Word bank updating method and device, storage medium and electronic equipment

Abstract

The invention discloses a lexicon updating method and device, a storage medium and electronic equipment, and the lexicon updating method comprises the steps: obtaining a to-be-processed text source; extracting a target hot word from the to-be-processed text source by adopting an NLP technology; classifying the target hot words by using a neural network model, and calculating first weight values of the target hot words; comparing the target hot words with a target word library according to a classification result; and updating the target word bank based on the comparison result and the first weight value. According to the scheme, the timeliness and accuracy of hot word recommendation can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a vocabulary updating method, device, storage medium and electronic device. Background Art

[0002] Hot words are a high-level summary of current hot events. Generally speaking, hot words are keywords associated with a certain event, and through these hot words, you can quickly understand the current hot events. For example, in the field of information and communications technology (ICT), users can search for relevant information content through hot words, which allows users to quickly and conveniently understand the hot information in the ICT field in the recent period of time.

[0003] The core of hot word recommendation is to continuously update and improve the word library to ensure the timeliness and accuracy of hot word recommendation. However, in the process of word library update, many manual review steps are often required, resulting in a delayed response to the newly appeared hot words on the Internet. Summary of the invention

[0004] The embodiments of the present application provide a vocabulary updating method, device, storage medium and electronic device, which can improve the timeliness of hot word recommendations.

[0005] In a first aspect, an embodiment of the present application provides a vocabulary updating method, comprising:

[0006] Get the text source to be processed;

[0007] Using NLP technology to extract target hot words from the text source to be processed;

[0008] Using a neural network model to classify the target hot words, and calculating a first weight value of the target hot words;

[0009] Comparing the target hot word with the target word library according to the classification result;

[0010] The target vocabulary is updated based on the comparison result and the first weight value.

[0011] In the vocabulary updating method provided in the embodiment of the present application, the updating of the target vocabulary based on the comparison result and the first weight value includes:

[0012] Determine the current weight value of the target hot word according to the comparison result and the first weight value;

[0013] The hot words in the target vocabulary are sorted according to the current weight values ​​to generate an updated target vocabulary.

[0014] In the word library updating method provided in the embodiment of the present application, determining the current weight value of the target hot word according to the comparison result and the first weight value includes:

[0015] If the target hot word exists in the target word library, the second weight value of the target hot word is updated according to the first weight value, and the updated second weight value is used as the current weight value of the target hot word;

[0016] If the target hot word does not exist in the target word library, the target hot word is added to the target word library, and a current weight value is assigned to the target hot word according to the first weight value.

[0017] In the vocabulary updating method provided in the embodiment of the present application, the method of extracting target hot words from the text source to be processed by using NLP technology includes:

[0018] Using NLP word segmentation tools to perform word segmentation on the text source to be processed to obtain a number of vocabulary units;

[0019] Performing a first screening on a number of the vocabulary units to obtain a number of primary hot words;

[0020] A second screening is performed on some of the primary hot words to obtain target hot words.

[0021] In the vocabulary updating method provided in the embodiment of the present application, the first screening of the plurality of vocabulary units to obtain a plurality of primary hot words includes:

[0022] By using an NLP word frequency counting tool, the frequency of occurrence of each of the vocabulary units in the text source to be processed is counted;

[0023] A plurality of primary hot words are selected from the plurality of vocabulary units based on the frequencies.

[0024] In the word library updating method provided in the embodiment of the present application, the second screening of the plurality of primary hot words to obtain the target hot words includes:

[0025] Performing semantic analysis on some of the primary hot words to determine whether the primary hot words meet the contextual requirements of a specific field or industry;

[0026] The primary hot words that meet the context requirements are used as target hot words.

[0027] In the vocabulary updating method provided in the embodiment of the present application, the step of obtaining the text source to be processed includes:

[0028] Use custom crawlers to obtain the text source to be processed from the web page.

