Method and system for identifying nameplate label of electric appliance system and electronic equipment

Abstract

The invention provides an electric appliance system nameplate label identification method, system and device and a storage medium. The method comprises the steps that an electric appliance label nameplate is mapped into a digital model; the digital model comprises nameplate component nodes and attribute feature edges; the nameplate component node comprises an identification sub-node and a description sub-node; the attribute feature edges comprise identification attribute edges for identifying child nodes, description attribute edges for describing the child nodes and association attribute edges among nameplate component nodes; selecting a starting node and a target node in the digital model, and extracting a set composed of a plurality of feasible recognition sequences from the minimum recognition sequence; executing attribute simulation for multiple times, generating attribute parameters of attribute feature edges in each feasible recognition sequence according to attribute requirements, and obtaining simulation attributes of each feasible recognition sequence; and taking the optimal feasible identification sequence as an identification result of the electric appliance label nameplate based on the simulation attribute. According to the invention, the accuracy and efficiency of electric appliance label nameplate identification can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of automatic identification technology, and more specifically, to a method and system for identifying nameplate labels of an electrical system, and electronic equipment. Background Art

[0002] In the field of automatic recognition of electrical system nameplates, existing technologies mainly use image recognition and optical character recognition (OCR) technology to achieve this. These technologies take pictures of nameplates and then use image processing algorithms to extract text information. Although these methods have improved recognition efficiency to a certain extent, they still face many challenges in practical applications. For example, they have high requirements for image quality and are sensitive to factors such as lighting conditions and background interference, resulting in unstable recognition accuracy; at the same time, OCR technology is prone to errors when processing complex fonts and blurred handwriting.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: the prior art often lacks sufficient flexibility and accuracy when processing the diverse information on the nameplate, such as model, specification, parameter and function description. In addition, the prior art has a certain dependence on the layout and format of the nameplate. When the nameplate design changes, the model needs to be retrained, which undoubtedly increases the complexity and cost of the technology application. These problems limit the application of automatic identification technology in a wider range of scenarios, especially in a changing industrial environment. Summary of the invention

[0004] The invention provides a method, system, medium and computing equipment for identifying nameplate labels of an electrical system.

[0005] In a first aspect of the present invention, a method for identifying a nameplate label of an electrical system is provided, comprising: Mapping the electrical appliance label nameplate into a digital model; the digital model includes a nameplate component node and an attribute feature edge; the nameplate component node includes an identification subnode and a description subnode; The attribute feature edges include: identification attribute edges of identification subnodes, description attribute edges of description subnodes, and association attribute edges between nameplate component nodes; Selecting a starting node and a target node in the digital model to determine a minimum recognition sequence, and extracting a set consisting of multiple feasible recognition sequences from the minimum recognition sequence based on recognition constraints; Execute multiple attribute simulations. In each simulation, generate attribute parameters of attribute feature edges in each feasible recognition sequence according to attribute requirements, and obtain simulation attributes of each feasible recognition sequence. Based on the simulation attributes, an optimal feasible recognition sequence of the electrical appliance label nameplate is identified, and the optimal feasible recognition sequence is used as a recognition result of the electrical appliance label nameplate.

[0006] Furthermore, the identification sub-node is used to describe the model and specification identification information of the electrical appliance label nameplate; The description sub-node is used to describe the parameters and function description information of the appliance label nameplate.

[0007] Furthermore, the identification attribute edge is used to describe the attributes of the identification subnode processing model and specification identification information; The description attribute edge is used to describe the attributes of the description sub-node processing parameters and function description information; The association attribute edge is used to describe the association relationship and attributes between nameplate component nodes.

[0008] Furthermore, the optimal feasible identification sequence for identifying the nameplate of the electrical appliance includes: For each feasible identification sequence, multiple attribute simulations are performed to obtain simulation attributes, and the attribute expectation and attribute variance of the feasible identification sequence are determined; Determining an attribute evaluation index of a feasible recognition sequence based on the attribute expectation and attribute variance of the recognition sequence; The recognition sequence corresponding to the highest value of the attribute evaluation index is taken as the optimal feasible recognition sequence.

