Coal chemical industry standard data classification method and system based on artificial intelligence

Abstract

The invention discloses a coal chemical industry standard data classification method and system based on artificial intelligence, and the method comprises the steps: collecting coal chemical industry standard data and feedback data, and carrying out the preprocessing of the coal chemical industry standard data and the feedback data; performing feature extraction on the coal chemical industry standard data to obtain standard feature data, and performing association clustering on the standard feature data to obtain first data; classifying the standard feature data according to energy to obtain second data, and comparing the first data with the second data to obtain consistent data and fuzzy data; and correcting the fuzzy data according to the feedback data to obtain third data, and outputting the consistent data and the third data as a classification result. The method not only can improve the accuracy of coal chemical industry standard data classification based on artificial intelligence, but also has good interpretability, and can be directly applied to a coal chemical industry standard data classification system.

Description

Technical Field

[0001] The present invention relates to the field of data classification, and in particular to a coal chemical industry standard data classification method and system based on artificial intelligence. Background Art

[0002] As an important part of the energy and chemical industry, the coal chemical industry involves many complex technical standards and process flows in its production process. These standards and processes are of great significance for ensuring product quality, improving production efficiency and ensuring safe production. However, with the rapid development of the coal chemical industry and the continuous advancement of technology, industry standard data is characterized by massive, heterogeneous and constantly updated data, which brings great challenges to data management and application.

[0003] The traditional coal chemical industry standard data classification method mainly relies on manual review and expert experience. This method is not only time-consuming and laborious, but also easily affected by personal subjective factors, resulting in inaccurate and inconsistent classification results. In addition, due to the complexity and diversity of coal chemical industry standard data, traditional classification methods often find it difficult to fully cover all standards and processes, thus limiting their effectiveness in practical applications.

[0004] In order to overcome the shortcomings of traditional classification methods, artificial intelligence technology has been widely used in the coal chemical industry in recent years. Among them, classification methods based on machine learning and data mining have attracted much attention due to their powerful data processing and pattern recognition capabilities. However, most of the existing artificial intelligence-based classification methods are designed for specific fields or data sets, and lack the versatility and adaptability to standard data in the coal chemical industry. In addition, these methods often have problems such as inaccurate feature extraction and unstable classification results when dealing with complex and heterogeneous standard data in the coal chemical industry. Therefore, Kou Dai invented a new artificial intelligence-based coal chemical industry standard data classification method to improve accuracy and stability. Summary of the invention

[0005] The purpose of the present invention is to provide a coal chemical industry standard data classification method based on artificial intelligence.

[0006] To achieve the above object, the present invention is implemented according to the following technical solutions:

[0007] The present invention comprises the following steps:

[0008] Collecting coal chemical industry standard data and feedback data, and preprocessing the coal chemical industry standard data and the feedback data;

[0009] Performing feature extraction on the coal chemical industry standard data to obtain standard feature data, and performing association clustering on the standard feature data to obtain first data;

[0010] Classifying the standard characteristic data according to energy to obtain second data, and comparing the first data with the second data to obtain consistent data and fuzzy data;

[0011] The fuzzy data is corrected according to the feedback data to obtain third data, and the consistent data and the third data are output as classification results.

[0012] Furthermore, the method for extracting features from the coal chemical industry standard data to obtain standard feature data includes:

[0013] Text data is obtained by text extraction of standard data of coal chemical industry. The weight of words in the text data is quantified according to the part of speech. When the part of speech is noun and verb, the initial weight of the word is 0.8; when the part of speech is adjective and adverb, the initial weight of the word is 0.6; when the part of speech is other parts of speech, the initial weight of the word is 0;

[0014] Calculate the semantic coupling similarity of word pairs:

[0015] β(b w ,b z )=(1-ω)·CuR(b w ,b z )+ω·CvR(b w ,b z )

[0016] CuR(b w ,b z )=CS(P1(b w ),P1(b z ))

[0017] CvR w ,b z )=CS(P2(b w ),P2(b z ))

[0018] P1(b w )=(P1(b1|b w ),P1(b2|b w ),R,P1(b v |b w ),R,P1(b N1 |b w ))

[0019]

[0020] P2(b w )=(P2(b1|b w ),P2(b2|bw ),R,P2(b v |b w ),R,P2(b N1 |b w ))