[0029] In a second aspect, an embodiment of the present application provides a vocabulary updating device, comprising:

[0030] An acquisition unit, used for acquiring a text source to be processed;

[0031] An extraction unit, used for extracting target hot words from the text source to be processed by using NLP technology;

[0032] A classification unit, used to classify the target hot word by using a neural network model, and calculate a first weight value of the target hot word;

[0033] A comparison unit, used for comparing the target hot word with a target word library according to the classification result;

[0034] An updating unit is used to update the target vocabulary based on the comparison result and the first weight value.

[0035] In a third aspect, the present application provides a storage medium storing a plurality of instructions suitable for loading by a processor to execute any of the above-mentioned vocabulary updating methods.

[0036] In a fourth aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-described vocabulary updating methods when executing the computer program.

[0037] In summary, the vocabulary updating method provided in the embodiment of the present application includes obtaining a text source to be processed; extracting target hot words from the text source to be processed using NLP technology; classifying the target hot words using a neural network model and calculating a first weight value of the target hot words; comparing the target hot words with a target vocabulary based on the classification result; and updating the target vocabulary based on the comparison result and the first weight value. This solution can automatically update the vocabulary and remove the manual review step, which can ensure timeliness while avoiding the error probability of manual review, thereby improving the efficiency and accuracy of vocabulary updates, thereby improving the timeliness and accuracy of hot word recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 It is a structural diagram of a vocabulary updating system provided in an embodiment of the present application.

[0040] Figure 2 It is a flowchart of the vocabulary updating method provided in the embodiment of the present application.

[0041] Figure 3 It is a structural diagram of a vocabulary updating device provided in an embodiment of the present application.

[0042] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0044] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0045] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0047] In the description of the present application, it should be noted that the terms "upper", "lower", "left", "right", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present application. In addition, terms such as "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0048] The core of hot word recommendation is to continuously update and improve the word library to ensure the timeliness and accuracy of hot word recommendation. However, in the process of word library update, many manual review steps are often required, resulting in a delayed response to the newly appeared hot words on the Internet.

[0049] Based on this, the embodiments of the present application provide a vocabulary updating method, device, storage medium and electronic device. Specifically, the vocabulary updating device can be integrated in an electronic device, which can be a server or a terminal; wherein the terminal can include a mobile phone, a wearable smart device, a tablet computer, a laptop computer, and a personal computer (PC); the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0050] See also Figure 1 , Figure 1A schematic diagram of the structure of the vocabulary update system provided by the embodiment of the present application. The system may include at least one electronic device 1000, at least one server or personal computer 2000. The electronic device 1000 held by the user can be connected to different servers or personal computers through a network. The electronic device 1000 may be an electronic device with computing hardware that can support and execute software products corresponding to multimedia. In addition, the electronic device 1000 may also have one or more multi-touch screens for sensing and obtaining the input of the user through touch or sliding operations performed at multiple points on one or more touch-sensitive display screens. In addition, the electronic device 1000 can be interconnected with the server or personal computer 2000 through a network. The network may be a wireless network or a wired network, such as a wireless network such as a wireless local area network (WLAN), a local area network (LAN), a cellular network, a 2G network, a 3G network, a 4G network, a 5G network, etc. In addition, different electronic devices 1000 may also use their own Bluetooth network or hotspot network to connect to other embedded platforms or to servers and personal computers, etc.

[0051] Among them, the electronic device includes a touch display screen and a processor, and the touch display screen is used to present a graphical user interface and receive operation instructions generated by the user acting on the graphical user interface. When the user operates the graphical user interface through the touch display screen, the graphical user interface can control the local content of the electronic device by responding to the received operation instructions, and can also control the content of the server side by responding to the received operation instructions. For example, the operation instructions generated by the user acting on the graphical user interface include instructions for processing the initial audio signal, and the processor is configured to start the corresponding application after receiving the instructions provided by the user. In addition, the processor is configured to render and draw a graphical user interface associated with the application on the touch display screen. The touch display screen is a multi-touch sensitive screen that can sense touch or sliding operations performed simultaneously at multiple points on the screen. The user uses a finger to perform a touch operation on the graphical user interface, and when the graphical user interface detects the touch operation, the corresponding operation is displayed in the graphical user interface of the control application.