[0009] Furthermore, the attribute evaluation index of each feasible recognition sequence is calculated.

[0010] Furthermore, the identification constraints include identification information integrity constraints, description information accuracy constraints and association attribute consistency constraints.

[0011] Further, extracting a set consisting of multiple feasible recognition sequences from the minimum recognition sequence includes: Acquire real-time data and performance parameters when the electrical appliance label nameplate is mapped to a digital model, wherein the real-time data includes real-time identification information, real-time description information and real-time associated attributes of each nameplate component node, and real-time associated attributes of each edge; The performance parameters include node performance indicators for each nameplate component node; For each recognition sequence in the minimum recognition sequence, determine whether the recognition constraint is satisfied; Extracting recognition sequences that satisfy recognition constraints as feasible recognition sequences; All feasible identification sequences extracted are summarized to form a set.

[0012] Furthermore, judging whether the identification constraint is satisfied includes: If the real-time identification information and real-time description information of each nameplate component node in the current identification sequence are complete, the identification information integrity constraint is satisfied; If the real-time association attribute of each edge in the current recognition sequence meets the preset association rule, the total association attribute of the appliance label nameplate meets the total association rule, and the sum of the association attributes of the current recognition sequence does not exceed the association attribute threshold, then the association attribute consistency constraint is satisfied; If the performance index of each nameplate component node in the current identification sequence meets the performance requirements, and the sum of the performance indexes of all nameplate component nodes meets the overall performance requirements, then the performance index constraint is satisfied; The recognition sequences that satisfy the above constraints are extracted as feasible recognition sequences.

[0013] In a second aspect of the present invention, a system for identifying nameplates and labels of an electrical system is provided, comprising: A digital model generation module, used for mapping the electrical appliance label nameplate into a digital model; the digital model includes a nameplate component node and an attribute feature edge; the nameplate component node includes an identification subnode and a description subnode; the attribute feature edge includes an identification attribute edge of the identification subnode, a description attribute edge of the description subnode, and an association attribute edge between nameplate component nodes; A feasible recognition sequence set determination module is used to select a starting node and a target node in the digital model to determine a minimum recognition sequence, and extract a set from the minimum recognition sequence based on recognition constraints; The attribute simulation module performs multiple attribute simulations, generates attribute parameters of attribute feature edges in each feasible recognition sequence according to attribute requirements in each simulation, and obtains simulation attributes of each feasible recognition sequence; The optimal feasible recognition sequence determination module identifies the optimal feasible recognition sequence of the electrical appliance label nameplate based on the simulation attribute, and uses the sequence as the recognition result of the electrical appliance label nameplate.

[0014] In a third aspect of the present invention, an electronic device is provided, comprising: at least one processor, a memory and an input-output unit; wherein the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute any one of the methods described in the first aspect.

