A processing method for bulletin automatic classification
By obtaining the title and body of the announcement, and using keyword and irrelevant word libraries for matching and word segmentation, the problem of high classification error rate in automated announcement classification is solved, achieving more efficient and accurate classification results.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SUZHOU LANGDONG NET TEC CO LTD
- Filing Date
- 2022-12-06
- Publication Date
- 2026-07-21
AI Technical Summary
In the existing technology, it is impossible to effectively achieve automated classification of announcements, especially in the processing method, there is a problem of high classification error rate.
By obtaining the title and body of the announcement to be categorized, the keyword thesaurus and irrelevant word thesaurus are used for matching to determine the category of the announcement. If the judgment result does not meet the classification rules, word segmentation is performed to obtain a more accurate classification result.
It improved the accuracy and efficiency of announcement classification, reduced the error rate, and ensured the precision of the classification results.
Smart Images
Figure CN115827864B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of natural language processing technology, and in particular to a method for automatically classifying announcements. Background Technology
[0002] As the market develops, announcements have become an important channel for information dissemination. Consequently, users have an increasing demand for precise categorization of announcements. However, currently, companies cover a wide range of industries, resulting in a diverse range of announcement types and a large amount of content, making it difficult for users to quickly filter announcements related to their specific field.
[0003] In related technologies, the main text of announcements is extracted, analyzed, and frequently occurring words are extracted for automated classification. However, announcements contain a large amount of text and cover a wide range of topics, resulting in a high error rate when using automated classification methods. Summary of the Invention
[0004] Therefore, it is necessary to provide a processing method for automatically classifying announcements to address the aforementioned technical problems. This method can determine the first category of the announcement to be classified, and then classify the announcement title and announcement body according to a keyword thesaurus and an irrelevant word thesaurus to obtain the category of the announcement to be classified.
[0005] Firstly, this application provides a method for automatically classifying announcements. The method includes:
[0006] Obtain announcements to be categorized, the announcements to be categorized including announcement title and announcement body; determine the first category of the announcements to be categorized, and determine the target thesaurus corresponding to the announcements to be categorized in the category configuration table based on the first category, the category configuration table storing thesaurus corresponding to different categories of announcements in a pre-set manner, the thesaurus including keyword thesaurus and irrelevant word thesaurus;
[0007] The target thesaurus is used to match the announcement title of the announcement text to be classified, and it is determined whether the announcement title conforms to the classification rules. The classification rules include that the announcement title includes at least one keyword from the keyword thesaurus and does not contain any irrelevant words from the irrelevant word thesaurus.
[0008] If the judgment result is consistent with the classification rules, the classification result of the announcement text to be classified is determined based on the keywords in the matched target thesaurus.
[0009] In one embodiment, the method further includes:
[0010] If the judgment result does not conform to the classification rules, the announcement body of the announcement text to be classified is matched with the target thesaurus to determine whether the announcement body conforms to the classification rules. The classification rules include that the announcement body includes at least one keyword from the keyword thesaurus and does not contain any irrelevant words from the irrelevant word thesaurus.
[0011] If the judgment result is consistent with the classification rules, the classification result of the announcement text to be classified is determined based on the keywords in the matched target thesaurus.
[0012] In one embodiment, if the judgment result does not conform to the classification rules, the word segmentation process is repeated, and the corresponding target word library is obtained according to the classification configuration table.
[0013] In one embodiment, the word segmentation process includes combining a single character or at least two adjacent characters in the announcement title or body to obtain candidate words, and determining the category of the announcement to be classified based on the target word library.
[0014] In one embodiment, the first category of the announcement to be classified includes at least one category, and the category of the announcement to be classified is obtained according to the degree of matching between the announcement to be classified and the classification configuration table.
[0015] Secondly, this application also provides a processing apparatus for automatically classifying announcements. The apparatus includes:
[0016] The acquisition module is used to acquire announcements to be categorized, which include the announcement title and the announcement body.
[0017] The classification module is used to determine the first category of the announcement to be classified, and to determine the target thesaurus corresponding to the announcement to be classified in the classification configuration table based on the first category. The classification configuration table stores the thesaurus corresponding to different categories of announcements in a pre-set manner. The thesaurus includes a keyword thesaurus and an irrelevant word thesaurus.
[0018] The discrimination module is used to match the announcement title of the announcement text to be classified using the target thesaurus, and to determine whether the announcement title conforms to the classification rules. The classification rules include that the announcement title includes at least one keyword from the keyword thesaurus and does not contain any irrelevant words from the irrelevant word thesaurus.
