Coal chemical industry standard metadata storage method and machine readable storage medium

Abstract

The invention discloses a coal chemical industry standard metadata storage method and a machine readable storage medium, and the method comprises the steps: collecting coal chemical industry standard metadata, and carrying out the preprocessing of the metadata; performing feature classification on the metadata in combination with semantic information to obtain classification data, and constructing a knowledge graph for the classification data according to the association degree to obtain knowledge graph data; performing relation correction on the knowledge graph data to obtain optimized graph data, and constructing a coal chemical industry standard metadata storage model according to the optimized graph data; and optimizing the coal chemical industry standard metadata storage model, inputting to-be-stored data into the optimized coal chemical industry standard metadata storage model, and outputting a storage result. The method not only can improve the precision of coal chemical industry standard metadata storage, but also has good interpretability, and can be directly applied to a metadata storage system.

Description

Technical Field

[0001] The present invention relates to the field of data storage, and in particular to a coal chemical industry standard metadata storage method and a machine-readable storage medium. Background Art

[0002] As an important intersection of energy and chemical industries, the management and storage of industry standard metadata in the coal chemical industry has always been a key issue in the industry. Industry standard metadata not only covers core information such as the production process, quality specifications, and safety standards of coal chemical products, but also involves multiple aspects such as technology updates, environmental protection requirements, and market access. The accuracy and completeness of these data have a vital impact on the operational decisions, product quality control, and market competitiveness of coal chemical companies.

[0003] However, traditional coal chemical industry standard metadata management methods mostly rely on paper documents, spreadsheets or simple database systems. These methods often have many limitations when dealing with massive, complex and constantly updated metadata. For example, paper documents and spreadsheets are difficult to support efficient retrieval and analysis, while simple database systems may lead to data isolation and fragmentation due to lack of semantic understanding and association analysis capabilities.

[0004] In order to overcome the shortcomings of traditional methods, in recent years, knowledge graph technology has gradually emerged in the management of standard metadata in the coal chemical industry due to its powerful semantic expression and association analysis capabilities. By constructing entity, attribute and relationship triples, knowledge graphs can clearly express the internal connections and hierarchical structures between metadata, thereby supporting more accurate and efficient data retrieval, analysis and application.

[0005] Therefore, Kou Dai invented a new storage method to improve the accuracy, consistency and completeness of standard metadata storage in the coal chemical industry. Summary of the invention

[0006] The purpose of the present invention is to provide a standard metadata storage method for the coal chemical industry.

[0007] To achieve the above object, the present invention is implemented according to the following technical solutions: The present invention comprises the following steps: Collecting metadata of coal chemical industry standards and preprocessing the metadata; Feature classification is performed on the metadata in combination with the semantic information to obtain classified data, and a knowledge graph is constructed for the classified data according to the association degree to obtain knowledge graph data; Performing relationship correction on the knowledge graph data to obtain optimized graph data, and constructing a coal chemical industry standard metadata storage model based on the optimized graph data; Optimize the coal chemical industry standard metadata storage model, input the data to be stored into the optimized coal chemical industry standard metadata storage model, and output the storage result.

[0008] Furthermore, the method of performing feature classification on the metadata in combination with the semantic information to obtain classified data includes: The metadata is input into the feature classification model, and the loss function is given as: , The loss function is , the actual classification result of the pth metadata is , the predicted classification result of the pth metadata is ; Extract the subject and text features of metadata, and obtain the semantic representation of metadata by superimposing multiple layers of multi-head self-attention mechanism and feedforward neural network. The expression is: , , The node degree matrix is ​​H, the topic co-occurrence binary matrix is ​​C, and the unit diagonal matrix is , the degree of node i is , the degree of node z is , the semantic representation of node v at level d is , the semantic representation of node i at the d+1th layer is , the normalized adjacency matrix is ; The attention mechanism is used to extract semantic information from metadata, and the expression is: , , The yth text feature vector is , transposed to T, the attention weight of the y-th text feature vector in the w-th metadata is , the wth topic semantics is expressed as , the number of text features is , the text feature related to the wth topic is ; Calculate the semantic relevance between topic-related text features and the topic: , , The semantic relevance between the topic-related text features and the wth topic is , the discriminant function is , the number of y-th text features related to the w-th topic is , the yth text feature related to the wth topic is , the control factor is , topic semantic representation The text feature vector appears under the condition The probability of , topic semantic representation The modulus length is , text feature vector The modulus length is ; The metadata are sorted according to the semantic relevance, the metadata with the greatest semantic relevance is classified into the corresponding topic, and the classification results are output as classified data.