[0015] According to the above embodiments of the present invention, at least the following beneficial effects are achieved: the electrical system nameplate label recognition method of the present invention accurately maps each component node of the nameplate and its attribute feature edges by constructing a digital model, thereby realizing efficient recognition of electrical appliance label nameplates. The method uses attribute simulation technology to simulate feasible recognition sequences multiple times, obtain simulation attributes, and calculate the attribute evaluation index of each sequence based on these attributes. Through this method, the optimal recognition sequence can be effectively evaluated and selected to ensure the accuracy and reliability of the recognition result. In addition, the method also introduces the calculation of attribute expectation and attribute variance, which can further optimize the recognition process and improve the recognition efficiency. In addition, the method of the present invention also includes a comprehensive consideration of recognition constraints, such as the integrity of identification information, the accuracy of description information, and the consistency of associated attributes, to ensure the rigor and systematicness of the recognition process. This method can not only reduce the interference of human factors, but also improve the real-time and dynamic adaptability of recognition through the analysis of real-time data and performance parameters. Finally, the implementation of the invention can enhance the automatic recognition capability of electrical system nameplates, provide strong technical support for industrial automation and intelligence, and have broad application prospects and significant social and economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which: Figure 1 A schematic diagram of a flow chart of a method for identifying a nameplate label of an electrical system provided by an embodiment of the present invention; Figure 2 A schematic diagram of the structure of a nameplate label recognition system for an electrical system provided by an embodiment of the present invention; Figure 3 The schematic diagram schematically shows the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0018] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0019] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0020] Reference below Figure 1 , Figure 1 The following is a flow chart of a method for identifying a nameplate label of an electrical system provided by an embodiment of the present invention. Figure 1 As shown, a method 100 for identifying a nameplate label of an electrical system includes: Step 101, mapping the electrical appliance label nameplate into a digital model; the digital model includes a nameplate component node and an attribute feature edge; the nameplate component node includes an identification subnode and a description subnode; Step 102, the attribute feature edges include: an identification attribute edge of an identification subnode, a description attribute edge of a description subnode, and an association attribute edge between nameplate component nodes; Step 103, selecting a start node and a target node in the digital model to determine a minimum recognition sequence, and extracting a set consisting of multiple feasible recognition sequences from the minimum recognition sequence based on the recognition constraints; Step 104, performing multiple attribute simulations, generating attribute parameters of attribute feature edges in each feasible recognition sequence according to attribute requirements in each simulation, and obtaining simulated attributes of each feasible recognition sequence; Step 105 : Based on the simulation attributes, an optimal feasible recognition sequence of the electrical appliance label nameplate is identified, and the optimal feasible recognition sequence is used as a recognition result of the electrical appliance label nameplate.

[0021] Specifically, to implement the method for identifying nameplates of electrical systems of the present invention, it is first necessary to map the nameplates of electrical appliances into a digital model. This digital model consists of nameplate component nodes and attribute feature edges, wherein the nameplate component nodes are further subdivided into identification subnodes and description subnodes. The identification subnode is responsible for storing identification information such as the model and specifications of the electrical appliance, while the description subnode records detailed information such as parameter and function description.

[0022] Furthermore, attribute feature edges are used to connect and describe the relationship between different nodes in the model. Specifically, the identification attribute edge describes how the identification sub-node handles model and specification information, and the description attribute edge describes how the description sub-node handles parameters and functional descriptions. In addition, the association attribute edge is used to express the relationship and attributes between the nameplate component nodes.

[0023] After the digital model is built, a starting node and a target node need to be selected to determine a minimum recognition sequence. This sequence is the node sequence that must be passed during the recognition process and will serve as the basis for the recognition process.

[0024] Preferably, based on the set recognition constraints, multiple feasible recognition sequences will be extracted from the minimum recognition sequence, and these sequences will serve as the basis for subsequent attribute simulation and evaluation.

[0025] Furthermore, multiple attribute simulations are performed on these feasible recognition sequences. In each simulation, attribute parameters of attribute feature edges in each sequence need to be generated according to attribute requirements, so as to obtain the simulated attributes of each sequence.

[0026] Specifically, based on these simulated attributes, the optimal feasible recognition sequence of the appliance label nameplate can be evaluated and identified. This sequence will be used as the final recognition result, which represents the best recognition path under the current conditions, ensuring the accuracy and efficiency of recognition.

[0027] In some embodiments, the identification sub-node is used to describe the model and specification identification information of the appliance label nameplate; The description sub-node is used to describe the parameters and function description information of the appliance label nameplate.

[0028] It should be noted that in the construction and application of the identification sub-node, the function of the identification sub-node is to describe key identification information such as the model and specifications of the appliance nameplate. The key identification information provides the basic classification and characteristics of the device when identifying the appliance.