[0021]

[0022] The relation strength function is CS(·,·), and the zth word is b z , the wth word is b w , the word pair is (b z ,b w ), word pair (b z ,b w ) is CuR(b w ,b z ), word pair (b z ,b w ) is CvR(b w ,b z ), the text set is U, the total number of texts is |U|, the word pair (b z ,b w ) in the probability of P1(b z |b w ), word b z and word b w The shortest path between z ,b w ), the decision parameter is ω, the word pair (b z ,b w ) appears at a frequency of DF(b z ,b w ), in the text set word b w The probability distribution of w ), word b w The similar probability distribution of w ), word b z and word b w The similarity between them is P2(b w |b z ), word pair (b z ,b w ) in the text set is P1(b z |b w ), the single text in the text set is u, the first word is b1, the second word is b2, and the vth word is b v , the N1th word is b N1 , the number of texts in the text set is N1, word pairs (b z ,b w) appears in a single text u is TPF((b z ,b w ),u);

[0023] Calculate the similarity between word attributes:

[0024]

[0025] The wth word attribute is a w , the attribute of the zth word is a z , word attribute a w and word attribute a z The similarity is The square of the Euclidean norm is The positive control parameter is η,

[0026] Build a text graph based on the text set, use the words as the feature terms of the text graph, and calculate the feature term weights:

[0027] θ(t+1)=(1-γ)·Q·θ(t)+γ·β·θ(t)

[0028]

[0029] The damping coefficient is γ, and the structural feature similarity between the t-th iteration feature term w and the feature term z is Q w,z , the similarity between word attributes is β, the feature word weight vector of the t-th iteration is θ(t), the feature word weight vector of the t+1-th iteration is θ(t+1), and the structural feature similarity is Q;

[0030] Continue to iterate until all feature terms are traversed, obtain the feature term weight vector, and output the feature term weight vector as standard feature data.

[0031] Furthermore, the method of performing association clustering on the standard feature data to obtain first data includes:

[0032] Construct a feature data set based on standard feature data and calculate the kernel density gradient:

[0033]

[0034] The kernel function is G(·), and the standard feature data g c The kernel density gradient is K(g c ), the cth standard feature data is g c , the number of standard feature data is M, and the bandwidth parameter of dimension σ is The standard characteristic data is g;

[0035] Calculate the relevance of standard feature data:

[0036]

[0037] The fuzzy neighborhood radius of the standard feature data is The association decision is W, the feature data set is S, the fuzzy neighborhood radius is Z, and the standard feature data is g c The fuzzy neighborhood particle size of the key data set is Z S (g c ), standard characteristic data g c The fuzzy neighborhood particle for association decision is Z W (g c ), the standard constant is δ, and the bandwidth parameter is The cth standard characteristic data is g c , kernel density gradient estimate is K(·), standard feature data g c The correlation degree is

[0038] Cluster the standard feature data according to the correlation to obtain clusters, and take the standard feature data with the largest kernel density gradient as the cluster center;

[0039] The fuzzy standard feature data are sorted into clusters according to the correlation, and the fuzzy standard feature data are divided into clusters with the largest correlation to obtain fuzzy clusters; and the clustering results are output as cluster first data.

[0040] Furthermore, the method of classifying the standard characteristic data according to energy to obtain the second data includes:

[0041] The energy type of the standard characteristic data is obtained according to the standard data of the coal chemical industry. The standard characteristic data containing only one type of energy is classified into a single energy data set, otherwise it is classified into a mixed energy data set;

[0042] The hybrid energy is sorted in descending order according to its importance, and the standard characteristic data of the hybrid energy data set is labeled according to the sorting; and the single energy data set and the hybrid energy data set are output as the second data.

[0043] Furthermore, the method of comparing the first data and the second data to obtain consistent data and fuzzy data includes:

[0044] Calculate the similarity between the first data and the second data:

[0045]

[0046] The first data of the rth category in the i-th category is h i,r , the jth second data of the i-th category is d i,j , the first data h i,r and the second data d i,jThe similarity is The number of first data of the i-th category is M h , the number of second data of the i-th category is M d , the control factor is α, and the optimization coefficient is

[0047] When the similarity is greater than 0.681, the corresponding first data or second data is classified as consistent data, otherwise the first data and the second data are classified as fuzzy data.

