Standard system classification method and device, storage medium and electronic equipment

Abstract

The invention relates to a standard system classification method and device, a storage medium and electronic equipment, and the method comprises the steps: obtaining a standard data text, and carrying out the recognition of the standard data text, and obtaining a standard text content; performing word segmentation processing on the standard text content to obtain a keyword group; word vectors are generated based on the keyword groups; and executing clustering operation according to the word vectors to obtain a standard system classification result. According to the method, the standard system can be classified more scientifically and effectively by performing recognition, word segmentation, clustering and the like on the standard data text.

Description

Technical Field

[0001] The present disclosure relates to the field of resource and environmental technology, and in particular, to a standard system classification method, device, storage medium and electronic device. Background Art

[0002] The standard system refers to a scientific and organic whole formed by the internal connections of standards within a certain range. The standard system is a unified and coordinated whole. The various standards in the standard system have some internal connections and cooperate with each other. However, the relevant technology cannot classify the various standard systems well, so how to classify the standard systems scientifically and effectively is a technical problem that needs to be solved urgently. Summary of the invention

[0003] The purpose of the present disclosure is to provide a standard system classification method, device, storage medium and electronic device, through which various standard systems can be classified scientifically and effectively.

[0004] In order to achieve the above-mentioned object, the present disclosure provides a standard system classification method in a first aspect, the method comprising:

[0005] Acquire standard data text, and identify the standard data text to obtain standard text content;

[0006] Performing word segmentation processing on the standard text content to obtain keyword groups;

[0007] Generate a word vector based on the keyword group;

[0008] A clustering operation is performed based on the word vectors to obtain a standard system classification result.

[0009] Optionally, the word segmentation processing of the standard text content to obtain the keyword group includes:

[0010] Performing word segmentation processing on the standard text content to obtain candidate phrases;

[0011] A keyword screening operation is performed based on the candidate word group, wherein the keyword screening operation is used to remove stop words in the candidate word group to obtain the keyword group.

[0012] Optionally, the stop words are phrases that have no effect on the clustering operation, and the stop words include at least one of ambiguous words, modal particles, and punctuation marks.

[0013] Optionally, generating a word vector based on the keyword group includes:

[0014] generating a word frequency based on the keyword group;

[0015] The word vector is determined according to the word frequency and the word frequency-inverse document frequency TF-IDF.

[0016] Optionally, generating a word vector based on the keyword group further includes:

[0017] Generate the word vector according to the word-vector Word2Vec algorithm and the keyword group; or

[0018] The word vector is generated according to the text-to-vector Doc2Vec algorithm and the keyword group.

[0019] Optionally, the method further comprises:

[0020] Adjust the existing standard system based on the classification results of the standard system; or

[0021] A new standard system is constructed based on the classification results of the standard system.

[0022] Optionally, the standard document text includes chemical park risk prevention and control standards.

[0023] A second aspect of the present disclosure provides a standard system classification device, the device comprising:

[0024] An acquisition module is used to acquire standard document text and identify the standard document text to obtain the content of the standard text;

[0025] A processing module, used for performing word segmentation processing on the standard text content to obtain a keyword group;

[0026] A generating module, used for generating a word vector based on the keyword group;

[0027] The clustering module is used to perform clustering operations according to the word vectors to obtain standard system classification results.

[0028] A third aspect of the present disclosure provides a non-temporary computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described in the first aspect when executed by a processor.

[0029] A fourth aspect of the present disclosure provides an electronic device, the electronic device comprising:

[0030] a memory having a computer program stored thereon;

[0031] A processor is used to execute the computer program in the memory to implement the steps of the method described in the first aspect.

[0032] Through the above technical solution, the standard data text is first obtained and recognized to obtain the standard text content, and then the obtained standard text content is segmented to obtain a keyword group. On this basis, a word vector is generated based on the keyword group, and a clustering operation is performed based on the word vector to obtain a standard system classification result. In this way, the embodiment of the present disclosure can scientifically and effectively realize the classification of the standard system.

[0033] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0035] Figure 1 The present invention is a flow chart showing a standard system classification method according to an exemplary embodiment.

[0036] Figure 2 The figure is an example diagram of a standard system classification result in a standard system classification method according to an exemplary embodiment.