[0029] In some embodiments, the description subnode is used to record and describe the parameters and functional description information of the appliance nameplate. The functional description information provides users with detailed descriptions of the performance and purpose of the device, and is an important reference for the use and maintenance of the appliance.

[0030] Based on the identification subnode and the description subnode, it is necessary to further define the identification attribute edge and the description attribute edge. The identification attribute edge is specifically used to describe how to process and identify the model and specification information in the identification subnode. In some embodiments, these identification information can be parsed and utilized by algorithms or rules to achieve accurate identification of the model and specification of the electrical appliance.

[0031] Furthermore, the description attribute edge will be used to describe the processing method of the parameter and function description information in the description child node, including the parsing, classification and storage of this information, so that it can be quickly retrieved and used when needed.

[0032] In some embodiments, the identification attribute edge is used to describe the attributes of the identification subnode processing model and specification identification information; The description attribute edge is used to describe the attributes of the description sub-node processing parameters and function description information; The association attribute edge is used to describe the association relationship and attributes between nameplate component nodes.

[0033] In some embodiments, the specific functions of the identification attribute edge and the description attribute edge need to be clarified first. The identification attribute edge is used to describe and process the model and specification information in the identification subnode. When the nameplate is mapped in the digital model, specific attribute edges are defined for these identification information, which will guide the system on how to identify and process the model and specification identification on the nameplate.

[0034] Preferably, the description attribute edge needs to pass the parameter and function description information in the description child node. These attribute edges will define how the system parses and understands the parameter details and function description on the nameplate, ensuring that this information can be accurately captured and used in the subsequent identification process.

[0035] Furthermore, the associative attribute edges in the digital model not only describe the association relationship between the nameplate component nodes, but also cover the attributes of these nodes. In this way, the associative attribute edges help the system understand the connection between different nameplate information, thereby providing a more comprehensive and in-depth understanding during the recognition process.

[0036] Specifically, corresponding rules and algorithms can be defined for these attribute edges to ensure that they can accurately reflect the characteristics and relationships of the nameplate information. These rules and algorithms will be based on the specific requirements and standards of the electrical system nameplate to achieve the best recognition effect.

[0037] In some embodiments, the step of identifying the optimal feasible identification sequence of the appliance label nameplate includes: For each feasible identification sequence, multiple attribute simulations are performed to obtain simulation attributes, and the attribute expectation and attribute variance of the feasible identification sequence are determined; Determining an attribute evaluation index of a feasible recognition sequence based on the attribute expectation and attribute variance of the recognition sequence; The recognition sequence corresponding to the highest value of the attribute evaluation index is taken as the optimal feasible recognition sequence.

[0038] It should be noted that, first of all, it is necessary to perform multiple attribute simulations on each feasible recognition sequence. This step is a key link in the recognition process, and the attribute performance of different recognition sequences can be predicted and evaluated through simulation.

[0039] When performing attribute simulation, corresponding attribute parameters can be generated for the attribute feature edges in each feasible recognition sequence according to the attribute requirements. These parameters will guide the simulation process and help us obtain the simulation attributes of each sequence, thereby evaluating the potential performance of the sequence.

[0040] Preferably, we will use these simulation properties to determine the property expectation and property variance of each feasible recognition sequence. The property expectation reflects the average performance of the sequence in the simulation, while the property variance measures the degree of fluctuation of the sequence performance. These two indicators provide us with important basis for evaluating the stability and reliability of the recognition sequence.

[0041] Based on the attribute expectation and attribute variance, the attribute evaluation index of each recognition sequence can be calculated. This evaluation index will comprehensively consider the expected performance and volatility of the sequence, providing a quantitative basis for us to select the optimal recognition sequence.

[0042] Furthermore, we will select the recognition sequence corresponding to the highest value of the attribute evaluation index as the optimal feasible recognition sequence based on the calculation results of the attribute evaluation index. This sequence represents the best recognition path under the current conditions, and it will be used as the recognition result of the electrical appliance label nameplate to ensure the accuracy and efficiency of the recognition process.