[0009] Furthermore, the method for constructing a knowledge graph for the classified data according to the association degree includes: Calculate the association between categorical data: , The correlation between the classification data u and the classification data c is , the j-th classification data u is , the j-th classification data c is , the average value of the classification data u is , the average value of the classification data c is , categorical data and categorical data The distance is , categorical data and categorical data The probability of simultaneous occurrence is , categorical data The probability of occurrence is , categorical data The probability of occurrence is , the number of classification data is n; The classified data are connected according to the correlation between them to obtain a knowledge graph.

[0010] Furthermore, the method of performing relationship correction on the knowledge graph data to obtain optimized graph data includes: Filter out named entities with semantic relevance less than 0.312 in the knowledge graph as initial entities, and take entities related to the initial entities as related entities; Aggregate the initial entities of the knowledge graph according to the relationship, and the expression is: , The embedding representation matrix of the initial entity d at time s is , the embedding representation matrix of the original entity d relationship at time s is , at time s the original entity The aggregation matrix is , the conditional format elimination function is , the number of adjacent entities of the initial entity d is ; Calculate the weight of the relationship edge: , The parameters of the qth fully connected layer are , at time s the original entity The embedding matrix of , the weight value of the relationship edge between the initial entity d and the related entity m is , the control coefficient is ; According to the weight value, the semantic relevance is adjusted to obtain the modified relevance, which is expressed as: , The attenuation rate is , the semantic association between the initial entity d and the related entity m is , the modified association between the initial entity d and the related entity m is ; The initial entities are sorted in descending order according to the corrected correlation, and the initial entity with the largest corrected correlation is used for adjustment, and the adjustment result is output as optimized graph data.

[0011] Furthermore, a method for constructing a standard metadata storage model for the coal chemical industry based on the optimized graph data includes: The storage score and loss function of the optimized graph data are used to construct the objective function of the standard metadata storage model for the coal chemical industry; The standard metadata storage model for the coal chemical industry includes time series feature extraction algorithm, hash table index algorithm, and machine learning algorithm; The bag-of-words feature extraction algorithm converts metadata into a numerical feature vector by counting the frequency of occurrence of terms in the input metadata; The hash table indexing algorithm uses a hash function to map the numerical feature vector to a unique position in the hash table to obtain the search result; The machine learning algorithm obtains the objective function value through the objective function of the retrieval results, takes the maximization of the objective function value as the learning goal, performs storage learning to obtain the storage mode, and performs predictive storage based on the storage mode.

[0012] Furthermore, the method for optimizing the coal chemical industry standard metadata storage model includes: Introduce particle population, store score difference as fitness, calculate particle fitness, and take the particle position with the smallest fitness as the best position; The chaotic mapping of particle population is expressed as: , The initial sequence for the tth iteration is , the chaotic mapping sequence of the tth iteration is , the control parameter is b, and the random number from 0 to 1 is ; Given the balance factor, the expression is: , The balance factor is , the control coefficient is , a random number from 0 to 2 is , the current number of iterations is t, and the maximum number of iterations is ; When the balance factor is greater than 0.5, the particle position is updated, and the expression is: , The updated position of the ath particle in the t+1th iteration is , the position of the ath particle in the xth dimension at the tth iteration is , the position of the random particle in the xth dimension at the tth iteration is , the random numbers from 0 to 1 are , ; When the balance factor is less than or equal to 0.5, the Levy flight strategy is used to update the particle position and obtain the flight position. The expression is: , The flight position of the ath particle in the t+1th iteration is , the random numbers from 0 to 1 are , , the updated position of the ath particle in the tth iteration is , the optimal position of the particle in the tth iteration is , the position of the random particle at the tth iteration is , the Levy flight step length is ; The nonlinear convergence factor is used to improve the balance factor, and the expression is: , , The nonlinear convergence factor is , the improved balance factor is , the constant greater than 0 is ; Continue to iterate until the maximum number of iterations is reached, otherwise update the particle population and recalculate the fitness.