[0037] Figure 3 It is a framework diagram of the classification of risk prevention and control standards for chemical parks in a standard system classification method according to an exemplary embodiment.

[0038] Figure 4 The present invention is a flow chart showing a standard system classification method according to another exemplary embodiment.

[0039] Figure 5 The figure is a block diagram of a standard system classification device according to an exemplary embodiment.

[0040] Figure 6 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0041] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0042] It should be understood that the various steps described in the method implementation of the present disclosure may be performed in different orders and / or in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect. The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the description below.

[0043] It should be noted that the concepts of "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0044] The embodiments of the present disclosure are not exhaustive, but are only illustrative of some embodiments, and are not intended to be a specific limitation on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment can be arbitrarily exchanged. In addition, the optional implementation methods in a certain embodiment can be arbitrarily combined; in addition, the embodiments can be arbitrarily combined, for example, some or all of the steps of different embodiments can be arbitrarily combined, and a certain embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0045] In each embodiment of the present disclosure, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between the embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form a new embodiment based on their internal logical relationships.

[0046] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure.

[0047] At present, the architecture of the technical standard system in the relevant fields is not clear enough, and the standardization technical committees (TCs) responsible for standard establishment are independent of each other, resulting in a lack of scientificity and overall coordination in the standard establishment plans in the relevant fields. Many standard-setting units usually only pursue the number of standards to be established, and arbitrarily split the standards, splitting the content that should belong to one standard into many standards, resulting in poor coordination of the standard system.

[0048] In order to solve the above problems, the embodiments of the present disclosure provide a standard system classification method, device, storage medium and electronic device to solve the scientificity and coordination problems of the structure of technical standard systems in existing related fields.

[0049] Figure 1 is a flow chart showing a standard system classification method according to an exemplary embodiment, which is applied to electronic devices, such as Figure 1 As shown, the method comprises the following steps:

[0050] In step S110, the standard document text is acquired and recognized to obtain the standard text content.

[0051] In some embodiments, the electronic device may obtain a standard document text, which may be pre-stored in the electronic device, collected and obtained through the network, or generated by the user according to needs. The standard document text may include information such as the standard number, standard name, standard status, and standard use profession and part.

[0052] As an optional method, after acquiring the standard document text, the embodiment of the present disclosure may perform text recognition on the standard document text to acquire the text content, that is, obtain the standard text content through text recognition.

[0053] In a specific implementation, the standard document may include a chemical park risk prevention and control standard, that is, the disclosed embodiment may classify the chemical park risk prevention and control standard system. In other words, the standard system of the disclosed embodiment may be a chemical park risk prevention and control standard system.

[0054] In step S120, the standard text content is segmented to obtain keyword groups.

[0055] As an optional method, after obtaining the standard text content, the embodiment of the present disclosure can perform a word segmentation operation, that is, perform word segmentation on the standard text content to obtain a keyword group. Specifically, the standard text content is processed by a conditional random field word segmentation algorithm to obtain multiple phrases, which can be used as keyword groups.

[0056] In step S130, a word vector is generated based on the keyword group.

[0057] As an optional method, after obtaining the keyword group, the embodiment of the present disclosure can generate a word vector based on the keyword group, and the word vector can be generated based on Word2Vec (word to vector), Doc2vec (document to vector), TF-IDF (Term Frequency-Inverse Document Frequency) or keyword frequency method. It should be noted that the process of generating word vectors can also be called the process of clustering analysis vectorization.

[0058] Here, word frequency refers to the frequency of a word appearing in a text, word frequency = (number of times a word appears in a text / total number of words in the text). Inverse document frequency is a measure of the importance of a word. The fewer texts that contain a word, the more important the word is to the text. For example, the inverse document frequency of a word = log (total number of texts in the text set / (texts containing the word + 1)).

[0059] In a specific implementation, the disclosed embodiment can generate word frequencies based on keyword groups, and on this basis, determine the word vector corresponding to the standard document text according to the word frequencies and word frequency-inverse document frequency TF-IDF.

[0060] In another specific embodiment, the disclosed embodiment can generate a word vector corresponding to the standard document text according to the word-vector Word2Vec algorithm and the keyword group. Optionally, the disclosed embodiment can also generate a word vector corresponding to the standard document text according to the text-vector Doc2Vec algorithm and the keyword group. The specific method of obtaining the word vector corresponding to the standard document text is not explicitly limited here and can be selected according to the actual situation.