[0043] In some embodiments, the attribute evaluation index of each feasible recognition sequence is calculated according to formula (1): (1) In the formula, It is an attribute evaluation index of a feasible recognition sequence, which is used to quantitatively evaluate the overall attribute performance of the recognition sequence. is the attribute expectation, which represents the average attribute value exhibited by the identification sequence in multiple simulations. is the attribute variance, which is used to measure the fluctuation or dispersion of the attribute performance of the recognition sequence. The expected average value of all identified sequence properties serves as the expected reference point. is the attribute expectation weight, which reflects the importance of attribute expectation in the evaluation index. It is the penalty coefficient for attribute fluctuation, which is used to penalize the volatility of attribute performance. is a coefficient related to the closeness of attribute distribution, which is used to evaluate the deviation between the expectation of the recognition sequence and the overall average expectation. , , is a non-negative real number, .

[0044] Specifically, and It is calculated by the attribute value of the recognition sequence obtained through multiple simulations. Specifically, it is obtained through the following steps: Perform multiple simulations for each recognition sequence and record the attribute value of each simulation. Calculate the average value of all simulation results as Calculate the sum of the squares of the differences between all simulation results and the mean, and then divide it by the number of simulations minus one to get .

[0045] It is obtained by statistically analyzing the attribute expectations of all recognition sequences. The average value of the attribute expectations of all recognition sequences is calculated. . , , are parameters pre-set according to the specific requirements and importance of the recognition task. They are non-negative real numbers and satisfy the following normalization conditions: The above parameters can be adjusted according to different application scenarios and recognition targets to achieve the best recognition effect.

[0046] In some embodiments, the identification constraints include identification information integrity constraints, description information accuracy constraints, and association attribute consistency constraints.

[0047] It should be noted that first, identification constraints need to be defined, which are the key factors to ensure the effectiveness and accuracy of the nameplate identification method of the electrical system. Identification constraints mainly include identification information integrity constraints, description information accuracy constraints and association attribute consistency constraints.

[0048] Preferably, the identification information integrity constraint ensures that during the identification process, key information on the appliance label, such as model, specification, etc., must be intact. This means that at each node in the identification sequence, the relevant identification information should be accurately captured and used in subsequent identification steps.

[0049] Furthermore, the description information accuracy constraint focuses on the accuracy of information such as parameters and function descriptions on the appliance nameplate. This constraint requires the system to accurately parse and use this description information during the recognition process to ensure the correctness of the recognition result.

[0050] Specifically, the association attribute consistency constraint involves the association relationship between nameplate component nodes and the consistency of their attributes. The system needs to ensure that during the recognition process, the association between different information on the nameplate is correctly processed and complies with the preset association rules.

[0051] During the recognition process, we will obtain real-time data and performance parameters when mapping the appliance nameplate to a digital model. These data include real-time identification information, real-time description information, and real-time associated attributes of each nameplate component node, as well as real-time associated attributes of each edge. The performance parameters cover the node performance indicators of each nameplate component node.

[0052] Next, for each recognition sequence in the minimum recognition sequence, we will determine whether the recognition constraints are satisfied. If the real-time identification information and real-time description information in the sequence are complete and meet the performance requirements, and the sum of the real-time association attributes of the edge and the node performance index also meets the overall requirements, then this recognition sequence meets all recognition constraints.

[0053] Finally, we extract all recognition sequences that meet the recognition constraints to form a set of feasible recognition sequences. This set will serve as the basis for subsequent attribute simulation and optimal recognition sequence selection, thereby ensuring the efficiency and accuracy of the entire recognition process.