[0013] In a second aspect, an embodiment of the present application further provides an electronic device, including: A processor; and a memory arranged to store computer executable instructions, which when executed cause the processor to perform the method steps described in the first aspect.

[0014] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes the method steps described in the first aspect.

[0015] The beneficial effects of the present invention are: The present invention is a coal chemical industry standard metadata storage method and a machine-readable storage medium. Compared with the prior art, the present invention has the following technical effects: The present invention can improve the accuracy of coal chemical industry standard metadata storage through preprocessing, characteristic classification, knowledge graph construction, knowledge graph adjustment, model construction and model optimization steps, thereby improving the accuracy of coal chemical industry standard metadata storage, and optimizing coal chemical industry standard metadata storage, which can greatly save resources and improve work efficiency, and can realize automatic storage of coal chemical industry standard metadata, and perform correlation correction on coal chemical industry standard metadata storage in real time, which is of great significance to coal chemical industry standard metadata storage, can adapt to coal chemical industry standard metadata storage of different standards and different coal chemical industry standard metadata storage requirements, and has a certain universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of the steps of the coal chemical industry standard metadata storage method of the present invention; Figure 2 It is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION

[0017] The present invention is further described below by means of specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0018] The coal chemical industry standard metadata storage method and machine-readable storage medium of the present invention include the following steps: like Figure 1 As shown, in this embodiment, the following steps are included: Collecting metadata of coal chemical industry standards and preprocessing the metadata; In the actual evaluation, the metadata of coal quality analysis standards, coal chemical product standards, and coal chemical equipment standards are taken as research objects; Feature classification is performed on the metadata in combination with the semantic information to obtain classified data, and a knowledge graph is constructed for the classified data according to the association degree to obtain knowledge graph data; In the actual evaluation, the classification data are coal quality analysis characteristics and coal chemical equipment characteristics; the secondary knowledge graph data of coal quality analysis characteristics is the ash content determination method; the secondary knowledge graph data of coal chemical equipment characteristics is the equipment material requirements, and the tertiary knowledge graph data is the composite coal chemical product requirements; Performing relationship correction on the knowledge graph data to obtain optimized graph data, and constructing a coal chemical industry standard metadata storage model based on the optimized graph data; In the actual evaluation, the three-level knowledge graph data of coal chemical equipment characteristics was revised to the production requirements of composite coal chemical products; Optimize the coal chemical industry standard metadata storage model, input the data to be stored into the optimized coal chemical industry standard metadata storage model, and output the storage result.

[0019] In this embodiment, the method of performing feature classification on the metadata in combination with semantic information to obtain classified data includes: The metadata is input into the feature classification model, and the loss function is given as: , The loss function is , the actual classification result of the pth metadata is , the predicted classification result of the pth metadata is ; Extract the subject and text features of metadata, and obtain the semantic representation of metadata by superimposing multiple layers of multi-head self-attention mechanism and feedforward neural network. The expression is: , , The node degree matrix is ​​H, the topic co-occurrence binary matrix is ​​C, and the unit diagonal matrix is , the degree of node i is , the degree of node z is , the semantic representation of node v at level d is , the semantic representation of node i at the d+1th layer is , the normalized adjacency matrix is ; The attention mechanism is used to extract semantic information from metadata, and the expression is: , , The yth text feature vector is , transposed to T, the attention weight of the y-th text feature vector in the w-th metadata is , the wth topic semantics is expressed as , the number of text features is , the text feature related to the wth topic is ; Calculate the semantic relevance between topic-related text features and the topic: , , The semantic relevance between the topic-related text features and the wth topic is , the discriminant function is , the number of y-th text features related to the w-th topic is , the yth text feature related to the wth topic is , the control factor is , topic semantic representation The text feature vector appears under the condition The probability of , topic semantic representation The modulus length is , text feature vector The modulus length is ; The metadata are sorted according to the semantic relevance, the metadata with the greatest semantic relevance is classified into the corresponding topic, and the classification results are output as classified data.