[0048] Furthermore, the method of correcting the fuzzy data according to the feedback data to obtain the third data includes:

[0049] Calculate the accuracy based on the feedback data:

[0050]

[0051] The accuracy of the sth test is χ s , the test data for the sth test is y s , the xth feedback data of the sth test is f s,x , the correlation between test data and feedback data is

[0052] Calculate satisfaction:

[0053]

[0054] The satisfaction of the sth test is φ s , the error factor is ε, and the matching degree between the test data and the feedback data is The feedback duration of the sth test is T s , the slowest feedback time that customers can accept is T min , the set response time of the sth test is T o ;

[0055] When the satisfaction rate is lower than 0.539, the feedback data is ambiguous and corrected to obtain the corrected data, which is expressed as:

[0056]

[0057] The xth correction data is The number of topics in the feedback data is The center of the pth cluster is D p ,theme The matching degree with the cluster center is The decision function of the correction data is C(x), the deviation factor is μ, and the mth topic of the xth correction data is The objective weight of the mth topic is ζ m, the xth feedback data is f x ,theme The distance from the cluster center is

[0058] The matching degree between the corrected data and the cluster center is calculated, the cluster centers are sorted in descending order according to the matching degree, the corrected data is divided into the first cluster center, and the corrected division result is output as the third data.

[0059] Second, the coal chemical industry standard data classification system based on artificial intelligence includes:

[0060] Data acquisition module: used to collect coal chemical industry standard data and feedback data, and pre-process the coal chemical industry standard data and the feedback data;

[0061] Extraction and classification module: used for performing feature extraction on the coal chemical industry standard data to obtain standard feature data, and performing association clustering on the standard feature data to obtain first data;

[0062] Classification and comparison module: used for classifying the standard characteristic data according to energy to obtain second data, and comparing the first data with the second data to obtain consistent data and fuzzy data;

[0063] Correction output module: used for correcting the fuzzy data according to the feedback data to obtain third data, and outputting the consistent data and the third data as classification results.

[0064] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0065] 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.

[0066] In a fourth 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.

[0067] The beneficial effects of the present invention are:

[0068] The present invention is a coal chemical industry standard data classification method and system based on artificial intelligence. Compared with the prior art, the present invention has the following technical effects:

[0069] The present invention can improve the accuracy of coal chemical industry standard data classification based on artificial intelligence through preprocessing, feature extraction, association clustering, feature classification, data comparison and classification correction steps, thereby improving the accuracy of coal chemical industry standard data classification based on artificial intelligence, and optimizing the coal chemical industry standard data classification based on artificial intelligence, which can greatly save resources and improve work efficiency, and can realize intelligent classification of coal chemical industry standard data based on artificial intelligence, and classify and correct the coal chemical industry standard data classification based on artificial intelligence in real time, which is of great significance to coal chemical industry standard data classification based on artificial intelligence, can adapt to coal chemical industry standard data classification of different standards and different coal chemical industry standard data classification requirements, and has a certain universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 This is a flowchart of the steps of the coal chemical industry standard data classification method based on artificial intelligence of the present invention;

[0071] Figure 2 It is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION

[0072] 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.

[0073] The coal chemical industry standard data classification method and system based on artificial intelligence of the present invention comprises the following steps:

[0074] like Figure 1 As shown, in this embodiment, the following steps are included:

[0075] Collecting coal chemical industry standard data and feedback data, and preprocessing the coal chemical industry standard data and the feedback data;

[0076] In actual evaluation, feedback data includes test content, response time, and feedback content;

[0077] The three coal chemical industry standard data including the production process, energy consumption and safety standards of coal chemical products were taken as the research objects;

[0078] Performing feature extraction on the coal chemical industry standard data to obtain standard feature data, and performing association clustering on the standard feature data to obtain first data;

[0079] In the actual evaluation, standard characteristic data include energy consumption, number of safety accidents, production efficiency, and safety standards; the first data: 1 group of high correlation includes coal chemical industry standard 1 and coal chemical industry standard 3, and 2 groups of low correlation include coal chemical industry standard 2;