[0052] The technical solutions shown in the present application will be described in detail below through specific embodiments. It should be noted that the description order of the following embodiments is not intended to limit the priority order of the embodiments.

[0053] See also Figure 2 , Figure 2 : is a flow chart of a vocabulary updating method provided in an embodiment of the present application. The specific flow of the vocabulary updating method may be as follows:

[0054] 101. Obtain the text source to be processed.

[0055] Specifically, a customized crawler may be used to obtain the text source to be processed from a web page.

[0056] It is understandable that the text source to be processed may include social media posts, news reports, blog articles, forum discussions, etc., thereby covering a variety of information channels.

[0057] Among them, a customized crawler refers to a web crawler customized according to specific needs. By simulating browser behavior, it can automatically access the target web page and deeply parse elements such as HTML, CSS, and JavaScript in the web page to extract the required text source.

[0058] For example, ICT consulting agencies can use customized crawlers to obtain the latest information about ICT from various websites to provide users with timely ICT industry information content, so that users can understand the latest trends in the ICT industry. News agencies can use customized crawlers to obtain the latest reports from other news websites, realize automatic aggregation and classification of news, and provide readers with a more personalized reading experience. E-commerce platforms can use customized crawlers to crawl competitor product information, understand market price trends and consumer reviews, and thus optimize their pricing and sales strategies.

[0059] 102. Use NLP technology to extract target hot words from the text source to be processed.

[0060] Among them, Natural Language Processing (NLP) technology plays an increasingly important role in modern text analysis, especially in extracting key information from large amounts of text data. For example, extracting target hot words from the text source to be processed.

[0061] NLP technology can provide an effective tool for the extraction of target hot words. In some embodiments, NLP technology can accurately split the text source to be processed into individual words or phrases through advanced word segmentation algorithms, providing basic data for subsequent analysis. Then, using methods such as word frequency statistics and TF-IDF, NLP technology can calculate the frequency of occurrence of each word in the text source to be processed, thereby screening out primary hot words. After that, sentiment analysis technology is used to analyze the context expressed by the primary hot words, thereby screening out the target hot words.

[0062] That is, the step of "using NLP technology to extract target hot words from the text source to be processed" may include:

[0063] Use NLP word segmentation tools to segment the text source to be processed and obtain several vocabulary units;

[0064] Perform a first screening on a number of vocabulary units to obtain a number of primary hot words;

[0065] A second screening is performed on several primary hot words to obtain target hot words.

[0066] It can be understood that the first screening of several vocabulary units is the process of using the NLP word frequency statistics tool to count the frequency of occurrence of each vocabulary unit. Specifically, the NLP word frequency statistics tool can be used to count the frequency of occurrence of each vocabulary unit in the text source to be processed; and a number of primary hot words can be screened out from the vocabulary units based on the frequency.

[0067] In a specific implementation process, a preset frequency may be set, and then the frequency of occurrence of each vocabulary unit in the text source to be processed is compared with the preset frequency, and the vocabulary units with a frequency higher than the preset frequency are used as primary hot words.

[0068] It can be understood that the second screening of several primary hot words is the process of analyzing the context expressed by the primary hot words by sentiment analysis technology. Specifically, semantic analysis can be performed on several primary hot words to determine whether the primary hot words meet the context requirements of a specific field or industry; and the primary hot words that meet the context requirements are used as target hot words.

[0069] For example, there is a preset text library about ICT industry information, and you want to extract hot words related to the ICT industry. Through the word segmentation function of NLP technology, the text can be split into individual words. Then, use the word frequency statistics tool to screen out high-frequency words closely related to the ICT industry. These high-frequency words are primary hot words, which can intuitively reflect the public's concerns and action directions for the ICT industry. At the same time, through sentiment analysis technology, it is possible to further determine whether the primary hot words meet the contextual requirements of the ICT industry, and use the primary hot words that meet the contextual requirements of the ICT industry as target hot words. In this embodiment, the target hot words are obtained by performing a secondary screening on the text source to be processed (after the first screening and the second screening in sequence) to ensure the accuracy of the hot word recommendation.

[0070] 103. Classify the target hot words using a neural network model and calculate the first weight value of the target hot words.