[0020] In this embodiment, the method of constructing a knowledge graph for the classified data according to the association degree includes: Calculate the association between categorical data: , The correlation between the classification data u and the classification data c is , the j-th classification data u is , the j-th classification data c is , the average value of the classification data u is , the average value of the classification data c is , categorical data and categorical data The distance is , categorical data and categorical data The probability of simultaneous occurrence is , categorical data The probability of occurrence is , categorical data The probability of occurrence is , the number of classification data is n; The classified data are connected according to the correlation between them to obtain a knowledge graph.

[0021] In this embodiment, the method for performing relationship correction on the knowledge graph data to obtain optimized graph data includes: Filter out named entities with semantic relevance less than 0.312 in the knowledge graph as initial entities, and take entities related to the initial entities as related entities; Aggregate the initial entities of the knowledge graph according to the relationship, and the expression is: , The embedding representation matrix of the initial entity d at time s is , the embedding representation matrix of the original entity d relationship at time s is , at time s the original entity The aggregation matrix is , the conditional format elimination function is , the number of adjacent entities of the initial entity d is ; Calculate the weight of the relationship edge: , The parameters of the qth fully connected layer are , at time s the original entity The embedding matrix of , the weight value of the relationship edge between the initial entity d and the related entity m is , the control coefficient is ; According to the weight value, the semantic relevance is adjusted to obtain the modified relevance, which is expressed as: , The attenuation rate is , the semantic association between the initial entity d and the related entity m is , the modified association between the initial entity d and the related entity m is ; The initial entities are sorted in descending order according to the corrected correlation, and the initial entity with the largest corrected correlation is used for adjustment, and the adjustment result is output as optimized graph data.

[0022] In this embodiment, the method for constructing a standard metadata storage model for the coal chemical industry according to the optimized graph data includes: The storage score and loss function of the optimized graph data are used to construct the objective function of the standard metadata storage model for the coal chemical industry; The standard metadata storage model for the coal chemical industry includes time series feature extraction algorithm, hash table index algorithm, and machine learning algorithm; The bag-of-words feature extraction algorithm converts metadata into a numerical feature vector by counting the frequency of occurrence of terms in the input metadata; The hash table indexing algorithm uses a hash function to map the numerical feature vector to a unique position in the hash table to obtain the search result; The machine learning algorithm obtains the objective function value through the objective function of the retrieval results, takes the maximization of the objective function value as the learning goal, performs storage learning to obtain the storage mode, and performs predictive storage based on the storage mode.