[0019] The matching module is used to determine the classification result of the announcement text to be classified based on the keywords in the target thesaurus if the judgment result is consistent with the classification rules.
[0020] In one embodiment, the device further includes:
[0021] If the judgment result does not conform to the classification rules, the announcement body of the announcement text to be classified is matched with the target thesaurus to determine whether the announcement body conforms to the classification rules. The classification rules include that the announcement body includes at least one keyword from the keyword thesaurus and does not contain any irrelevant words from the irrelevant word thesaurus.
[0022] If the judgment result is consistent with the classification rules, the classification result of the announcement text to be classified is determined based on the keywords in the matched target thesaurus.
[0023] In one embodiment, if the judgment result does not conform to the classification rules, the word segmentation process is repeated, and the corresponding target word library is obtained according to the classification configuration table.
[0024] In one embodiment, the word segmentation process includes combining a single character or at least two adjacent characters in the announcement title or body to obtain candidate words, and determining the category of the announcement to be classified based on the target word library.
[0025] In one embodiment, the first category of the announcement to be classified includes at least one category, and the category of the announcement to be classified is obtained according to the degree of matching between the announcement to be classified and the classification configuration table.
[0026] Thirdly, this disclosure also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of a processing method for automatically classifying announcements.
[0027] Fourthly, this disclosure also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of a processing method for automatically classifying announcements.
[0028] Fifthly, this disclosure also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of a processing method for automatically classifying announcements.
[0029] The above-mentioned method for automatically classifying announcements has at least the following beneficial effects:
[0030] The embodiments provided in this disclosure can determine the first category of the announcement to be classified. The announcement title is segmented according to a thesaurus to obtain relevant keywords and irrelevant words. If no relevant keywords are obtained or irrelevant words are included, the announcement text can be segmented, and then the category of the announcement to be classified can be obtained according to a classification configuration table.
[0031] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0032] To more clearly illustrate the technical solutions in the embodiments or conventional technologies of this disclosure, the accompanying drawings used in the description of the embodiments or conventional technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0033] Figure 1 This is an application environment diagram of a method for automatically classifying announcements in one embodiment;
[0034] Figure 2 This is a flowchart illustrating a method for automatically classifying announcements in one embodiment;
[0035] Figure 3 This is a schematic diagram of a classification configuration table in one embodiment;
[0036] Figure 4 This is a flowchart illustrating the automated classification process for announcements in another embodiment;
[0037] Figure 5 This is a structural block diagram of a processing device for automated classification of announcements in one embodiment;
[0038] Figure 6 This is an internal structural diagram of a computer device in one embodiment;
[0039] Figure 7 This is an internal structure diagram of a server in one embodiment. Detailed Implementation
[0040] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.
[0041] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims. The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitation, the presence of other identical or equivalent elements in a process, method, product, or apparatus that includes said elements is not excluded. For example, the use of terms such as "first," "second," etc., is to denote names and does not indicate any specific order.
[0042] This disclosure provides a method for automatically classifying announcements, which can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located in the cloud or on other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.
[0043] In some embodiments of this disclosure, such as Figure 2 As shown, a method for automatically classifying announcements is provided, which can be applied to... Figure 1 The method is illustrated using the example of a server processing announcements to be categorized. It is understood that this method can be applied to a server, and also to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In a specific embodiment, the method may include the following steps:
[0044] S202: Obtain announcements to be categorized, including announcement title and announcement body.
[0045] A notice to be categorized can include a title and a body. The title and body can include keywords, related keywords, and irrelevant words. Keywords, related keywords, and irrelevant words can each consist of at least one character. The keyword thesaurus stores synonyms and near-synonyms of the keywords, i.e., related keywords. The irrelevant word thesaurus stores words that should not be included in the notice title or body. For example, if the category of the notice to be categorized is annual financial report, generally, the target thesaurus in the category configuration table should not contain words such as semi-annual financial report or quarterly financial report. Therefore, the keyword thesaurus for the first category of annual financial report can store words such as "annual" and "financial," while the irrelevant word thesaurus can store words such as "semi-annual financial report" and "quarterly financial report."
[0046] S204: Determine the first category of the announcement to be classified, and determine the target thesaurus corresponding to the announcement to be classified in the classification configuration table based on the first category. The classification configuration table stores the thesaurus corresponding to different categories of announcements in a pre-set manner. The thesaurus includes a keyword thesaurus and an irrelevant word thesaurus.