[0054] In some embodiments, extracting a set consisting of multiple feasible recognition sequences from the minimum recognition sequence includes: Acquire real-time data and performance parameters when the electrical appliance label nameplate is mapped to a digital model, wherein the real-time data includes real-time identification information, real-time description information and real-time associated attributes of each nameplate component node, and real-time associated attributes of each edge; The performance parameters include node performance indicators for each nameplate component node; For each recognition sequence in the minimum recognition sequence, determine whether the recognition constraint is satisfied; Extracting recognition sequences that satisfy recognition constraints as feasible recognition sequences; All feasible identification sequences extracted are summarized to form a set.

[0055] It should be noted that we first need to extract multiple feasible recognition sequences from the minimum recognition sequence. This step is the key link of the recognition method because it involves screening out sequences that meet specific conditions from all possible recognition paths.

[0056] Preferably, we first obtain the real-time data and performance parameters of the appliance nameplate when it is mapped to a digital model. These data include the real-time identification information, real-time description information, and real-time associated attributes of each nameplate component node, as well as the real-time associated attributes of each edge. The performance parameters include the node performance indicators of each nameplate component node, which are important bases for evaluating whether the recognition sequence is feasible.

[0057] Furthermore, we will evaluate each recognition sequence in the minimum recognition sequence to determine whether they meet the previously defined recognition constraints. These constraints include the completeness of identification information, the accuracy of description information, and the consistency of associated attributes, which ensure the accuracy and reliability of the recognition sequence.

[0058] For the recognition sequences that meet the recognition constraints, we mark them as feasible recognition sequences and extract them from the set. This step is to ensure that the recognition sequences we obtain not only meet the technical requirements but also work effectively in practical applications.

[0059] Specifically, we aggregate all the extracted feasible recognition sequences into a set. This set contains all the recognition sequences that meet the conditions, which will serve as the basis for subsequent attribute simulation and optimal recognition sequence selection. In this way, we can ensure that only those recognition sequences that meet all technical requirements and constraints will be further considered and used during the recognition process.

[0060] In some embodiments, determining whether the identification constraint is satisfied includes: If the real-time identification information and real-time description information of each nameplate component node in the current identification sequence are complete, the identification information integrity constraint is satisfied; If the real-time association attribute of each edge in the current recognition sequence meets the preset association rule, the total association attribute of the appliance label nameplate meets the total association rule, and the sum of the association attributes of the current recognition sequence does not exceed the association attribute threshold, then the association attribute consistency constraint is satisfied; If the performance index of each nameplate component node in the current identification sequence meets the performance requirements, and the sum of the performance indexes of all nameplate component nodes meets the overall performance requirements, then the performance index constraint is satisfied; The recognition sequences that simultaneously satisfy the above constraints are extracted as feasible recognition sequences.

[0061] It should be noted that we first need to make a detailed judgment on the satisfaction of the identification constraints. This step is a key link to ensure the feasibility of the identification sequence, which involves a comprehensive evaluation of the real-time information and performance indicators of the nameplate component nodes.

[0062] Preferably, we first check whether the real-time identification information and real-time description information of each nameplate component node in the current identification sequence are complete. If this information is complete, then we believe that the identification sequence meets the identification information integrity constraint. The satisfaction of this constraint is the basis for the accuracy of the identification process, ensuring that the key information on the nameplate is accurately captured.

[0063] Furthermore, we will evaluate whether the real-time association attribute of each edge meets the preset association rule. In addition, we need to ensure that the total association attribute of the appliance label nameplate meets the total association rule, and the sum of the association attributes of the current recognition sequence does not exceed the association attribute threshold. If these conditions are met, then we believe that the recognition sequence meets the association attribute consistency constraint. The satisfaction of this constraint ensures that the logical relationship and consistency between the nameplate information are correctly handled.

[0064] Specifically, we also need to evaluate whether the performance indicators of each nameplate component node in the current identification sequence meet the performance requirements. If the sum of the performance indicators of all nodes also meets the overall performance requirements, then we believe that the identification sequence meets the performance indicator constraint. The satisfaction of this constraint ensures that the performance of the identification sequence meets expectations and can run stably in practical applications. Only when an identification sequence satisfies all the above constraints at the same time, we extract it as a feasible identification sequence.