[0023] In this embodiment, the method for optimizing the coal chemical industry standard metadata storage model includes: Introduce particle population, store score difference as fitness, calculate particle fitness, and take the particle position with the smallest fitness as the best position; The chaotic mapping of particle population is expressed as: , The initial sequence for the tth iteration is , the chaotic mapping sequence of the tth iteration is , the control parameter is b, and the random number from 0 to 1 is ; Given the balance factor, the expression is: , The balance factor is , the control coefficient is , a random number from 0 to 2 is , the current number of iterations is t, and the maximum number of iterations is ; When the balance factor is greater than 0.5, the particle position is updated, and the expression is: , The updated position of the ath particle in the t+1th iteration is , the position of the ath particle in the xth dimension at the tth iteration is , the position of the random particle in the xth dimension at the tth iteration is , the random numbers from 0 to 1 are , ; When the balance factor is less than or equal to 0.5, the Levy flight strategy is used to update the particle position and obtain the flight position. The expression is: , The flight position of the ath particle in the t+1th iteration is , the random numbers from 0 to 1 are , , the updated position of the ath particle in the tth iteration is , the optimal position of the particle in the tth iteration is , the position of the random particle at the tth iteration is , the Levy flight step length is ; The nonlinear convergence factor is used to improve the balance factor, and the expression is: , , The nonlinear convergence factor is , the improved balance factor is , the constant greater than 0 is ; Continue to iterate until the maximum number of iterations is reached, otherwise update the particle population and recalculate the fitness. Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 2 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0024] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0025] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0026] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a user intention recognition device for a multi-dimensional human-computer interaction scene at the logical level. The processor executes the program stored in the memory and is specifically used to execute any of the above-mentioned coal chemical industry standard metadata storage methods.

[0027] The above application Figure 1 The coal chemical industry standard metadata storage method disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in software form. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in a decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0028] The electronic device may also perform Figure 1 China Coal Chemical Industry Standard Metadata Storage Method and Implementation Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0029] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple applications, they execute any of the aforementioned coal chemical industry standard metadata storage methods.

[0030] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0031] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0032] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0033] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0034] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0035] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0036] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0037] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0038] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0039] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A standard metadata storage method for the coal chemical industry, characterized in that: The following steps are involved: Collecting metadata of coal chemical industry standards and preprocessing the metadata; Feature classification is performed on the metadata in combination with the semantic information to obtain classified data, and a knowledge graph is constructed for the classified data according to the association degree to obtain knowledge graph data; Performing relationship correction on the knowledge graph data to obtain optimized graph data, and constructing a coal chemical industry standard metadata storage model based on the optimized graph data; Optimize the coal chemical industry standard metadata storage model, input the data to be stored into the optimized coal chemical industry standard metadata storage model, and output the storage result.

2. The method for storing standard metadata for the coal chemical industry according to claim 1, characterized in that: The method of performing feature classification on the metadata in combination with semantic information to obtain classified data includes: The metadata is input into the feature classification model, and the loss function is given as: ， The loss function is , the actual classification result of the pth metadata is , the predicted classification result of the pth metadata is ; Extract the subject and text features of metadata, and obtain the semantic representation of metadata by superimposing multiple layers of multi-head self-attention mechanism and feedforward neural network. The expression is: ， ， The node degree matrix is ​​H, the topic co-occurrence binary matrix is ​​C, and the unit diagonal matrix is , the degree of node i is , the degree of node z is , the semantic representation of node v at level d is , the semantic representation of node i at the d+1th layer is , the normalized adjacency matrix is ; The attention mechanism is used to extract semantic information from metadata, and the expression is: ， ， The yth text feature vector is , transposed to T, the attention weight of the y-th text feature vector in the w-th metadata is , the wth topic semantics is expressed as , the number of text features is , the text feature related to the wth topic is ; Calculate the semantic relevance between topic-related text features and the topic: ， ， The semantic relevance between the topic-related text features and the wth topic is , the discriminant function is , the number of y-th text features related to the w-th topic is , the yth text feature related to the wth topic is , the control factor is , topic semantic representation The text feature vector appears under the condition The probability of , topic semantic representation The modulus length is , text feature vector The modulus length is ; The metadata are sorted according to the semantic relevance, the metadata with the greatest semantic relevance is classified into the corresponding topic, and the classification results are output as classified data.

3. The method for storing standard metadata for the coal chemical industry according to claim 1, characterized in that: The method for constructing a knowledge graph for the classified data according to the association degree includes: Calculate the association between categorical data: ， The correlation between the classification data u and the classification data c is , the j-th classification data u is , the j-th classification data c is , the average value of the classification data u is , the average value of the classification data c is , categorical data and categorical data The distance is , categorical data and categorical data The probability of simultaneous occurrence is , categorical data The probability of occurrence is , categorical data The probability of occurrence is , the number of classification data is n; The classified data are connected according to the correlation between them to obtain a knowledge graph.

