WO2020077825A1 - 论坛社区应用管理方法、装置、设备及可读存储介质 - Google Patents
论坛社区应用管理方法、装置、设备及可读存储介质 Download PDFInfo
- Publication number
- WO2020077825A1 WO2020077825A1 PCT/CN2018/122746 CN2018122746W WO2020077825A1 WO 2020077825 A1 WO2020077825 A1 WO 2020077825A1 CN 2018122746 W CN2018122746 W CN 2018122746W WO 2020077825 A1 WO2020077825 A1 WO 2020077825A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- user
- information
- word segmentation
- community application
- forum
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Definitions
- This application relates to the field of knowledge management, and in particular to a forum community application management method, device, equipment, and readable storage medium.
- the forum community application is a knowledge transaction APP platform, however, the existing forum community application sharing categories are more complicated, users can not distinguish the quality of the posting topics in the forum before joining, and users usually do not review when posting content in the forum community application, and user preferences are more , Resulting in inconsistency in the categories of published content, and it is impossible to achieve the same or similar categories of knowledge in the community application of the same forum; or only through manual review, the review speed is slow, the efficiency of user publishing content is reduced, and the user experience is not high .
- the main purpose of this application is to propose a forum community application management method, device, equipment and readable storage medium, aiming to solve the existing forum community application sharing category is more complicated, unable to achieve the same forum community application knowledge is the same The subject of technical issues.
- this application provides a forum community application management method, which includes:
- the knowledge system library of the forum community application includes the tag or the keyword, the user is allowed to publish the information; otherwise, the user is prohibited from publishing the information.
- the present application also provides a forum community application management device, which includes:
- the obtaining module is used to obtain user information corresponding to the request when receiving a request to join the forum community application, and review the user according to the user information;
- the permission granting module is used to grant the user permission to join the forum community application when the user is approved, and monitor whether the user releases information in real time;
- the word segmentation module is used to perform word segmentation processing and semantic analysis on the information when the user posts information, to obtain the word segmentation of the information;
- An extraction module for extracting tags or keywords of the information according to the word segmentation, and comparing the tags or keywords with the knowledge system library applied by the forum community; if the knowledge system library applied by the forum community If the tag or the keyword is included, the user is allowed to publish the information; otherwise, the user is prohibited from publishing the information.
- the present application also provides a forum community application management device.
- the forum community application management device includes a memory, a processor, and a computer that is stored on the memory and can run on the processor. Read instructions, when the computer-readable instructions are executed by the processor, implement the steps of the forum community application management method as described above.
- the present application also provides a readable storage medium on which the forum community application management computer readable instructions are stored, and the forum community application management computer readable instructions are executed by the processor To implement the steps of the forum community application management method as described above.
- the forum community application management method, device, device and readable storage medium proposed in this application when receiving a request to join the forum community application, obtain user information corresponding to the request, and review the user according to the user information; When the user is approved, grant the user permission to join the forum community application, and monitor whether the user publishes information in real time; when monitoring the user to publish information, perform word segmentation processing and semantics on the information Analyze and obtain the word segmentation of the information; extract the tags or keywords of the information according to the word segmentation, and compare the tags or keywords with the knowledge system library of the forum community application; if the forum community application The knowledge system library contains the tags or the keywords, allowing users to post the information, otherwise, the user is prohibited from publishing the information, so as to ensure that the content posted by the user is consistent with the knowledge topic applied by the forum community, and avoid other users When acquiring knowledge, it is necessary to filter among irrelevant knowledge, which improves users The efficiency of acquiring knowledge also improves the management efficiency of the forum community application.
- FIG. 1 is a schematic flowchart of a first embodiment of a community application management method for an application forum
- FIG. 2 is a detailed flowchart of the steps of obtaining user information corresponding to the request in the forum community application management method of the application, and reviewing the user according to the user information;
- FIG. 3 is a schematic flowchart of a second embodiment of a community application management method for an application forum
- FIG. 4 is a schematic flowchart of a third embodiment of a community application management method for an application forum
- FIG. 5 is a schematic flowchart of a fourth embodiment of a community application management method for an application forum
- FIG. 6 is a schematic diagram of a device structure of a hardware operating environment involved in an embodiment of the present application.
- This application provides a forum community application management method.
- FIG. 1 is a schematic flowchart of a first embodiment of a forum community application management method of this application.
- the method includes:
- Step S10 When receiving a request to join the forum community application, obtain user information corresponding to the request, and review the user according to the user information;
- the various embodiments of the present application can be applied to forum communities, knowledge planets, etc. in order to screen and classify knowledge.
- a request to join the forum community application is received, in order to ensure joining the forum community
- the quality of the users of the application to prevent bad users from joining the forum community application, resulting in a decline in the quality of the forum community application.
