 13 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0116] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3The structure shown does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0117] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0118] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0119] The electricity application information review program based on the knowledge graph stored in the memory 11 of the electronic device is a combination of multiple computer programs. When running in the processor 10, it can achieve:

[0120] Obtaining customer information of the customer to be connected to the electricity bill, and determining whether the customer information is text information or image information;

[0121] If the customer information is text information, then directly obtain text data from the text information to obtain the electricity application data;

[0122] If the customer information is image information, then optical character recognition is used to obtain text data in the image information to obtain electricity application data;

[0123] Obtaining preset historical power supply data, and constructing a power supply data map based on the historical power supply data;

[0124] The electricity application object features in the electricity application data are extracted to obtain the electricity application data features, and the electricity application data features are analyzed through the electricity application data map, and the electricity application data is audited to obtain the audit results.

[0125] Specifically, the specific implementation method of the processor 10 for the above computer program can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0126] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0127] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0128] Obtaining customer information of the customer to be connected to the electricity bill, and determining whether the customer information is text information or image information;

[0129] If the customer information is text information, then directly obtain text data from the text information to obtain the electricity application data;

[0130] If the customer information is image information, then optical character recognition is used to obtain text data in the image information to obtain electricity application data;

[0131] Obtaining preset historical power supply data, and constructing a power supply data map based on the historical power supply data;

[0132] The electricity application object features in the electricity application data are extracted to obtain the electricity application data features, and the electricity application data features are analyzed through the electricity application data map, and the electricity application data is audited to obtain the audit results.

[0133] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0134] The modules described as separate components may or may not be physically separated, and the components shown as modules 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 modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, 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 hardware plus software functional modules.

[0136] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0137] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0138] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0139] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0140] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The second and other words are used to indicate names, but not to indicate any particular order.

[0141] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for reviewing electricity application materials based on knowledge graph, characterized in that: The method comprises: Obtaining customer information of the customer to be connected to the service, and determining whether the customer information is text information or image information; If the customer information is text information, then directly obtain text data from the text information to obtain the electricity application data; If the customer information is image information, the text data in the image information is obtained by optical character recognition to obtain the electricity application data; Obtaining preset historical power supply data, and constructing a power supply data map based on the historical power supply data; The electricity application object features in the electricity application data are extracted to obtain the electricity application data features, and the electricity application data features are analyzed through the electricity application data map, and the electricity application data is audited to obtain the audit results.

2. The method for reviewing electricity application materials based on knowledge graph according to claim 1, characterized in that: The step of acquiring text data in the image data by optical character recognition to obtain electricity application data includes: Gray-scaling, binarization and denoising are performed on the image data, and tilt correction is performed to obtain standard image data; Detecting the text portion in the standard image data by a texture feature detection method to obtain a detected text area; The characters in the detected character area are recognized by optical character recognition to obtain electricity processing data.

3. The method for reviewing electricity application materials based on knowledge graph according to claim 2, characterized in that: The method of detecting the text part in the standard image data by using the texture feature detection method to obtain the detected text area includes: Extract features from the standard image data through a pre-trained VGG16 model to obtain a power supply feature map; By setting a sliding window on the power supply feature map and extracting a feature vector through the sliding window, a power supply feature vector is obtained; Inputting the electricity-handling feature vector into a bidirectional long short-term memory network and processing it to obtain an electricity-handling feature relationship; Based on the preset output layer, the initial text detection area is obtained according to the power supply feature vector and the power supply feature relationship, and the repeated detection areas are removed by non-maximum suppression to obtain the detected text area.

4. The method for reviewing electricity application materials based on knowledge graph according to claim 1, characterized in that: The step of constructing a power supply data map according to the historical power supply data includes: Performing dimension reduction and clustering on the historical electricity application data to obtain a cluster distribution of the electricity application data; By extracting the electricity service field terms from the cluster distribution of the electricity service data, a term list of the electricity service field is obtained; Constructing a word embedding model word2vec, and performing feature extraction and fusion on the term list in the power supply field through the word embedding model word2vec to obtain a power supply word embedding matrix; The electricity service term embedding matrix is ​​subjected to dimensionality reduction and clustering to obtain a cluster distribution of electricity service terminology, and an electricity service data map is constructed through the cluster distribution of electricity service terminology.

5. The method for reviewing electricity application materials based on knowledge graph according to claim 1, characterized in that: The extracting the electricity application object features from the electricity application data to obtain the electricity application data features includes: Performing word segmentation processing on the electricity application data to obtain a plurality of electricity application words; By performing word vector mapping on the electricity application word, a word vector matrix corresponding to the electricity application word is obtained, and the word vector matrix is ​​used as the electricity application data feature.

6. The method for reviewing electricity application materials based on knowledge graph according to claim 1, characterized in that: The step of analyzing the characteristics of the power application data through the power application data map, reviewing the power application data, and obtaining the review result includes: Calculate the shortest distance between two points in the power supply data map to obtain the power supply distance: Based on the electricity service distance, the number of shortest paths passing through a certain point is calculated using the betweenness centrality algorithm, and the importance of the node is calculated using the PageRank algorithm to obtain the relationship between the electricity service data features; The electricity application data is reviewed based on the relationship between the electricity application characteristics to obtain a review result.

7. The method for reviewing electricity application materials based on knowledge graph according to any one of claims 1 to 6, characterized in that: The determining whether the customer information is text information or image information includes: The data format of the customer information is obtained, and according to the data format, it is determined whether the customer information is text information or image information.

8. A device for reviewing electricity application materials based on knowledge graph, characterized in that: The device comprises: The data acquisition module is used to acquire the customer data of the customer waiting for electricity service and determine whether the customer data is text data or image data; A data extraction module, for obtaining text data directly from the text data to obtain electricity application data if the customer information is text information; and for obtaining text data in the image data by optical character recognition to obtain electricity application data if the customer information is image information; A graph construction module is used to obtain preset historical power supply data and construct a power supply data graph based on the historical power supply data; The audit analysis module is used to extract the electricity application object characteristics in the electricity application data, obtain the electricity application data characteristics, and analyze the electricity application data characteristics through the electricity application data map, audit the electricity application data, and obtain the audit results.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the electricity application document review method based on knowledge graph as described in any one of claims 1 to 7.

10. A computer-readable storage medium, comprising a data storage area and a program storage area, wherein the data storage area stores created data and the program storage area stores a computer program; wherein: When the computer program is executed by a processor, the knowledge graph-based electricity application document review method as described in any one of claims 1 to 7 is implemented.

Images