[0065] The above-mentioned embodiments of the present invention have the following beneficial effects: the electrical system nameplate label recognition method of the present invention can realize efficient and accurate recognition of electrical appliance labels and nameplates through a series of innovative technical means. First, by mapping the nameplate into a digital model, the method can improve the systematicity and structured degree of information processing. Secondly, by selecting the starting node and the target node to determine the minimum recognition sequence, and extracting the feasible recognition sequence based on the recognition constraints, the method can optimize the recognition process and reduce invalid or inefficient recognition paths. Thirdly, by performing multiple attribute simulations and evaluating the optimal recognition sequence based on the simulated attributes, the method can enhance the accuracy and reliability of the recognition results. In addition, by introducing the calculation of attribute evaluation indicators, the method further improves the recognition efficiency and can ensure adaptability and flexibility under variable conditions. Finally, by comprehensively considering the recognition constraints, including the integrity of the identification information, the accuracy of the description information, and the consistency of the associated attributes, the method can ensure the rigor and systematicity of the recognition process, reduce the interference of human factors, and improve the level of automation.

[0066] like Figure 2 As shown, in some embodiments, an electrical system nameplate label recognition system 200 includes: A digital model generation module, used for mapping the electrical appliance label nameplate into a digital model; the digital model includes a nameplate component node and an attribute feature edge; the nameplate component node includes an identification subnode and a description subnode; the attribute feature edge includes an identification attribute edge of the identification subnode, a description attribute edge of the description subnode, and an association attribute edge between nameplate component nodes; A feasible recognition sequence set determination module is used to select a starting node and a target node in the digital model to determine a minimum recognition sequence, and extract a set from the minimum recognition sequence based on recognition constraints; The attribute simulation module performs multiple attribute simulations, generates attribute parameters of attribute feature edges in each feasible recognition sequence according to attribute requirements in each simulation, and obtains simulation attributes of each feasible recognition sequence; The optimal feasible recognition sequence determination module identifies the optimal feasible recognition sequence of the electrical appliance label nameplate based on the simulation attribute, and uses the sequence as the recognition result of the electrical appliance label nameplate.

[0067] It is understandable that the modules recorded in the electrical system nameplate label recognition system 200 are similar to those in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the electrical system nameplate label recognition method are also applicable to the electrical system nameplate label recognition system 200 and the modules contained therein, and will not be repeated here.

[0068] Reference below Figure 3 , which shows a schematic diagram of a structure 300 of an electronic device suitable for implementing some embodiments of the present invention. The electronic devices in some embodiments of the present invention may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0069] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 to a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0070] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0071] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0072] The above descriptions are only some preferred embodiments of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention.

Claims

1. A method for identifying nameplate labels of an electrical system, characterized in that: include: Mapping the electrical appliance label nameplate into a digital model; the digital model includes nameplate component nodes and attribute feature edges; The nameplate component node includes an identification subnode and a description subnode; The attribute feature edges include: identification attribute edges of identification subnodes, description attribute edges of description subnodes, and association attribute edges between nameplate component nodes; Selecting a starting node and a target node in the digital model to determine a minimum recognition sequence, and extracting a set consisting of multiple feasible recognition sequences from the minimum recognition sequence based on recognition constraints; Execute multiple attribute simulations. In each simulation, generate attribute parameters of attribute feature edges in each feasible recognition sequence according to attribute requirements, and obtain simulation attributes of each feasible recognition sequence. Based on the simulation attributes, an optimal feasible recognition sequence of the electrical appliance label nameplate is identified, and the optimal feasible recognition sequence is used as a recognition result of the electrical appliance label nameplate.