[0047] The first category of the announcement to be categorized can be determined based on methods such as original classification or manual classification. The original classification can be a classification system constructed using general classification methods, which may include some misclassified or inaccurate classifications. Categories that do not conform to the rules can be deleted or inaccurate categories can be reclassified based on the original classification to obtain the first category of the announcement to be categorized. The classification configuration table can store a pre-set thesaurus corresponding to different categories of announcements. The announcement title can be segmented based on the thesaurus, which may include a keyword thesaurus and an irrelevant word thesaurus. The character length range for segmentation can be determined based on the character length of the thesaurus. For example, if the longest character group in the thesaurus belonging to the first category of the announcement to be categorized is determined to be 5 characters, then the announcement to be categorized can be segmented into a maximum of 5 characters during the segmentation process, which helps to improve the classification speed.
[0048] S206: Use the target thesaurus to match the announcement title of the announcement text to be classified, and determine whether the announcement title conforms to the classification rules. The classification rules include that the announcement title includes at least one keyword from the keyword thesaurus and does not contain any irrelevant words from the irrelevant word thesaurus.
[0049] By segmenting the announcement title using the target thesaurus, we can obtain the first candidate words. The first candidate words can include three cases: including keywords but excluding irrelevant words; including keywords and irrelevant words; or excluding keywords. If the first candidate words include irrelevant words or do not include keywords, then no classification result can be obtained based on the title to be classified.
[0050] In some embodiments of this disclosure, if the first candidate term includes keywords but excludes irrelevant words, the classification result of the announcement to be classified can be obtained based on the announcement title. If the first candidate term includes keywords and irrelevant words, the classification result of the announcement to be classified cannot be obtained. If the first candidate term does not include keywords, regardless of whether it includes irrelevant words, the classification result of the announcement to be classified cannot be obtained.
[0051] S208: If the judgment result is consistent with the classification rules, the classification result of the announcement text to be classified is determined based on the keywords in the matched target thesaurus.
[0052] If the first candidate word meets the classification rules, that is, it includes keywords but does not include irrelevant words, then the classification result of the announcement text to be classified can be determined based on the keywords in the matched target thesaurus.
[0053] In the above-mentioned method for automatically classifying announcements, the first category of the announcement to be classified can be determined, and then the target thesaurus corresponding to the announcement to be classified in the classification configuration table can be determined. The thesaurus includes a keyword thesaurus and an irrelevant word thesaurus. The announcement title of the announcement to be classified can be matched according to the target thesaurus. If the matching judgment result between the target thesaurus and the announcement title of the announcement to be classified is consistent with the classification rules, the classification result of the announcement text to be classified can be determined based on the keywords in the matched target thesaurus.
[0054] In some embodiments of this disclosure, the method further includes:
[0055] If the judgment result does not conform to the classification rules, the announcement body of the announcement text to be classified is matched with the target thesaurus to determine whether the announcement body conforms to the classification rules. The classification rules include that the announcement body includes at least one keyword from the keyword thesaurus and does not contain any irrelevant words from the irrelevant word thesaurus.
[0056] If the judgment result is consistent with the classification rules, the classification result of the announcement text to be classified is determined based on the keywords in the matched target thesaurus.
[0057] If the matching result between the target thesaurus and the announcement title of the announcement text to be classified does not meet the classification rules, the announcement text can be segmented according to the thesaurus to obtain second candidate words, and the announcement to be classified can be judged again. The second candidate words may include keywords and irrelevant words.
[0058] like Figure 3 The diagram shown is a schematic representation of a classification configuration table in one embodiment. The classification configuration table includes multiple thesauruses, which may include keyword thesauruses and irrelevant word thesauruses.
[0059] In some embodiments of this disclosure, if the announcement text includes relevant keywords but excludes irrelevant words, it conforms to the target thesaurus, and the category of the announcement to be classified is obtained. If the announcement text includes both keywords and irrelevant words, the category of the announcement to be classified cannot be obtained from the announcement text.
[0060] For example, if the first category of the announcement to be classified is "important report" according to the classification configuration table, the corresponding target thesaurus can be found. The first classification result may also correspond to multiple second classification results. The second classification result can be located based on the keyword thesaurus. If the second classification result is "annual report", irrelevant words can include words such as "half a year" and "entrusted", which can improve the accuracy of classification.
[0061] In some embodiments of this disclosure, if the judgment result does not conform to the classification rules, the word segmentation process is re-performed, and the corresponding target word library is obtained according to the classification configuration table.
[0062] Word segmentation may involve combining a single character or at least two adjacent characters from the announcement title or body to obtain candidate words, and then determining the category of the candidate words based on a dictionary. If the determination result does not conform to the classification rules, the announcement title and body can be segmented again to improve the accuracy of classification.