[0071] Among them, the neural network model can be a convolutional neural network (CNN) model or a recurrent neural network (RNN) model.

[0072] In the specific implementation process, the neural network model can be trained in advance by collecting a large data set. It is understandable that the data set should contain various types of hot words and the categories they belong to. For example, hot words can be divided into different categories such as ICT, technology, entertainment, sports, politics, etc.

[0073] During the model training process, each hot word can be represented as a vector that contains the feature information of the hot word. Then, the vector is input into the neural network, and the category to which each hot word belongs is preset as the output of the neural network. The neural network will learn how to classify hot words by adjusting its internal weights and bias items to minimize prediction errors. It should be noted that during the model training process, the neural network can use the latest deep learning architecture, such as BERT or its variants, for text analysis to ensure accurate identification of hot words in different contexts.

[0074] When the neural network model is trained, the neural network model can be used to calculate the first weight value of the target hot word. Specifically, the target hot word can be represented as a vector and then input into the neural network model. The neural network can generate a prediction result based on the feature information and weight values ​​it has learned, and the prediction result is the probability distribution of the category to which the target hot word belongs. After that, the weight value corresponding to the category with the highest probability in the probability distribution can be used as the first weight value of the target hot word.

[0075] It should be noted that in actual application, the first weight value can be calculated not only based on the frequency of occurrence of the target hot word, but also by using a word frequency statistical method (such as TF-IDF) to calculate the total number of times the target hot word appears in the text, thereby obtaining the first weight value of the target hot word. f It can be as follows: f =C d / C t Among them, C t is the number of times the target hot word appears in the document, C d is the total number of words in the document.

[0076] In some embodiments, multiple factors such as the context of the target hot word, user interaction (such as likes, shares, comments), etc. can also be comprehensively considered to improve the accuracy of the first weight value.

[0077] Specifically, natural language processing technology can be used to calculate the sentiment tendency of the target hot word context and obtain a sentiment score: W c = Sentiment score, where W c is the context weight of the target hot word, and its value range is between 0 and 1. After collecting user interaction data related to the target hot word (such as likes, shares, comments, etc.), the interaction weight can be calculated according to the quantity and quality of the interaction (such as the positivity of the comments), as follows: i =α·L+β·S+γ·C. Among them, W iis the interaction weight, L is the number of likes, S is the number of shares, C is the number of comments, α, β and γ are the weight coefficients of various interactions, which can be adjusted according to actual conditions. Finally, the first weight value W can be obtained by comprehensively considering the frequency of occurrence of the target hot word, the context environment, and the user's interaction as follows: W = ω 1 ·W f +ω 2 ·W c +ω 3 ·W i Among them, ω 1 ,ω 2 and ω 3 is the weight ratio of each part, which reflects the importance of frequency, context and interaction respectively. 1 ,ω 2 and ω 3 The size can be adjusted according to actual conditions.

[0078] For example, suppose the target hot word appears 50 times, the total number of words in the document is 1000, the context sentiment score is 0.8, the number of likes is 100, the number of shares is 50, the number of comments is 20, α=1, β=1.5, γ=2, ω 1 ,ω 2 and ω 3 are 0.4, 0.3 and 0.3 respectively. Then, we can calculate: W f =50 / 1000=0.05,W c =0.8, Wi=1·100+1.5·50+2·20=100+75+40=215. The final first weight value W=0.4·0.05+0.3·0.8+0.3·215=0.02+0.24+64.5=64.76.

[0079] 104. Compare the target hot words with the target vocabulary according to the classification results.

[0080] It is understandable that the category of the target word library is the same as the category of the target hot word. For example, when the category of the target hot word is the ICT industry, the target word library is the ICT industry word library.

[0081] The construction of the target vocabulary is based on the analysis and processing of a large amount of data, ensuring the comprehensiveness and accuracy of its content. The target vocabulary not only includes professional terms within the industry, but also covers vocabulary in other fields closely related to the ICT industry, such as artificial intelligence, big data, cloud computing, etc. In addition, the target vocabulary will be updated regularly to reflect the latest trends and technological advances in industry development. In this way, the target vocabulary can provide users with a dynamic and real-time industry vocabulary resource to help users better understand and grasp the latest developments in the ICT industry.