2. The method for identifying nameplates and labels of electrical systems according to claim 1, characterized in that: The identification sub-node is used to describe the model and specification identification information of the electrical appliance label nameplate; The description sub-node is used to describe the parameters and function description information of the appliance label nameplate.

3. The method for identifying nameplates and labels of electrical systems according to claim 2, characterized in that: The identification attribute edge is used to describe the attributes of the identification subnode processing model and specification identification information; The description attribute edge is used to describe the attributes of the description sub-node processing parameters and function description information; The association attribute edge is used to describe the association relationship and attributes between nameplate component nodes.

4. The method for identifying nameplates and labels of electrical systems according to claim 1, characterized in that: The optimal feasible identification sequence for identifying the nameplate of the electrical appliance includes: For each feasible identification sequence, multiple attribute simulations are performed to obtain simulation attributes, and the attribute expectation and attribute variance of the feasible identification sequence are determined; Determining an attribute evaluation index of a feasible recognition sequence based on the attribute expectation and attribute variance of the recognition sequence; The recognition sequence corresponding to the highest value of the attribute evaluation index is taken as the optimal feasible recognition sequence.

5. The method for identifying nameplates and labels of an electrical system according to claim 4, characterized in that: Calculate the attribute evaluation index of each feasible recognition sequence.

6. The method for identifying nameplates and labels of an electrical system according to claim 1, characterized in that: The identification constraints include identification information integrity constraints, description information accuracy constraints and association attribute consistency constraints.

7. The method for identifying nameplates and labels of an electrical system according to claim 6, characterized in that: The step of extracting a set consisting of a plurality of feasible identification sequences from the minimum identification sequence comprises: Acquire real-time data and performance parameters when the electrical appliance label nameplate is mapped to a digital model, wherein the real-time data includes real-time identification information, real-time description information and real-time associated attributes of each nameplate component node, and real-time associated attributes of each edge; The performance parameters include node performance indicators for each nameplate component node; For each recognition sequence in the minimum recognition sequence, determine whether the recognition constraint is satisfied; Extracting recognition sequences that satisfy recognition constraints as feasible recognition sequences; All feasible identification sequences extracted are summarized to form a set.

8. The method for identifying nameplates and labels of an electrical system according to claim 6, characterized in that: Judging whether the identification constraints are satisfied includes: If the real-time identification information and real-time description information of each nameplate component node in the current identification sequence are complete, the identification information integrity constraint is satisfied; If the real-time association attribute of each edge in the current recognition sequence meets the preset association rule, the total association attribute of the appliance label nameplate meets the total association rule, and the sum of the association attributes of the current recognition sequence does not exceed the association attribute threshold, then the association attribute consistency constraint is satisfied; If the performance index of each nameplate component node in the current identification sequence meets the performance requirements, and the sum of the performance indexes of all nameplate component nodes meets the overall performance requirements, then the performance index constraint is satisfied; The recognition sequences that satisfy the above constraints are extracted as feasible recognition sequences.

9. An electrical system nameplate label recognition system, characterized in that: include: A digital model generation module, used for mapping the electrical appliance label nameplate into a digital model; the digital model includes a nameplate component node and an attribute feature edge; the nameplate component node includes an identification subnode and a description subnode; the attribute feature edge includes an identification attribute edge of the identification subnode, a description attribute edge of the description subnode, and an association attribute edge between nameplate component nodes; A feasible recognition sequence set determination module is used to select a starting node and a target node in the digital model to determine a minimum recognition sequence, and extract a set from the minimum recognition sequence based on recognition constraints; The attribute simulation module performs multiple attribute simulations, generates attribute parameters of attribute feature edges in each feasible recognition sequence according to attribute requirements in each simulation, and obtains simulation attributes of each feasible recognition sequence; The optimal feasible recognition sequence determination module identifies the optimal feasible recognition sequence of the electrical appliance label nameplate based on the simulation attribute, and uses the sequence as the recognition result of the electrical appliance label nameplate.

10. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

Images