[0061] It should be noted that the process of generating word vectors based on keyword groups in the embodiment of the present disclosure can be a process of constructing a word vector space model for keyword groups to achieve structured representation of text content. Here, the structured text representation can represent the distance between each keyword group in a spatial manner.

[0062] As another optional method, the embodiment of the present disclosure can generate different word vectors based on the keyword group, and on this basis, use the word vectors as the classification basis to form N data clusters, and these N data clusters can also be used as word vectors. In other words, the embodiment of the present disclosure can perform cluster analysis on the N data clusters to obtain a standard system classification result, that is, enter step S140.

[0063] In step S140, a clustering operation is performed based on the word vectors to obtain a standard system classification result.

[0064] In some implementations, after obtaining the word vectors, the embodiments of the present disclosure may perform a clustering operation based on the word vectors to obtain a standard system classification result. Specifically, the word vectors are analyzed using a clustering analysis method.

[0065] Here, the clustering analysis method may include at least one of the following: K-Means clustering, mean shift clustering, density-based spatial clustering of applications with noise (DBSCAN), expectation-maximization (EM) clustering using a Gaussian mixed model (GMM), agglomerative hierarchical clustering, and graph community detection (Graph Community Detection) clustering.

[0066] Here, the cluster analysis method may be a set of statistical analysis techniques for dividing standard specifications into relatively homogeneous groups (clusters), that is, the cluster analysis method of the present disclosure may be used to analyze existing standards or standards to be issued to divide them into relatively homogeneous groups.

[0067] In the embodiment of the present disclosure, clustering operations performed on word vectors can be unsupervised learning, and unsupervised learning can be based on not relying on predefined classes or training instances with class labels. The clustering operation can automatically determine the observational learning of the labels, that is, the clustering operation in the embodiment of the present disclosure can determine the internal connection of the existing standards. In this way, the embodiment of the present disclosure can assist the artificial generation of the standard system, making the classification of the standard system more scientific and more coordinated.

[0068] In a specific implementation, the standard system may be a chemical park risk prevention and control standard system, that is, the classification work of the chemical park risk prevention and control standard system may be completed through the standard system classification method shown in the embodiment of the present disclosure.

[0069] Specifically, the embodiment of the present disclosure can vectorize 38 items of chemical park risk prevention and control related standards through the Doc2vec method. On this basis, the vectorized coordinates of the chemical park risk prevention and control related standards are clustered by the k-means method, and the standards are divided into 5 categories to obtain the standard system classification results, as shown in detail. Figure 2 shown.

[0070] pass Figure 2It is known that after clustering the 38 standards related to risk prevention and control in chemical parks, the classification results of the standard system can include five categories, among which the first category 101 can be class 0, which can be the preliminary planning of a chemical park; the second category 102 can be class 1, which can be the engineering construction of a chemical park; the third category 103 can be class 2, which can be the operation and management of a chemical park; the fourth category 104 can be class 3, which can be the evaluation and assessment of a chemical park; the fifth category 105 can be class 4, which can be a smart chemical park.

[0071] In order to clearly understand the above classification, the present disclosure embodiment provides the following Figure 3 The standard classification framework diagram shown in Figure 3 It is known that the risk prevention and control standard system of chemical parks can include five categories, which can be chemical park preliminary planning, chemical park engineering construction, chemical park operation management, chemical park evaluation and assessment, and chemical park evaluation and assessment.

[0072] It should be noted that the process of performing clustering operations based on word vectors can be a process of constructing a clustering algorithm model based on structured word vectors, and learning to obtain the classification results of the text based on the clustering algorithm model, and the result is the standard system classification result. In addition, after obtaining the standard system classification result, the embodiment of the present disclosure can visualize the standard system classification result. The specific display effect can be as follows: Figure 2 shown.

[0073] The embodiment of the present disclosure obtains standard data text and identifies the standard data text to obtain standard text content, and then performs word segmentation processing on the obtained standard text content to obtain keyword groups. On this basis, a word vector is generated based on the keyword group, and a clustering operation is performed based on the word vector to obtain a standard system classification result. In this way, the embodiment of the present disclosure can scientifically and effectively realize the classification of the standard system.