4. The coal chemical industry standard metadata storage method according to claim 1, characterized in that: The method of performing relationship correction on the knowledge graph data to obtain optimized graph data includes: Filter out named entities with semantic relevance less than 0.312 in the knowledge graph as initial entities, and take entities related to the initial entities as related entities; Aggregate the initial entities of the knowledge graph according to the relationship, and the expression is: ， The embedding representation matrix of the initial entity d at time s is , the embedding representation matrix of the original entity d relationship at time s is , at time s the original entity The aggregation matrix is , the conditional format elimination function is , the number of adjacent entities of the initial entity d is ; Calculate the weight of the relationship edge: ， The parameters of the qth fully connected layer are , at time s the original entity The embedding matrix of , the weight value of the relationship edge between the initial entity d and the related entity m is , the control coefficient is ; According to the weight value, the semantic relevance is adjusted to obtain the modified relevance, which is expressed as: ， The attenuation rate is , the semantic association between the initial entity d and the related entity m is , the modified association between the initial entity d and the related entity m is ; The initial entities are sorted in descending order according to the corrected correlation, and the initial entity with the largest corrected correlation is used for adjustment, and the adjustment result is output as optimized graph data.

5. The method for storing standard metadata for the coal chemical industry according to claim 1, characterized in that: The method for constructing a standard metadata storage model for the coal chemical industry according to the optimized graph data comprises: The storage score and loss function of the optimized graph data are used to construct the objective function of the standard metadata storage model for the coal chemical industry; The standard metadata storage model for the coal chemical industry includes time series feature extraction algorithm, hash table index algorithm, and machine learning algorithm; The bag-of-words feature extraction algorithm converts metadata into a numerical feature vector by counting the frequency of occurrence of terms in the input metadata; The hash table indexing algorithm uses a hash function to map the numerical feature vector to a unique position in the hash table to obtain the search result; The machine learning algorithm obtains the objective function value through the objective function of the retrieval results, takes the maximization of the objective function value as the learning goal, performs storage learning to obtain the storage mode, and performs predictive storage based on the storage mode.

6. The coal chemical industry standard metadata storage method according to claim 1, characterized in that: The method for optimizing the coal chemical industry standard metadata storage model includes: Introduce particle population, store score difference as fitness, calculate particle fitness, and take the particle position with the smallest fitness as the best position; The chaotic mapping of particle population is expressed as: ， The initial sequence for the tth iteration is , the chaotic mapping sequence of the tth iteration is , the control parameter is b, and the random number from 0 to 1 is ; Given the balance factor, the expression is: ， The balance factor is , the control coefficient is , a random number from 0 to 2 is , the current number of iterations is t, and the maximum number of iterations is ; When the balance factor is greater than 0.5, the particle position is updated, and the expression is: ， The updated position of the ath particle in the t+1th iteration is , the position of the ath particle in the xth dimension at the tth iteration is , the position of the random particle in the xth dimension at the tth iteration is , the random numbers from 0 to 1 are , ; When the balance factor is less than or equal to 0.5, the Levy flight strategy is used to update the particle position and obtain the flight position. The expression is: ， The flight position of the ath particle in the t+1th iteration is , the random numbers from 0 to 1 are , , the updated position of the ath particle in the tth iteration is , the optimal position of the particle in the tth iteration is , the position of the random particle at the tth iteration is , the Levy flight step length is ; The nonlinear convergence factor is used to improve the balance factor, and the expression is: ， ， The nonlinear convergence factor is , the improved balance factor is , the constant greater than 0 is ; Continue to iterate until the maximum number of iterations is reached, otherwise update the particle population and recalculate the fitness.

7. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, which, when executed, cause the processor to perform the method according to any one of claims 1 to 6.

8. A machine computer readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, enables the electronic device to execute the method according to any one of claims 1 to 6.

Images