- users who regularly publish bad advertisements or send content that violates regulations join first obtain the user information corresponding to the request, and then User information to review users;
- obtaining user information corresponding to the request in step S10 and reviewing the user according to the user information includes:
- Step S11 Perform word segmentation processing on the user information by using a full segmentation algorithm to obtain the word segmentation using the user information;
- Step S12 Quantify the word segmentation of the user information through a neural network language model to obtain a word vector of the word segmentation of the user information;
- Step S13 Input the word vector of the word segmentation of the user information into a preset database model to obtain the Euclidean distance between the word vector of the word segmentation of the user information and the word vector in the preset database;
- Step S14 Analyze the semantics of the user information according to the Euclidean distance between the word vector of the word segmentation of the user information and the word vectors in the preset database, and extract the corresponding illegal content database according to the semantics of the user information;
- step S15 if the violation content database contains the user information, it is determined that the user audit fails, otherwise it is determined that the user audit passes.
- the user's specific information may include the user name, user ID, etc., and then obtain the user's related content in other forum community applications or other websites, such as the published text, video, and published topic, based on the user ID or user name , Based on the relevant content obtained to determine whether the user has posted illegal content; specifically, you can crawl the page to obtain the text, video, and published topics posted by users in other forum community applications or other websites, specifically by using the user ID or The user name is entered as a crawling condition, and then crawling, you can get the text, video, and published topic published by the user, and then perform semantic analysis on the obtained text, video, and published topic.
- the segmentation algorithm performs word segmentation on the text and themes posted by the user to obtain the word segmentation of the text and themes posted by the user; specifically, first, the text and themes posted by the user are segmented out to match all the preset lexicons Possible words, and then use the statistical language model to determine the optimal segmentation result, First, search for terms (generally stored in Trie), find all the matching terms, and express them in the form of word grids, and then do a path search to find the optimal path based on a statistical language model (such as n-gram).
- the optimal segmentation result can be calculated to obtain the word segmentation result; after the word segmentation result is obtained, the word segmentation can be input into the neural network language model, and the word segmentation can be quantified through the neural network language model.
- the neural network language model can be trained in advance. Specifically, select and The community of this forum applies relevant corpus, and then inputs the selected corpus into the neural network language model for training, updates the parameters of the neural network language model through an iterative algorithm (Baum-welch algorithm), and iterates the selected corpus Training, continuously looping and iterating until it reaches the previously set number of iterations or has converged In this case, the best available model parameters of the neural network model language, a language model to complete the training of the neural network.
- an iterative algorithm Boum-welch algorithm
- the word vector after obtaining the word vector of the word segmentation, the word vector can be input into a preset database model, and the Euclidean distance between the word vector of the word segmentation and the word vector in the preset database is calculated by the preset database model Thus, the Euclidean distance between the word vector of the word segmentation and the word vector in the preset database is obtained;
- the word vector of the word segmentation is input into a preset database model, through a formula Calculate the Euclidean distance between the word vector of the word segmentation and the word vector in the preset database, where x 1k represents 1k coordinates of the word vector of the word segmentation posted by the user, and x 2k represents the word in the preset database 2k coordinates of the vector, d 12 represents Euclidean distance.
- the calculated Euclidean distance is compared with the Euclidean distance of the preset threshold to obtain the Euclidean distance greater than the preset threshold, and then the The Euclidean distance between the word vector of the word and topic segmentation posted by the user of the preset threshold and the word vector in the preset database is used as the target Euclidean distance for analyzing the specific content of the query sentence, specifically, the pre Assume the text content of the word vector in the database, and use the extracted text content as the specific content of the text and theme published by the user.
- the specific content of the text and theme posted by the user contains illegal content. Specifically, the specific content of the text and theme posted by the user can be compared with the content in the illegal content database. Information, it is determined that the user verification fails, otherwise it is determined that the user verification passes.
- Step S20 when the user is approved, grant the user permission to join the forum community application, and monitor whether the user publishes information in real time;
- Step S30 when monitoring the user's posting information, perform word segmentation processing and semantic analysis on the user's posting information to obtain the word segmentation of the user's posting information;
- the current forum community application is a paid application
- the user is given the right to join the forum community application
- the current forum community application is a free application
- the user is directly granted to join the forum Community application permissions to ensure the quality of users who join the community application.
- the process of using the forum community application by the user in order to ensure that the content published by the user in the forum community application is consistent with the theme of the forum community application, it is necessary to monitor whether the user publishes information in real time. The user releases information for word segmentation processing and semantic analysis;
- Step S40 Extract tags or keywords of the information according to the word segmentation, and compare the tags or keywords with the knowledge system library applied by the forum community;
- step S50 if the tag or keyword is included in the knowledge system library of the forum community application, the user is granted to publish information; otherwise, the user is prohibited from publishing information.
- the forum community application management method proposes a request to join the forum community application, the user information corresponding to the request is obtained, and the user is audited according to the user information; when the user audit passes, Grant the user permission to join the forum community application, and monitor whether the user publishes information in real time; when the user is detected to post information, perform word segmentation processing and semantic analysis on the information to obtain the word segmentation of the information ; Extracting tags or keywords of the information according to the word segmentation, and comparing the tags or keywords with the forum community application knowledge system library; if the forum community application knowledge system library includes the The label or the keyword allows the user to publish the information, otherwise, the user is prohibited from publishing the information, so as to ensure that the content posted by the user is consistent with the knowledge topic applied by the forum community, and avoid other users ’ Screening of relevant knowledge, which improves the efficiency of users ’knowledge acquisition Improve the management efficiency of the forum community application.