[0074] Figure 4 is a flow chart showing a standard system classification method according to another exemplary embodiment, which is applied to electronic devices, such as Figure 4 As shown, the method comprises the following steps:

[0075] In step S210, the standard data text is obtained and recognized to obtain the standard text content.

[0076] The specific implementation of step S210 has been described in detail in the above embodiment, and will not be repeated here.

[0077] In step S220, the standard text content is segmented to obtain keyword groups.

[0078] As an optional method, after obtaining the standard text content, the embodiment of the present disclosure can first perform word segmentation processing on the standard text content to obtain candidate phrases. On this basis, a keyword screening operation is performed based on the candidate phrases, and the keyword screening operation is used to remove stop words in the candidate phrases to obtain keyword phrases.

[0079] In the disclosed embodiment, the stop words may be phrases that have no effect on the clustering operation, that is, the stop words may be phrases that have no effect on the text classification features. Specifically, the stop words may include at least one of a word with ambiguous meaning, an modal particle, and a punctuation mark. In other words, in the process of performing a keyword screening operation on a candidate phrase, the disclosed embodiment may screen out stop words such as a word with ambiguous meaning, an modal particle, and a punctuation mark, and then these screened stop words may be deleted, and the remaining phrases may be used as keyword phrases.

[0080] In step S230, a word vector is generated based on the keyword group.

[0081] In step S240, a clustering operation is performed based on the word vectors to obtain a standard system classification result.

[0082] The specific implementation of step S230 to step S240 has been described in detail in the above embodiment, and will not be repeated here.

[0083] In step S250, the existing standard system is adjusted based on the standard system classification result; or, a new standard system is constructed based on the standard system classification result.

[0084] As an optional manner, after obtaining the standard system classification result, the embodiment of the present disclosure may make adjustments based on the standard system classification result, or may also construct a new standard system based on the standard system classification result.

[0085] Specifically, the embodiment of the present disclosure may first obtain an existing standard system, which may include multiple different categories, which may be classified according to human experience, or may be obtained through historical clustering operations. After obtaining the existing standard system, the embodiment of the present disclosure may compare and analyze the standard system classification results with the existing standard system to obtain a comparison analysis result. On this basis, the existing standard system is adjusted according to the comparison analysis result, or a new standard system is created.

[0086] As a specific implementation, the system targeted by the standard system classification results is the target standard system. After obtaining the comparison analysis results, the disclosed embodiment can determine whether there are classifications that do not belong to the target standard system in the classification results of the standard system obtained at the current moment based on the comparison analysis results. If there is a first classification that does not belong to the target standard system, determine the first standard system in which the first classification is located. On this basis, determine whether the first classification is located in a place where the first standard system is adjacent to the target standard system. If it is not located in an adjacent place, the first classification can be adjusted to the first standard system. Here, the first standard system belongs to an existing standard system.

[0087] As another specific implementation, if it is determined that the first classification does not belong to any existing standard system, the embodiment of the present disclosure may construct a new standard system based on the standard system classification result (first classification).

[0088] The disclosed embodiment obtains the standard document text and identifies the standard document text to obtain the standard text content, and then performs word segmentation processing on the obtained standard text content to obtain a keyword group, on this basis, generates a word vector based on the keyword group, and performs a clustering operation based on the word vector to obtain a standard system classification result, so that the disclosed embodiment can scientifically and effectively realize the classification of the standard system. In addition, the disclosed embodiment can adjust the existing standard system based on the obtained standard system classification result, or construct a new standard system, so that it can not only assist in the artificial generation of a more scientific and coordinated standard system, but also can propose further adaptive modification suggestions for the first draft of the standard and discover the gaps in the standard system.

[0089] Figure 5 is a block diagram of a standard system classification device 300 according to an exemplary embodiment. Figure 5 The standard system classification device 300 shown may include an acquisition module 310 , a processing module 320 , a generation module 330 and a clustering module 340 .

[0090] The acquisition module 310 is used to acquire the standard document text, and identify the standard document text to obtain the standard text content;

[0091] The processing module 320 is used to perform word segmentation processing on the standard text content to obtain a keyword group;

[0092] The generating module 330 is used to generate a word vector based on the keyword group;

[0093] The clustering module 340 is used to perform a clustering operation according to the word vector to obtain a standard system classification result.