[0063] In some embodiments of this disclosure, the word segmentation process includes combining a single character or at least two adjacent characters in the announcement title or body to obtain candidate words, and determining the category of the announcement to be classified based on the target lexicon.
[0064] During word segmentation, the character length range can be determined based on the character length of the dictionary. The minimum segmentation result is a single character, while the maximum segmentation result is the longest character range in the dictionary corresponding to the category determined by the classification configuration table. Furthermore, adjacent character pairs can be combined during the segmentation process to improve recognition accuracy.
[0065] like Figure 4 The diagram shown is a flowchart illustrating an automated announcement classification method in one embodiment. The target thesaurus corresponding to the first category of the announcement to be classified can be determined. Then, based on the keyword thesaurus and the irrelevant word thesaurus, the title and body text to be classified are categorized to obtain the category of the announcement.
[0066] In some embodiments of this disclosure, the first category of the announcement to be classified includes at least one category, and the category of the announcement to be classified is obtained according to the degree of matching between the announcement to be classified and the classification configuration table.
[0067] When determining the first category of an announcement to be categorized, multiple first categories may be obtained. Therefore, during classification processing, a judgment can be made based on the thesaurus corresponding to multiple first categories. The most matching target thesaurus can be obtained according to the classification configuration table rules of the thesaurus. The classification configuration table rules can include keyword rules and irrelevant word rules. The category of the announcement to be categorized can be obtained based on the degree of matching between the announcement to be categorized and the classification configuration table rules. The degree of matching can be determined based on relevant keywords and irrelevant words. For example, if one of the first categories contains irrelevant words during word segmentation, then the other first categories are used for judgment. If none of the first categories contain irrelevant words, the classification result of the announcement to be categorized can be determined based on the number of keywords.
[0068] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.
[0069] Based on the same inventive concept, this disclosure also provides a processing apparatus for automatically classifying announcements, which implements the aforementioned processing method for automatically classifying announcements. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in the embodiments of the processing apparatus for automatically classifying announcements provided below can be found in the limitations of the processing method for automatically classifying announcements described above, and will not be repeated here.
[0070] The apparatus may include a system (including a distributed system), software (application), module, component, server, client, etc., that uses the methods described in the embodiments of this specification, combined with necessary hardware implementation. Based on the same innovative concept, the apparatuses in one or more embodiments provided in this disclosure are as described in the following embodiments. Since the implementation schemes and methods for solving the problem by the apparatus are similar, the implementation of the specific apparatus in the embodiments of this specification can refer to the implementation of the foregoing methods, and repeated details will not be repeated. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the apparatuses described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.
[0071] In one embodiment, such as Figure 5 As shown, a processing device 500 for automated announcement classification is provided. The device can be the aforementioned server, or a module, component, device, or unit integrated into the server. The device 500 may include:
[0072] The acquisition module 502 is used to acquire announcements to be classified, wherein the announcements to be classified include an announcement title and an announcement body;
[0073] The classification module 504 is used to determine the first category of the announcement to be classified, and to determine the target thesaurus corresponding to the announcement to be classified in the classification configuration table based on the first category. The classification configuration table stores the thesaurus corresponding to different categories of announcements in a pre-set manner. The thesaurus includes a keyword thesaurus and an irrelevant word thesaurus.
[0074] The discrimination module 506 is used to match the announcement title of the announcement text to be classified using the target thesaurus, and to determine whether the announcement title conforms to the classification rules. The classification rules include that the announcement title includes at least one keyword from the keyword thesaurus and does not contain any irrelevant words from the irrelevant word thesaurus.
[0075] The matching module 508 is used to determine the classification result of the announcement text to be classified based on the keywords in the target thesaurus if the judgment result is consistent with the classification rules.
[0076] In one embodiment, if the determination result does not conform to the classification rules, the target thesaurus is used to match the announcement body of the announcement text to be classified to determine whether the announcement body conforms to the classification rules. The classification rules include that the announcement body includes at least one keyword from the keyword thesaurus and does not contain any irrelevant words from the irrelevant word thesaurus.
[0077] If the judgment result is consistent with the classification rules, the classification result of the announcement text to be classified is determined based on the keywords in the matched target thesaurus.
[0078] In one embodiment, if the judgment result does not conform to the classification rules, the word segmentation process is repeated, and the corresponding target word library is obtained according to the classification configuration table.
[0079] In one embodiment, the word segmentation process includes combining a single character or at least two adjacent characters in the announcement title or body to obtain candidate words, and determining the category of the announcement to be classified based on the target lexicon.