[0080] Classifying the standard characteristic data according to energy to obtain second data, and comparing the first data with the second data to obtain consistent data and fuzzy data;

[0081] In the actual evaluation, the second data: 1 group of single energy is coal chemical industry standard 1, 2 groups of mixed energy include coal chemical industry standard 2 and coal chemical industry standard 3; consistent data are coal chemical industry standard 1 and coal chemical industry standard 2, and fuzzy data are coal chemical industry standard 3;

[0082] Correcting the fuzzy data according to the feedback data to obtain third data, and outputting the consistent data and the third data as a classification result;

[0083] In the actual evaluation, the third data: Group 1 includes coal chemical industry standard 1, and Group 2 includes coal chemical industry standard 2 and coal chemical industry standard 3.

[0084] In this embodiment, the method for extracting features from the coal chemical industry standard data to obtain standard feature data includes:

[0085] Text data is obtained by text extraction of standard data of coal chemical industry. The weight of words in the text data is quantified according to the part of speech. When the part of speech is noun and verb, the initial weight of the word is 0.8; when the part of speech is adjective and adverb, the initial weight of the word is 0.6; when the part of speech is other parts of speech, the initial weight of the word is 0;

[0086] Calculate the semantic coupling similarity of word pairs:

[0087] β(b w ,b z )=(1-ω)·CuR(b w ,b z )+ω·CvR(b w ,b z )

[0088] CuR(b w ,b z )=CS(P1(b w ),P1(b z ))

[0089] CvR w ,b z )=CS(P2(b w 0,P2(b z ))

[0090] P1(b w )=(P1(b1|b w ),P1(b2|b w ),R,P1(bv |b w ),R,P1(b N1 |b w ))

[0091]

[0092] P2(b w )=(P2(b1|b w ),P2(b2|b w ),R,P2(b v |b w ),R,P2(b N1 |b w ))

[0093]

[0094] The relation strength function is CS(·,·), and the zth word is b z , the wth word is b w , the word pair is (b z ,b w ), word pair (b z ,b w ) is CuR(b w ,b z ), word pair (b z ,b w ) is CvR(b w ,b z ), the text set is U, the total number of texts is |U|, the word pair (b z ,b w ) in the probability of P1(b z |b w ), word b z and word b w The shortest path between z ,b w ), the decision parameter is ω, the word pair (b z ,b w The frequency of occurrence is DF(b z ,b w ), in the text set word b w The probability distribution of w ), word b w The similar probability distribution of w ), word b z and word b w The similarity between them is P2(b w |b z ), word pair (b z ,bw ) in the text set is P1(b z |b w ), the single text in the text set is u, the first word is b1, the second word is b2, and the vth word is b v , the N1th word is b N1 , the number of texts in the text set is N1, word pairs (b z ,b w The number of occurrences in a single text u is TPF((b z ,b w ),u);

[0095] Calculate the similarity between word attributes:

[0096]

[0097] The wth word attribute is a w , the attribute of the zth word is a z , word attribute a w and word attribute a z The similarity is The square of the Euclidean norm is The positive control parameter is η,

[0098] Build a text graph based on the text set, use the words as the feature terms of the text graph, and calculate the feature term weights:

[0099] θ(t+1)=(1-γ)·Q·θ(t)+γ·β·θ(t)

[0100]

[0101] The damping coefficient is γ, and the structural feature similarity between the t-th iteration feature term w and the feature term z is Q w,z , the similarity between word attributes is β, the feature word weight vector of the t-th iteration is θ(t), the feature word weight vector of the t+1-th iteration is θ(t+1), and the structural feature similarity is Q;

[0102] Continue to iterate until all feature terms are traversed, obtain the feature term weight vector, and output the feature term weight vector as standard feature data.