[0082] When comparing the target hot word with the target vocabulary according to the classification result, first find the target vocabulary belonging to the same classification as the target hot word according to the classification of the target hot word in step 103, and compare the target hot word with the corresponding target vocabulary to confirm whether the target hot word exists in the target vocabulary.

[0083] 105. Update the target vocabulary based on the comparison result and the first weight value.

[0084] Specifically, the current weight value of the target hot word can be determined according to the comparison result and the first weight value; the hot words in the target word library are sorted according to the current weight value to generate an updated target word library.

[0085] Among them, if the target hot word exists in the target vocabulary, the second weight value of the target hot word is updated according to the first weight value, and the updated second weight value is used as the current weight value of the target hot word; if the target hot word does not exist in the target vocabulary, the target hot word is added to the target vocabulary, and the current weight value is assigned to the target hot word according to the first weight value.

[0086] It is understandable that the second weight value is the current weight value of the target hot word in the target word library. When the target hot word exists in the target word library, the current weight value of the target hot word can be adjusted according to the first weight value, so that the current weight value of the target hot word has real-time performance.

[0087] In some embodiments, the hot words in the target word library whose weight values ​​are lower than a threshold value may also be deleted to maintain the efficiency and accuracy of the target word library. This deletion operation may be performed regularly or irregularly and may be adjusted according to actual needs.

[0088] In some embodiments, after the target word library is updated, the target word library can be displayed to the technicians through views (such as hot word cloud charts, trend charts, etc.) so that the technicians can intuitively understand the analysis results.

[0089] In summary, the vocabulary updating method provided in the embodiment of the present application can be obtained by obtaining the text source to be processed; using NLP technology to extract the target hot words from the text source to be processed; using a neural network model to classify the target hot words and calculate the first weight value of the target hot words; comparing the target hot words with the target vocabulary according to the classification results; and updating the target vocabulary based on the comparison results and the first weight value. This solution can automatically update the vocabulary and remove the manual review step, which can ensure timeliness while avoiding the error probability of manual review, thereby improving the efficiency and accuracy of vocabulary updates, thereby improving the timeliness and accuracy of hot word recommendations.

[0090] In order to better implement the word library updating method provided in the embodiment of the present application, the embodiment of the present application also provides a word library updating device, wherein the meaning of the nouns is the same as that in the above-mentioned word library updating method, and the specific implementation details can refer to the description in the method embodiment.

[0091] See also Figure 3 , Figure 3 201 is a schematic diagram of the structure of the vocabulary updating device provided in the embodiment of the present application. The vocabulary updating device may include an acquisition unit 201, an extraction unit 202, a classification unit 203, a comparison unit 204 and an update unit 205.

[0092] An acquisition unit 201 is used to acquire a text source to be processed;

[0093] An extraction unit 202 is used to extract target hot words from the text source to be processed using NLP technology;

[0094] The classification unit 203 is used to classify the target hot word by using the neural network model and calculate the first weight value of the target hot word;

[0095] A comparison unit 204, used to compare the target hot word with the target word library according to the classification result;

[0096] The updating unit 205 is used to update the target vocabulary based on the comparison result and the first weight value.

[0097] The specific implementation of each of the above units can refer to the above-mentioned embodiment of the vocabulary updating method, which will not be described one by one here.

[0098] In summary, the vocabulary updating device provided in the embodiment of the present application can obtain the text source to be processed through the acquisition unit 201; the extraction unit 202 uses NLP technology to extract the target hot words from the text source to be processed; the classification unit 203 uses the neural network model to classify the target hot words and calculate the first weight value of the target hot words; the comparison unit 204 compares the target hot words with the target vocabulary according to the classification result; the update unit 205 updates the target vocabulary based on the comparison result and the first weight value. This solution can automatically update the vocabulary and remove the manual review step, which can ensure timeliness in time while avoiding the error probability of manual review, thereby improving the efficiency of vocabulary update and thus improving the timeliness of hot word recommendation.