[0080] In one embodiment, the first category of the announcement to be classified includes at least one category, and the category of the announcement to be classified is obtained according to the degree of matching between the announcement to be classified and the classification configuration table.
[0081] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
[0082] The modules in the aforementioned processing device for automated classification of announcements can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.
[0083] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores the categories of announcements to be categorized. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a massive keyword search method based on a finite deterministic automaton.
[0084] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for automatically classifying announcements. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.
[0085] Those skilled in the art will understand that Figure 6, Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the computer device to which the present disclosure is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0086] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the methods described in any embodiment of this disclosure.
[0087] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the methods described in any embodiment of this disclosure.
[0088] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this disclosure can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this disclosure may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this disclosure may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0089] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0090] The embodiments described above are merely illustrative of several implementations of this disclosure, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent disclosure. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this disclosure, and these all fall within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the appended claims.
Claims
1. A method for automatically classifying announcements, characterized in that, The method includes: Obtain announcements to be categorized, including announcement title and announcement body; determine the first category of the announcements to be categorized; determine the target thesaurus corresponding to the announcements to be categorized in the category configuration table based on the first category; the category configuration table stores thesaurus corresponding to announcements of different categories that are pre-set; the thesaurus includes a keyword thesaurus and an irrelevant word thesaurus; the first category of the announcements to be categorized includes at least one; obtain the category of the announcements to be categorized based on the degree of matching between the announcements to be categorized and the category configuration table. The target thesaurus is used to match the announcement title of the announcement text to be classified, and it is determined whether the announcement title conforms to the classification rules. The classification rules include that the announcement title includes at least one keyword from the keyword thesaurus and does not contain any irrelevant words from the irrelevant word thesaurus. If the judgment result is consistent with the classification rules, the classification result of the announcement text to be classified is determined based on the keywords in the matched target thesaurus; If the judgment result does not meet the classification rules, the word segmentation process is repeated, and the corresponding target word library is obtained according to the classification configuration table. The word segmentation process includes determining the character length range of the segmented words based on the maximum character length of the words in the target word library, combining a single character or at least two adjacent characters in the announcement title and announcement body to obtain the combined candidate words, and determining the category of the announcement to be classified according to the target word library.
2. The method according to claim 1, characterized in that, The method further includes: If the judgment result does not conform to the classification rules, the announcement body of the announcement text to be classified is matched with the target thesaurus to determine whether the announcement body conforms to the classification rules. The classification rules include that the announcement body includes at least one keyword from the keyword thesaurus and does not contain any irrelevant words from the irrelevant word thesaurus. If the judgment result is consistent with the classification rules, the classification result of the announcement text to be classified is determined based on the keywords in the matched target thesaurus.
3. A processing device for automated classification of announcements, characterized in that, The device includes: The acquisition module is used to acquire announcements to be categorized, which include the announcement title and the announcement body. The classification module is used to determine the first category of the announcement to be classified, and to determine the target thesaurus corresponding to the announcement to be classified in the classification configuration table based on the first category. The classification configuration table stores the thesaurus corresponding to different categories of announcements in a pre-set manner. The thesaurus includes a keyword thesaurus and an irrelevant word thesaurus. The first category of the announcement to be classified includes at least one category. The category of the announcement to be classified is obtained based on the degree of matching between the announcement to be classified and the classification configuration table. The discrimination module is used to match the announcement title of the announcement text to be classified using the target thesaurus, and to determine whether the announcement title conforms to the classification rules. The classification rules include that the announcement title includes at least one keyword from the keyword thesaurus and does not contain any irrelevant words from the irrelevant word thesaurus. The matching module is used to determine the classification result of the announcement text to be classified based on the keywords in the target thesaurus if the judgment result is consistent with the classification rules; If the judgment result does not meet the classification rules, the word segmentation process is repeated, and the corresponding target word library is obtained according to the classification configuration table. The word segmentation process includes determining the character length range of the segmented words based on the maximum character length of the words in the target word library, combining a single character or at least two adjacent characters in the announcement title and announcement body to obtain the combined candidate words, and determining the category of the announcement to be classified according to the target word library.
4. The apparatus according to claim 3, characterized in that, The device further includes: If the judgment result does not conform to the classification rules, the announcement body of the announcement text to be classified is matched with the target thesaurus to determine whether the announcement body conforms to the classification rules. The classification rules include that the announcement body includes at least one keyword from the keyword thesaurus and does not contain any irrelevant words from the irrelevant word thesaurus. If the judgment result is consistent with the classification rules, the classification result of the announcement text to be classified is determined based on the keywords in the matched target thesaurus.
5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 2.
6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 2.
7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 2.