[0103] In this embodiment, the method of performing association clustering on the standard feature data to obtain first data includes:

[0104] Construct a feature data set based on standard feature data and calculate the kernel density gradient:

[0105]

[0106] The kernel function is G(·), and the standard feature data g c The kernel density gradient is K(g c ), the cth standard feature data is g c , the number of standard feature data is M, and the bandwidth parameter of dimension σ is The standard characteristic data is g;

[0107] Calculate the relevance of standard feature data:

[0108]

[0109] The fuzzy neighborhood radius of the standard feature data is The association decision is W, the feature data set is S, the fuzzy neighborhood radius is Z, and the standard feature data is g c The fuzzy neighborhood particle size of the key data set is Z S (g c ), standard characteristic data g c The fuzzy neighborhood particle for association decision is Z W (g c ), the standard constant is δ, and the bandwidth parameter is The cth standard characteristic data is g c , kernel density gradient estimate is K(·), standard feature data g c The correlation degree is

[0110] Cluster the standard feature data according to the correlation to obtain clusters, and take the standard feature data with the largest kernel density gradient as the cluster center;

[0111] The fuzzy standard feature data are sorted into clusters according to the correlation, and the fuzzy standard feature data are divided into clusters with the largest correlation to obtain fuzzy clusters; and the clustering results are output as cluster first data.

[0112] In this embodiment, the method for obtaining the second data by classifying the standard characteristic data according to energy sources includes:

[0113] The energy type of the standard characteristic data is obtained according to the standard data of the coal chemical industry. The standard characteristic data containing only one type of energy is classified into a single energy data set, otherwise it is classified into a mixed energy data set;

[0114] The hybrid energy is sorted in descending order according to its importance, and the standard characteristic data of the hybrid energy data set is labeled according to the sorting; and the single energy data set and the hybrid energy data set are output as the second data.

[0115] In this embodiment, the method of comparing the first data and the second data to obtain consistent data and fuzzy data includes:

[0116] Calculate the similarity between the first data and the second data:

[0117]

[0118] The first data of the rth category in the i-th category is h i,r , the jth second data of the i-th category is d i,j , the first data h i,r and the second data d i,j The similarity is The number of first data of the i-th category is M h , the number of second data of the i-th category is M d , the control factor is α, and the optimization coefficient is

[0119] When the similarity is greater than 0.681, the corresponding first data or second data is classified as consistent data, otherwise the first data and the second data are classified as fuzzy data.

[0120] In this embodiment, the method of correcting the fuzzy data according to the feedback data to obtain the third data includes:

[0121] Calculate the accuracy based on the feedback data:

[0122]

[0123] The accuracy of the sth test is χ s , the test data for the sth test is y s , the xth feedback data of the sth test is f s,x , the correlation between test data and feedback data is

[0124] Calculate satisfaction:

[0125]

[0126] The satisfaction of the sth test is φ s , the error factor is ε, and the matching degree between the test data and the feedback data is The feedback duration of the sth test is T s , the slowest feedback time that customers can accept is T min , the set response time of the sth test is T o ;

[0127] When the satisfaction rate is lower than 0.539, the feedback data is ambiguous and corrected to obtain the corrected data, which is expressed as:

[0128]

[0129] The xth correction data is The number of topics in the feedback data is The center of the pth cluster is D p ,theme The matching degree with the cluster center is The decision function of the correction data is C(x), the deviation factor is μ, and the mth topic of the xth correction data is The objective weight of the mth topic is ζ m , the xth feedback data is f x ,theme The distance from the cluster center is

[0130] The matching degree between the corrected data and the cluster center is calculated, the cluster centers are sorted in descending order according to the matching degree, the corrected data is divided into the first cluster center, and the corrected division result is output as the third data.

[0131] Second, the coal chemical industry standard data classification system based on artificial intelligence includes:

[0132] Data acquisition module: used to collect coal chemical industry standard data and feedback data, and pre-process the coal chemical industry standard data and the feedback data;

[0133] Extraction and classification module: used for performing feature extraction on the coal chemical industry standard data to obtain standard feature data, and performing association clustering on the standard feature data to obtain first data;

[0134] Classification and comparison module: used for classifying the standard characteristic data according to energy to obtain second data, and comparing the first data with the second data to obtain consistent data and fuzzy data;

[0135] Correction output module: used for correcting the fuzzy data according to the feedback data to obtain third data, and outputting the consistent data and the third data as classification results.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a standard data classification device for the coal chemical industry based on artificial intelligence at the logical level. The processor executes the program stored in the memory and is specifically used to execute any of the aforementioned standard data classification methods for the coal chemical industry based on artificial intelligence.

[0140] The above application Figure 1The coal chemical industry standard data classification method based on artificial intelligence 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 the form of software. 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.