[0099] The present application also provides an electronic device, in which the vocabulary updating device of the present application can be integrated, such as Figure 4As shown, it shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application, which includes a memory 301, a processor 302, and a computer program stored in the memory 301 and executable on the processor 302, wherein the processor 302 implements the above-mentioned vocabulary update method in the embodiment of the present application when executing the computer program.

[0100] In the above embodiments, the description of each embodiment has its own focus. For the part that is not described in detail in a certain embodiment, please refer to the detailed description of the vocabulary updating method above, and will not be repeated here.

[0101] It should be noted that, for the vocabulary updating method in the embodiment of the present application, those skilled in the art can understand that all or part of the processes of the vocabulary updating method in the embodiment of the present application can be implemented by controlling the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, such as in the memory of a terminal, and executed by at least one processor in the terminal. During the execution process, it may include the processes of the embodiment of the vocabulary updating method.

[0102] For the vocabulary updating device of the embodiment of the present application, each functional module can be integrated into a processing chip, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of software functional modules. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0103] To this end, an embodiment of the present application provides a storage medium in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any of the word library updating methods provided in the embodiments of the present application. The storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), etc.

[0104] The above respectively introduces in detail the vocabulary updating method, device, storage medium and electronic device provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the core idea of ​​the present application; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A vocabulary updating method, characterized in that: include: Get the text source to be processed; Using NLP technology to extract target hot words from the text source to be processed; Classifying the target hot words using a neural network model, and calculating a first weight value of the target hot words; Comparing the target hot word with the target word library according to the classification result; The target vocabulary is updated based on the comparison result and the first weight value.

2. The word library updating method according to claim 1, characterized in that: The updating of the target vocabulary based on the comparison result and the first weight value includes: Determine the current weight value of the target hot word according to the comparison result and the first weight value; The hot words in the target vocabulary are sorted according to the current weight values ​​to generate an updated target vocabulary.

3. The word library updating method according to claim 2, characterized in that: The determining the current weight value of the target hot word according to the comparison result and the first weight value includes: If the target hot word exists in the target word library, the second weight value of the target hot word is updated according to the first weight value, and the updated second weight value is used as the current weight value of the target hot word; If the target hot word does not exist in the target word library, the target hot word is added to the target word library, and a current weight value is assigned to the target hot word according to the first weight value.

4. The word library updating method according to claim 1, characterized in that: The extracting target hot words from the text source to be processed by using NLP technology includes: Using NLP word segmentation tools to perform word segmentation on the text source to be processed to obtain a number of vocabulary units; Performing a first screening on a number of the vocabulary units to obtain a number of primary hot words; A second screening is performed on some of the primary hot words to obtain target hot words.

5. The word library updating method according to claim 4, characterized in that: The first screening of the plurality of vocabulary units obtains a plurality of primary hot words, including: By using an NLP word frequency counting tool, the frequency of occurrence of each of the vocabulary units in the text source to be processed is counted; A plurality of primary hot words are selected from the plurality of vocabulary units based on the frequencies.

6. The word library updating method according to claim 4, characterized in that: The second screening of the plurality of primary hot words to obtain target hot words includes: Performing semantic analysis on some of the primary hot words to determine whether the primary hot words meet the contextual requirements of a specific field or industry; The primary hot words that meet the context requirements are used as target hot words.

7. The word library updating method according to claim 1, characterized in that: The step of obtaining the text source to be processed includes: Use custom crawlers to obtain the text source to be processed from the web page.

8. A vocabulary updating device, characterized in that: include: An acquisition unit, used for acquiring a text source to be processed; An extraction unit, used for extracting target hot words from the text source to be processed by using NLP technology; A classification unit, used to classify the target hot word by using a neural network model, and calculate a first weight value of the target hot word; A comparison unit, used for comparing the target hot word with a target word library according to the classification result; An updating unit is used to update the target vocabulary based on the comparison result and the first weight value.

9. A storage medium, characterized in that: The storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the vocabulary updating method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for updating the vocabulary library as claimed in any one of claims 1 to 7 is implemented.

Images