- a second embodiment of the forum community application management method is proposed based on the first embodiment of the forum community application management method of the present application.
- the steps after the step S50 further include:
- Step S60 Collect information about the user's browsing records, question records, and answer records according to the account or ID of each user;
- Step S70 Analyze the preferences of each user based on the collected information, where the preferences of each user include the type of knowledge browsed, the type of knowledge answered, and construct a corresponding user portrait according to the preferences of each user;
- user records can be searched based on the user's ID address or user account, where the user records specifically include browsing records, posting records, and question answering records, etc. Specifically, first select the user ID to search for the user based on the user ID Record; then start the data collector added in the forum community application system, wherein the data collector can also be a data collector installed in the browser, where the data collector is used to collect content of web pages, forums, etc. in batches , An information tool that saves directly to data or publishes to the network. The original web page can be automatically collected according to the rules set by the user to obtain the required content in the format web page, and now it has developed into a tool (system) that can also process data.
- system tool
- SQL Server 2008 performance data collector allows us to create a central database to store performance data; it contains three built-in data collection groups to collect and store data; in order to help us identify and eliminate SQL Server performance related issues, we can use It has three built-in reports to view collected and stored data.
- the preferences of each user include the type of knowledge browsed, the knowledge category of the answer, and then obtain a preset knowledge category feature tag, and according to the preset knowledge category feature tag, from the user Grab the corresponding user knowledge category feature label data item in the recorded information, and then associate the knowledge category feature label with the captured user knowledge category feature label data item to obtain the user knowledge category feature label;
- a label score corresponding to the user knowledge category feature label may be further obtained, and the label score corresponding to the user knowledge category feature label may be configured with a preset user portrait template to generate a user portrait.
- the label score configuration corresponding to the feature label of the user knowledge category and the preset user portrait template wherein the user portrait template may be a table, or a database, a tab, etc., without limitation, and then the user knowledge
- the category feature tag and the tag score corresponding to the knowledge category feature tag are associated with the user account or user ID to obtain a user portrait.
- Step S80 When receiving a question from another user, analyze the knowledge category corresponding to the question from the other user, and compare the knowledge category with each knowledge category in the user portrait to obtain the knowledge category from the other user's question and each user Match between
- Step S90 Push the user's question to the user with the highest matching degree to answer.
- the knowledge category corresponding to the question from the user When receiving a question from a user, analyze the knowledge category corresponding to the question from the user. Specifically, the content category of the question can be analyzed to obtain the knowledge category, and then compare the knowledge category with each knowledge category in the user portrait , You can get the matching degree between the knowledge category of the user ’s question and each user, and then push the user ’s question to the user with the highest matching degree to answer, so that the answer of the questioning user is more accurate. For the answering user, because It is an area where users are good at, and it also reduces the answer time for answering users, and improves the user experience.
- the forum community application management method proposed in this embodiment constructs a user portrait, and then, when receiving a question from another user, analyzes the knowledge category corresponding to the question of the other user, and compares the knowledge category with each knowledge in the user portrait Compare the categories to obtain the matching degree between the knowledge category of other users ’questions and each user, and push the user ’s questions to the users with the highest matching degree to answer, so that the answering users get more accurate answers.
- answering users because It is an area where users are good at, and it also reduces the answer time for answering users, and improves the user experience.
- a third embodiment of the forum community application management method is proposed based on the second embodiment of the forum community application management method of the present application.
- steps before step S80 further include:
- Step S100 When the received question is a voice query, obtain first voice data input by the other user, and divide the first voice data to obtain a corresponding syllable, where the syllable includes initials and finals;
- the user can also query the answer by inputting the voice.
- the voice query is received, the first voice data input by other users is obtained, and then the first voice data is segmented to obtain the corresponding syllable ,
- syllables include initials and finals.
- Automatic segmentation of speech data is one of the key steps in Chinese speech recognition.
- the segmentation method based on the time domain feature parameters or frequency domain feature parameters can separate the initials and finals, which is conducive to subsequent speech analysis and Identify.
- Step S110 Recognize the initials and finals through the trained voice recognition model to obtain corresponding voice recognition results, and analyze the knowledge categories corresponding to the questions asked by other users according to the voice recognition results.
- the recognition process of the initials and finals by the trained speech recognition model may be: preprocessing the voice data corresponding to the initials or finals (including pre-emphasis, windowing and framing processing, endpoint detection and noise reduction processing), Then extract the voice features of the voice data corresponding to the pre-processed initials and finals, and then recognize them according to the voice features through the trained voice recognition model to obtain the corresponding voice recognition results.
- the voice recognition results include the trained voice recognition results. The initials / vowels recognized by the speech recognition model and their corresponding recognition probabilities.
- a fourth embodiment of the forum community application management method is proposed based on any one of the first to third embodiments of the forum community application management method of the present application.
- the steps after the step S50 further include:
- Step S120 recording the user's browsing time in the forum community application according to the user's account or ID;
- Step S130 When it is detected that the user's single browsing time exceeds the first time threshold, obtain a live broadcast related to the user's portrait and push it to the user;
- step S140 after receiving the user's confirmation click to play command, the user's playing time is recorded, and when it is detected that the user's playing time reaches the second time threshold, a prompt message to close the video playing is sent to the user.