[0141] The electronic device may also perform Figure 1 The coal chemical industry standard data classification method based on artificial intelligence is implemented Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0142] 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, which, when executed by an electronic device including multiple applications, executes any of the aforementioned artificial intelligence-based coal chemical industry standard data classification methods.

[0143] 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 in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0144] 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.

[0145] 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.

[0146] 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 A step that specifies a function in one or more boxes.

[0147] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0148] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0149] 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.

[0150] 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.

[0151] 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 in combination with 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.) that contain computer-usable program code.

[0152] 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 data classification method for the coal chemical industry based on artificial intelligence, characterized in that: The following steps are involved: Collecting coal chemical industry standard data and feedback data, and preprocessing the coal chemical industry standard data and the feedback data; Performing feature extraction on the coal chemical industry standard data to obtain standard feature data, and performing association clustering on the standard feature data to obtain first data; Classifying the standard characteristic data according to energy to obtain second data, and comparing the first data with the second data to obtain consistent data and fuzzy data; The fuzzy data is corrected according to the feedback data to obtain third data, and the consistent data and the third data are output as classification results.

2. The coal chemical industry standard data classification method based on artificial intelligence according to claim 1 is characterized in that: The method for extracting features from the coal chemical industry standard data to obtain standard feature data comprises: Text data is obtained by text extraction of standard data of coal chemical industry. The weight of words in the text data is quantified according to the part of speech. When the part of speech is noun and verb, the initial weight of the word is 0.8; when the part of speech is adjective and adverb, the initial weight of the word is 0.6; when the part of speech is other parts of speech, the initial weight of the word is 0; Calculate the semantic coupling similarity of word pairs: β(b w ,b z )=(1-ω)·CuR(b w ,b z )+ω·CvR(b w ,b z ) CuR(b w ,b z )=CS(P1(b w ),P1(b z )) CvR(b w ,b z )=CS(P2(b w ),P2(b z )) P1(b w )=(P1(b1|b w ),P1(b2|b w ),R,P1(b v |b w ),R,P1(b N1 |b w )) P2(b w )=(P2(b1|b w ),P2(b2|b w ),R,P2(b v |b w ),R,P2(b N1 |b w )) The relation strength function is CS(·,·), and the zth word is b z , the wth word is b w , the word pair is (b z ,b w ), word pair (b z ,b w ) is CuR(b w ,b z ), word pair (b z ,b w ) is CvR(b w ,b z ), the text set is U, the total number of texts is |U|, the word pair (b z ,b w ) in the probability of P1(b z |b w ), word b z and word b w The shortest path between z ,b w ), the decision parameter is ω, the word pair (b z ,b w ) appears at a frequency of DF(b z ,b w ), in the text set word b w The probability distribution of w ), word b w The similar probability distribution of w ), word b z and word b w The similarity between them is P2(b w |b z ), word pair (b z ,b w ) in the text set is P1(b z |b w ), the single text in the text set is u, the first word is b1, the second word is b2, and the vth word is b v , the N1th word is b N1 , the number of texts in the text set is N1, word pairs (b z ,b w ) appears in a single text u is TPF((b z ,b w ),u); Calculate the similarity between word attributes: The wth word attribute is a w , the attribute of the zth word is a z , word attribute a w and word attribute a z The similarity is The square of the Euclidean norm is The positive control parameter is η, Build a text graph based on the text set, use the words as the feature terms of the text graph, and calculate the feature term weights: θ(t+1)=(1-γ)·Q·θ(t)+γ·β·θ(t) The damping coefficient is γ, and the structural feature similarity between the t-th iteration feature term w and the feature term z is Q w,z , the similarity between word attributes is β, the feature word weight vector of the t-th iteration is θ(t), the feature word weight vector of the t+1-th iteration is θ(t+1), and the structural feature similarity is Q; Continue to iterate until all feature terms are traversed, obtain the feature term weight vector, and output the feature term weight vector as standard feature data.