[0094] In some implementations, the processing module 320 may include:

[0095] A word segmentation submodule, used to perform word segmentation processing on the standard text content to obtain candidate phrases;

[0096] The screening submodule is used to perform a keyword screening operation based on the candidate phrase, wherein the keyword screening operation is used to remove stop words in the candidate phrase to obtain the keyword phrase.

[0097] In some implementations, the stop words are phrases that have no effect on the clustering operation, and the stop words include at least one of ambiguous words, modal particles, and punctuation marks.

[0098] In some implementations, the generating module 330 is further configured to generate a word frequency based on the keyword group; and determine the word vector according to the word frequency and word frequency-inverse document frequency TF-IDF.

[0099] In some implementations, the generation module 330 is further configured to generate the word vector according to a word-vector Word2Vec algorithm and the keyword group; or to generate the word vector according to a text-vector Doc2Vec algorithm and the keyword group.

[0100] In some embodiments, the standard system classification device 300 may further include:

[0101] An adjustment module is used to adjust the existing standard system based on the standard system classification result; or a creation module is used to construct a new standard system based on the standard system classification result.

[0102] In some embodiments, the standard document includes chemical park risk prevention and control standards.

[0103] The embodiment of the present disclosure obtains standard data text and identifies the standard data text to obtain standard text content, and then performs word segmentation processing on the obtained standard text content to obtain keyword groups. On this basis, a word vector is generated based on the keyword group, and a clustering operation is performed based on the word vector to obtain a standard system classification result. In this way, the embodiment of the present disclosure can scientifically and effectively realize the classification of the standard system.

[0104] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0105] Figure 6 FIG. 7 is a block diagram of an electronic device 700 according to an exemplary embodiment. Figure 6As shown, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0106] The processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned standard system classification method. The memory 702 is used to store various types of data to support the operation of the electronic device 700, and these data may include, for example, instructions for any application or method used to operate on the electronic device 700, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 702 or sent through the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 705 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0107] In an exemplary embodiment, the electronic device 700 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned standard system classification method.

[0108] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned standard system classification method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions can be executed by the processor 701 of the electronic device 700 to complete the above-mentioned standard system classification method.

[0109] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device, and the computer program has a code portion for executing the above-mentioned standard system classification method when executed by the programmable device.

[0110] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0111] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0112] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A standard system classification method, characterized in that: The method comprises: Acquire standard data text, and identify the standard data text to obtain standard text content; Performing word segmentation processing on the standard text content to obtain keyword groups; Generate a word vector based on the keyword group; A clustering operation is performed based on the word vectors to obtain a standard system classification result.

2. The method according to claim 1, characterized in that The word segmentation process of the standard text content to obtain a keyword group includes: Performing word segmentation processing on the standard text content to obtain candidate phrases; A keyword screening operation is performed based on the candidate word group, wherein the keyword screening operation is used to remove stop words in the candidate word group to obtain the keyword group.

3. The method according to claim 2, characterized in that The stop words are phrases that have no effect on the clustering operation, and the stop words include at least one of ambiguous words, modal particles, and punctuation marks.

4. The method according to claim 1, characterized in that The generating a word vector based on the keyword group includes: generating a word frequency based on the keyword group; The word vector is determined according to the word frequency and the word frequency-inverse document frequency TF-IDF.

5. The method according to claim 1, characterized in that: The generating of word vectors based on the keyword group further includes: Generate the word vector according to the word-vector Word2Vec algorithm and the keyword group; or The word vector is generated according to the text-to-vector Doc2Vec algorithm and the keyword group.

6. The method according to claim 1, characterized in that The method further comprises: Adjust the existing standard system based on the classification results of the standard system; or A new standard system is constructed based on the classification results of the standard system.

7. The method according to any one of claims 1 to 6, characterized in that: The standard document text includes risk prevention and control standards for chemical parks.

8. A standard system classification device, characterized in that: The device comprises: An acquisition module is used to acquire standard document text and identify the standard document text to obtain the content of the standard text; A processing module, used for performing word segmentation processing on the standard text content to obtain a keyword group; A generating module, used for generating a word vector based on the keyword group; The clustering module is used to perform clustering operations according to the word vectors to obtain standard system classification results.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 7.

Images