- the forum community application management method proposed in this embodiment records the user's browsing time in the forum community application according to the user's account or ID; when it is detected that the user's single browsing time exceeds the first time threshold, the user profile is obtained Live broadcast and push it to the user; after receiving the user's confirmation to click the play instruction, record the user's play time, and when the user's play time is detected to reach the second time threshold, send the user a prompt message to close the video play , Which makes the forum community applications more diverse and enhances the stickiness between users and forum community applications.
- Embodiments of the present application further provide a forum community application management device.
- the embodiments of the forum community application management device are basically the same as the embodiments of the forum community application management method described above, and details are not repeated herein.
- FIG. 6 is a schematic structural diagram of a hardware operating environment involved in a solution of an embodiment of the present application.
- FIG. 6 is a schematic diagram of the hardware operating environment of the forum community application management device.
- the forum community application management device in the embodiment of the present application may be a terminal device such as a PC or a portable computer.
- the forum community application management device may include: a processor 1001, such as a CPU, a network interface 1004, a memory 1005, a user interface 1003, and a communication bus 1002.
- the communication bus 1002 is used to implement connection communication between these components.
- the user interface 1003 may include a display (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
- the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).
- the memory 1005 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as a disk memory.
- the memory 1005 may optionally be a storage device independent of the foregoing processor 1001.
- the forum community application management device may further include a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, and so on.
- RF Radio Frequency
- the structure of the forum community application management device shown in FIG. 6 does not constitute a limitation on the forum community application management device, and may include more or less components than the illustration, or a combination of certain components, Or different component arrangements.
- the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and computer-readable instructions.