3. The coal chemical industry standard data classification method based on artificial intelligence according to claim 1 is characterized in that: The method of performing association clustering on the standard feature data to obtain first data includes: Construct a feature data set based on standard feature data and calculate the kernel density gradient: The kernel function is G(·), and the standard feature data g c The kernel density gradient is K(g c ), the cth standard feature data is g c , the number of standard feature data is M, and the bandwidth parameter of dimension σ is The standard characteristic data is g; Calculate the relevance of standard feature data: The fuzzy neighborhood radius of the standard feature data is The association decision is W, the feature data set is S, the fuzzy neighborhood radius is Z, and the standard feature data is g c The fuzzy neighborhood particle size of the key data set is Z S (g c ), standard characteristic data g c The fuzzy neighborhood particle for association decision is Z W (g c ), the standard constant is δ, the bandwidth parameter is m, and the cth standard characteristic data is g c , kernel density gradient estimate is K(·), standard feature data g c The correlation degree is Cluster the standard feature data according to the correlation to obtain clusters, and take the standard feature data with the largest kernel density gradient as the cluster center; The fuzzy standard feature data are sorted into clusters according to the correlation, and the fuzzy standard feature data are divided into clusters with the largest correlation to obtain fuzzy clusters; and the clustering results are output as cluster first data.

4. The coal chemical industry standard data classification method based on artificial intelligence according to claim 1 is characterized in that: The method for obtaining second data by classifying the standard characteristic data according to energy sources comprises: The energy type of the standard characteristic data is obtained according to the standard data of the coal chemical industry. The standard characteristic data containing only one type of energy is classified into a single energy data set, otherwise it is classified into a mixed energy data set; The hybrid energy is sorted in descending order according to its importance, and the standard characteristic data of the hybrid energy data set is labeled according to the sorting; and the single energy data set and the hybrid energy data set are output as the second data.

5. The coal chemical industry standard data classification method based on artificial intelligence according to claim 1 is characterized in that: The method for comparing the first data and the second data to obtain consistent data and fuzzy data includes: Calculate the similarity between the first data and the second data: The first data of the rth category in the i-th category is h i,r , the jth second data of the i-th category is d i,j , the first data h i,r and the second data d i,j The similarity is The number of first data of the i-th category is M h , the number of second data of the i-th category is M d , the control factor is α, and the optimization coefficient is When the similarity is greater than 0.681, the corresponding first data or second data is classified as consistent data, otherwise the first data and the second data are classified as fuzzy data.

6. The coal chemical industry standard data classification method based on artificial intelligence according to claim 1 is characterized in that: The method for obtaining third data by correcting the fuzzy data according to the feedback data includes: Calculate the accuracy based on the feedback data: The accuracy of the sth test is χ s , the test data for the sth test is y s , the xth feedback data of the sth test is f s,x , the correlation between test data and feedback data is l(f,y); Calculate satisfaction: The satisfaction of the sth test is φ s , the error factor is ε, the matching degree between the test data and the feedback data is θ(f,y), and the feedback time of the sth test is T s The slowest feedback time that customers can accept is T min , the set response time of the sth test is T o ; When the satisfaction rate is lower than 0.539, the feedback data is ambiguous and corrected to obtain the corrected data, which is expressed as: The xth correction data is The number of topics in the feedback data is The center of the pth cluster is D p ,theme The matching degree with the cluster center is The decision function of the correction data is C(x), the deviation factor is μ, and the mth topic of the xth correction data is The objective weight of the mth topic is ζ m , the xth feedback data is f x ,theme The distance from the cluster center is The matching degree between the corrected data and the cluster center is calculated, the cluster centers are sorted in descending order according to the matching degree, the corrected data is divided into the first cluster center, and the corrected division result is output as the third data.

7. A coal chemical industry standard data classification system based on artificial intelligence, used to execute the method described in any one of claims 1 to 6, characterized in that: include: Data acquisition module: used to collect coal chemical industry standard data and feedback data, and pre-process the coal chemical industry standard data and the feedback data; Extraction and classification module: used for performing feature extraction on the coal chemical industry standard data to obtain standard feature data, and performing association clustering on the standard feature data to obtain first data; Classification and comparison module: used for classifying the standard characteristic data according to energy to obtain second data, and comparing the first data with the second data to obtain consistent data and fuzzy data; Correction output module: used for correcting the fuzzy data according to the feedback data to obtain third data, and outputting the consistent data and the third data as classification results.

8. 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.

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

Images