- the operating system is a computer-readable instruction for managing and controlling the forum community application management equipment hardware and software resources, and supports the operation of the computer-readable instruction and other software or computer-readable instructions.
- the user interface 1003 is mainly used to obtain data to be transmitted and output prompt information, etc.
- the network interface 1004 is mainly used to connect the receiving end and perform data communication with the receiving end;
- the processor 1001 It can be used to call computer-readable instructions stored in the memory 1005 and execute the steps of the forum community application management method as described above.
- an embodiment of the present application further proposes a readable storage medium having computer-readable instructions stored on the readable storage medium, the computer-readable instructions being executed by the processor to implement the forum community application management method as described above A step of.
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Information Transfer Between Computers (AREA)
Abstract
一种论坛社区应用管理方法、装置、设备及可读存储介质,所述方法包括:在接收到加入论坛社区应用的请求时,获取请求对应的用户信息,并根据用户信息对用户进行审核(S10);在用户审核通过时,授予用户加入论坛社区应用的权限,并监测用户是否发布信息(S20);在监测到所述用户发布信息时,对信息进行分词处理及语义分析,获得所述信息的分词(S30);根据所述分词提取所述信息的标签或者关键词,并将所述标签或者关键词与所述论坛社区应用的知识体系库进行对比(S40);若所述论坛社区应用的知识体系库中包括所述标签或者所述关键词,则允许发布所述信息,否则,禁止用户发布所述信息(S50)。该方法可提高论坛社区应用的管理效率,保证论坛社区应用的知识质量。
Description
本申请要求于2018年10月18日提交中国专利局、申请号为201811213006.1、发明名称为“论坛社区应用管理方法、装置、设备及计算机可读存储介质”的中国专利申请的优先权,其全部内容通过引用结合在申请中。
本申请涉及知识管理领域,尤其涉及一种论坛社区应用管理方法、装置、设备及可读存储介质。
随着社会的进步,人们对知识的获取越来越注重,而知识量非常庞大,因此在获取时,用户需要进行筛选识别,由此论坛社区应用应运而生,论坛社区应用是一个知识交易的APP平台,然而,现有的论坛社区应用分享类目比较繁杂,用户在加入之前无法甄别论坛里面的发布主题的质量,而且用户在论坛社区应用发布内容时,通常不进行审核,用户喜好比较多,造成发布的内容类别不统一,无法实现同一论坛社区应用中的知识类别为相同或相似的类别;或者只是通过人工进行审核,造成审核速度较慢,用户发布内容的效率下降,用户体验不高。
发明内容
本申请的主要目的在于提出一种论坛社区应用管理方法、装置、设备及可读存储介质,旨在解决现有的论坛社区应用分享类目比较繁杂,无法实现同一论坛社区应用中的知识为同一主题的技术问题。
为实现上述目的,本申请提供一种论坛社区应用管理方法,所述方法包括:
接收到加入论坛社区应用的请求时,获取所述请求对应的用户信息,并根据所述用户信息对用户进行审核;
在所述用户审核通过时,授予所述用户加入所述论坛社区应用的权限,并实时监测所述用户是否发布信息;
在监测到所述用户发布信息时,对所述信息进行分词处理及语义分析,获得所述信息的分词;
根据所述分词提取所述信息的标签或者关键词,并将所述标签或者关键词与所述论坛社区应用的知识体系库进行对比;
若所述论坛社区应用的知识体系库中包括所述标签或者所述关键词,则允许用户发布所述信息,否则,禁止用户发布所述信息。
此外,为实现上述目的,本申请还提供一种论坛社区应用管理装置,所述装置包括:
获取模块,用于接收到加入论坛社区应用的请求时,获取所述请求对应的用户信息,并根据所述用户信息对用户进行审核;
权限授予模块,用于在所述用户审核通过时,授予所述用户加入所述论坛社区应用的权限,并实时监测所述用户是否发布信息;
分词模块,用于在监测到所述用户发布信息时,对所述信息进行分词处理及语义分析,获得所述信息的分词;
提取模块,用于根据所述分词提取所述信息的标签或者关键词,并将所述标签或者关键词与所述论坛社区应用的知识体系库进行对比;若所述论坛社区应用的知识体系库中包括所述标签或者所述关键词,则允许用户发布所述信息,否则,禁止用户发布所述信息。
此外,为实现上述目的,本申请还提供一种论坛社区应用管理设备,所述论坛社区应用管理设备包括存储器、处理器和存储在所述存储器上并可在所述处理器上运行的计算机可读指令,所述计算机可读指令被所述处理器执行时实现如上所述的论坛社区应用管理方法的步骤。
此外,为实现上述目的,本申请还提供一种可读存储介质,所述可读存储介质上存储有论坛社区应用管理计算机可读指令,所述论坛社区应用管理计算机可读指令被处理器执行时实现如上所述的论坛社区应用管理方法的步骤。
本申请提出的论坛社区应用管理方法、装置、设备及可读存储介 质,在接收到加入论坛社区应用的请求时,获取所述请求对应的用户信息,并根据所述用户信息对用户进行审核;在所述用户审核通过时,授予所述用户加入所述论坛社区应用的权限,并实时监测所述用户是否发布信息;在监测到所述用户发布信息时,对所述信息进行分词处理及语义分析,获得所述信息的分词;根据所述分词提取所述信息的标签或者关键词,并将所述标签或者关键词与所述论坛社区应用的知识体系库进行对比;若所述论坛社区应用的知识体系库中包括所述标签或者所述关键词,则允许用户发布所述信息,否则,禁止用户发布所述信息,从而保证用户发布的内容与论坛社区应用的知识主题一致,避免其他用户在获取知识时,需要在不相关的知识中进行筛选,提高了用户获取知识的效率,同时也提高了对论坛社区应用的管理效率。
图1为本申请论坛社区应用管理方法第一实施例的流程示意图;
图2为本申请论坛社区应用管理方法中获取所述请求对应的用户信息,并根据所述用户信息对用户进行审核的步骤的细化流程示意图;
图3为本申请论坛社区应用管理方法第二实施例的流程示意图;
图4为本申请论坛社区应用管理方法第三实施例的流程示意图;
图5为本申请论坛社区应用管理方法第四实施例的流程示意图;
图6为本申请实施例方案涉及的硬件运行环境的设备结构示意图。
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
本申请提供一种论坛社区应用管理方法。
参照图1,图1为本申请论坛社区应用管理方法第一实施例的流 程示意图。
在本实施例中,该方法包括:
步骤S10,接收到加入论坛社区应用的请求时,获取所述请求对应的用户信息,并根据所述用户信息对用户进行审核;
在本实施例中,本申请各个实施例可以应用在对论坛社区、知识星球等应用中,以便对知识进行甄别分类,具体地,在接收到加入论坛社区应用的请求时,为了保证加入论坛社区应用的用户的质量,避免不良用户加入论坛社区应用,造成论坛社区应用中的质量下降,比如经常发布不良广告、违规内容发的用户加入,首先获取所述请求对应的用户信息,然后根据所述用户信息对用户进行审核;
具体地,参照图2,步骤S10中的获取所述请求对应的用户信息,并根据所述用户信息对用户进行审核包括:
步骤S11,通过全切分算法对所述用户信息进行分词处理,获得所述用用户信息的分词;
步骤S12,通过神经网络语言模型对所述用户信息的分词进行量化处理,获得所述用户信息的分词的词向量;
步骤S13,将所述用户信息的分词的词向量输入至预设数据库模型中,获得所述用户信息的分词的词向量与所述预设数据库中的词向量的欧式距离;
步骤S14,根据所述用户信息的分词的词向量与所述预设数据库中的词向量的欧式距离分析所述用户信息的语义,并根据所述用户信息的语义提取对应的违规内容数据库;
步骤S15,若所述违规内容数据库包含所述用户信息,则确定所 述用户审核不通过,否则确定所述用户审核通过。
在本实施例中,用户的具体信息可以包括用户名,用户ID等,然后根据用户ID或用户名获取用户在其他论坛社区应用或者其他网站的相关内容,比如发布的文字,视频、发表的主题,根据获取到的相关内容判断用户是否发布过违规内容;具体地,可以通过页面爬取,获取用户在其他论坛社区应用或者其他网站发布的文字,视频、发表的主题,具体通过将用户ID或用户名作为爬取条件进行输入,然后进行爬取,即可获得用户发布的文字,视频、发表的主题,然后将获得的用户发布的文字,视频、发表的主题进行语义分析,具体可以通过全切分算法对所述用户发布的文字和主题进行分词处理,获得所述用户发布的文字和主题的分词;具体地,首先将用户发布的文字和主题切分出与预设词库匹配的所有可能的词,再运用统计语言模型决定最优的切分结果,首先进行词条检索(一般用Trie存储),找到匹配的所有词条,以词网格(word lattices)形式表示,接着做路径搜索,基于统计语言模型(例如n-gram)找到最优路径,即可计算得到最优的切分结果,从而获得分词结果;在获得分词结果之后,即可将分词输入至神经网络语言模型中,通过神经网络语言模型对所述分词进行量化处理,具体地,通过神经网络语言模型的输入层将分词进行输入,即可输出分词的词向量,进一步地,为了提高分词输出的词向量的准确性,可以预先对神经网络语言模型进行训练,具体地,选取与本论坛社区应用相关的语料,然后将选取的语料输入至神经网络语言模型中进行训练,通过迭代算法(Baum-welch算法)对该神经网络语言 模型的参数进行更新,并对选取的语料进行迭代训练,不断地循环迭代,直到达到先前设置的迭代次数或已经收敛,此时,可得到该神经网络语言模型的最优模型参数,即可完成神经网络语言模型的训练。具体地,在获得所述分词的词向量之后,即可将所述词向量输入至预设数据库模型中,通过预设数据库模型计算分词的词向量与预设数据库中的词向量的欧式距离,从而获得所述分词的词向量与所述预设数据库中的词向量的欧式距离;
进一步地,具体地,将所述分词的词向量输入至预设数据库模型中,通过公式
计算分词的词向量与所述预设数据库中的词向量的欧式距离,其中,x
1k表示所述用户发布内容的分词的词向量的1k个坐标,x
2k表示所述预设数据库中的词向量的2k个坐标,d
12表示欧式距离。然后根据所述用户发布的文字和主题的分词的词向量与所述预设数据库中的词向量的欧式距离分析所述用户发布的文字和主题的具体内容;在计算得到所述用户发布的文字和主题的分词的词向量与所述预设数据库中的词向量的欧式距离之后,将计算得到的欧式距离与预设阈值的欧式距离进行对比,获得大于预设阈值的欧式距离,然后将大于预设阈值的用户发布的文字和主题的分词的词向量与所述预设数据库中的词向量的欧式距离作为分析查询语句的具体内容的目标欧式距离,具体地,提取目标欧式距离对应的预设数据库中的词向量的文本内容,并将提取到的文本内容作为用户发布的文字和主题的具体内容。然后判断所述用户发布的文字和主题 的具体内容是否包含违规内容,具体可以将用户发布的文字和主题的具体内容与违规内容数据库中的内容进行对比,若所述违规内容数据库包含所述用户信息,则确定所述用户审核不通过,否则确定所述用户审核通过。
步骤S20,在所述用户审核通过时,授予所述用户加入论坛社区应用的权限,并实时监测所述用户是否发布信息;
步骤S30,在监测到所述用户发布信息时,对所述用户发布信息进行分词处理及语义分析,获得所述用户发布信息的分词;
在用户审核通过后,若当前论坛社区应用为付费应用,则在接收到用户的付款之后,赋予用户加入本论坛社区应用的权限,若当前论坛社区应用为免费应用,则直接赋予用户加入本论坛社区应用的权限,从而保证加入论坛社区应用的用户质量。然后在用户使用论坛社区应用过程中,为了保证用户在论坛社区应用的发布的内容与论坛社区应用的主题一致,需要实时监测所述用户是否发布信息,在监测到所述用户发布信息时,对所述用户发布信息进行分词处理及语义分析;
步骤S40,根据所述分词提取所述信息的标签或者关键词,并将所述标签或者关键词与所述论坛社区应用的知识体系库进行对比;
步骤S50,若所述论坛社区应用的知识体系库中包括所述标签或者关键词,则授予用户进行发布信息,否则,禁止用户进行发布信息。
在通过分词处理及语义分析,获得所述用户发布信息的分词之后,然后根据所述分词提取所述用户发布信息的标签或者关键词,并将所述标签或者关键词论坛社区应用的知识体系库进行对比;若所述论坛社区应用的知识体系库中包括所述标签或者关键词,则授予用户进行发布信息,否则,禁止用户进行发布内容,从而保证了用户发布或者分享的内容与本论坛社区应用的知识类别体系一致,避免其他用户在获取知识时,需要在不相关的知识中进行筛选,提高了用户获取知识的效率。
本实施例提出的论坛社区应用管理方法,在接收到加入论坛社区 应用的请求时,获取所述请求对应的用户信息,并根据所述用户信息对用户进行审核;在所述用户审核通过时,授予所述用户加入所述论坛社区应用的权限,并实时监测所述用户是否发布信息;在监测到所述用户发布信息时,对所述信息进行分词处理及语义分析,获得所述信息的分词;根据所述分词提取所述信息的标签或者关键词,并将所述标签或者关键词与所述论坛社区应用的知识体系库进行对比;若所述论坛社区应用的知识体系库中包括所述标签或者所述关键词,则允许用户发布所述信息,否则,禁止用户发布所述信息,从而保证用户发布的内容与论坛社区应用的知识主题一致,避免其他用户在获取知识时,需要在不相关的知识中进行筛选,提高了用户获取知识的效率,同时也提高了对论坛社区应用的管理效率。
进一步地,参照图3,基于本申请论坛社区应用管理方法第一实施例提出论坛社区应用管理方法第二实施例。
在本实施例中,所述步骤S50之后的步骤,还包括:
步骤S60,根据各个用户的账号或ID对用户的浏览记录、提问记录以及回答记录的信息进行采集;
步骤S70,根据采集到的信息分析所述各个用户的喜好,其中,所述各个用户的喜好包括浏览的知识类型,回答的知识类别,并根据所述各个用户的喜好构建对应的用户画像;
在本实施例中,可以根据用户的ID地址或者用户账号查找用户记录,其中用户记录具体包括浏览记录、发表记录和提问回答记录等,具体地,首先选择用户ID,以便根据用户ID进行查找用户记录;然后启动论坛社区应用系统中添加的数据采集器,其中所述数据采集器也可以为安装在浏览器中的数据采集器,其中,数据采集器是用来批量采集网页,论坛等的内容,直接保存到数据或发布到网络的一种信息化工具。可以根据用户设定的规则自动采集原网页,获取格式网页中需要的内容,现在发展成也可以对数据进行处理的工具(系统)。如SQL Server 2008性能数据采集器可以让我们创建一个中心数据库来存储性能数据;它包含三个内置数据收集组来收集和存储数据;为了帮助我们识别和排除SQL Server性能相关的问题,我们可以使用 其内置的三个报表来查看收集存储的数据。然后根据接收到的爬取条件,选取用户记录,即可获取用户在论坛社区应用系统中的记录,即可获得用户在论坛社区应用系统中的记录的信息,然后根据采集到的信息分析所述各个用户的喜好,其中,所述各个用户的喜好包括浏览的知识类型,回答的知识类别,然后获取预设的知识类别特征标签,并根据所述预设的知识类别特征标签,从所述用户的记录的信息中抓取对应的用户知识类别特征标签数据项,然后将所述知识类别特征标签与抓取到的用户知识类别特征标签数据项进行关联,获得用户知识类别特征标签;在获得知识类别特征标签之后,可以进一步获取用户知识类别特征标签对应的标签分值,并将所述用户知识类别特征标签对应的标签分值配置与预设的用户画像模板,生成用户画像。即将所述用户知识类别特征标签对应的标签分值配置与预设的用户画像模板,其中,所述用户画像模板可以为表格,或者数据库、页签等,在此不做限制,然后将用户知识类别特征标签以及所述知识类别特征标签对应的标签分值与用户账户或用户ID进行关联,即可得到用户画像。
步骤S80,在接收到其他用户的提问时,分析所述其他用户提问对应的知识类别,并将所述知识类别与用户画像中的各个知识类别进行对比,获得其他用户提问的知识类别与各个用户之间的匹配度;
步骤S90,将用户的提问推送至匹配度最高的用户进行回答。
在接收到用户提问时,分析所述用户提问对应的知识类别,具体可以为对用户的提问进行内容分析,即可获取知识类别,然后将所述知识类别与用户画像中的各个知识类别进行对比,即可获得用户提问的知识类别与各个用户之间的匹配度,然后将用户的提问推送至匹配度最高的用户进行回答,从而使得提问用户获得的答案更精准,对回答用户而言,由于是用户擅长的领域,也减少了回答用户的回答时间,提高了用户体验。
本实施例提出的论坛社区应用管理方法,通过构建用户画像,然后在接收到其他用户的提问时,分析所述其他用户提问对应的知识类别,并将所述知识类别与用户画像中的各个知识类别进行对比,获得 其他用户提问的知识类别与各个用户之间的匹配度,将用户的提问推送至匹配度最高的用户进行回答,使得提问用户获得的答案更精准,对回答用户而言,由于是用户擅长的领域,也减少了回答用户的回答时间,提高了用户体验。
进一步地,参照图4,基于本申请论坛社区应用管理方法第二实施例提出论坛社区应用管理方法第三实施例。
在本实施例中,所述步骤S80之前的步骤,还包括:
步骤S100,当接收到的提问为语音查询时,获取所述其他用户输入的第一语音数据,并对所述第一语音数据进行分割得到对应的音节,其中所述音节包括声母和韵母;
在本实施例中,用户还可以通过输入语音进行答案查询,具体地,当接收到语音查询时,获取其他用户输入的第一语音数据,然后对所述第一语音数据进行分割得到对应的音节,其中音节包括声母和韵母。其中,对于第一语音数据的分割方法可以基于时域特征参数的方法进行分割,时域参数包括短时平均能量E
n、短时过零率Z
n、平均能量过零数积A=E
n*Z
n及平均能量过零数比B=E
n/Z
n。也可以基于频域特征参数的方法进行分割,通过利用语音信号的谱特征如LPC(Linear Predictive Coding,线性预测编码)倒谱、MFCC(Mel Frequency Cepstrum Coefficient,梅尔频率倒谱系数)倒谱等,利用清、浊音频谱的能量分布及谱值幅度不同,可用判别出清、浊音,进一步得到音节分割的结果。语音数据的自动分割是汉语语音识别的关键步骤之一,通过上述基于时域特征参数或基于频域特征参数的分割方法,可将声母和韵母分隔开来,从而有利于后续的语音分析和识别。
步骤S110,通过训练好的语音识别模型对所述声母和韵母进行识别,得到对应的语音识别结果,并根据所述语音识别结果分析所述其他用户提问对应的知识类别。
在将第一语音数据分割成声母和韵母后,通过训练好的语音识别模型对分割后的声母和韵母进行识别,得到对应的语音识别结果,并将所述语音识别结果转换为查询语句,具体的,训练好的语音识别模型对所述声母和韵母的识别过程可以为:对声母或韵母对应的语音数 据进行预处理(包括预加重、加窗分帧处理、端点检测和降噪处理),然后提取经过预处理的声母或韵母对应的语音数据的语音特征,然后根据该语音特征,通过训练好的语音识别模型进行识别,即可得到对应的语音识别结果,语音识别结果包括通过训练好的语音识别模型识别出的声母/韵母及其对应的识别概率。
进一步地,参照图5,基于本申请论坛社区应用管理方法第一至第三任一实施例提出论坛社区应用管理方法第四实施例。
在本实施例中,所述步骤S50之后的步骤,还包括:
步骤S120,根据用户的账号或ID对用户在论坛社区应用的浏览时间进行记录;
步骤S130,当监测到用户单次浏览时长超过第一时间阈值时,获取与用户画像相关的直播,并向用户进行推送;
步骤S140,在接收到用户确认点击播放指令之后,对用户的播放时间进行记录,当监测到用户的播放时长达到第二时间阈值时,向用户发送关闭视频播放的提示信息。
在本实施例中,在用户使用论坛社区应用或者知识星球过程中,由于有些用户需要浏览的内容,获取的知识较多,因此使用论坛社区应用或者知识星球的时间会较长,因此可以对用户单次使用论坛社区应用或者知识星球的时长进行记录,当记录到用户单次使用论坛社区应用或者知识星球的时长超过第一时间阈值时,可以获取跟用户知识特征相关的直播,并向用户进行推送,避免用户长时间进行枯燥的浏览,可以理解的是,向用户进行推送的直播,也可以单纯是搞笑放松直播,以便用户进行放松,在用户确认点击播放之后,为了避免用户长时间沉迷与直播,需要进一步记录用户的播放时间,当用户的播放时长达到第二时间阈值时,向用户发送提示信息,以便用户关闭视频播放,继续进行浏览知识。
本实施例提出的论坛社区应用管理方法,通过根据用户的账号或ID对用户在论坛社区应用的浏览时间进行记录;当监测到用户单次浏览时长超过第一时间阈值时,获取与用户画像相关的直播,并向用户进行推送;在接收到用户确认点击播放指令之后,对用户的播放时 间进行记录,当监测到用户的播放时长达到第二时间阈值时,向用户发送关闭视频播放的提示信息,从而使得论坛社区应用的更加多样化,增强了用户与论坛社区应用之间的粘性。
本申请实施例进一步提供一种论坛社区应用管理装置,所述论坛社区应用管理装置的各个实施例与上述论坛社区应用管理方法的各实施例基本相同,在此不再详细赘述。
此外,本申请实施例还提供一种论坛社区应用管理设备。如图6所示,图6是本申请实施例方案涉及的硬件运行环境的结构示意图。
需要说明的是,图6即可为论坛社区应用管理设备的硬件运行环境的结构示意图。本申请实施例论坛社区应用管理设备可以是PC,便携计算机等终端设备。
如图6所示,该论坛社区应用管理设备可以包括:处理器1001,例如CPU,网络接口1004,存储器1005,用户接口1003,通信总线1002。其中,通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏(Display)、输入单元比如键盘(Keyboard),可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。存储器1005可以是高速RAM存储器,也可以是稳定的存储器(non-volatile memory),例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
可选地,论坛社区应用管理设备还可以包括摄像头、RF(Radio Frequency,射频)电路,传感器、音频电路、WiFi模块等等。
本领域技术人员可以理解,图6中示出的论坛社区应用管理设备结构并不构成对论坛社区应用管理设备的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。
如图6所示,作为一种计算机存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及计算机可读指令。其中,操作系统是管理和控制论坛社区应用管理设备硬件和软件资源的计算机可读指令,支持计算机可读指令以及其它软件或计算机可读指令的运行。
在图6所示的论坛社区应用管理设备中,用户接口1003主要用于获取待传输数据,以及输出提示信息等,网络接口1004主要用于连接接收端,与接收端进行数据通信;处理器1001可以用于调用存储器1005中存储的计算机可读指令,并执行如上所述的论坛社区应用管理方法的步骤。
本申请论坛社区应用管理设备具体实施方式与上述论坛社区应用管理方法各实施例基本相同,在此不再赘述。
此外,本申请实施例还提出一种可读存储介质,所述可读存储介质上存储有计算机可读指令,所述计算机可读指令被处理器执行时实现如上所述的论坛社区应用管理方法的步骤。
本申请可读存储介质具体实施方式与上述论坛社区应用管理方法各实施例基本相同,在此不再赘述。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。
Claims (20)
- 一种论坛社区应用管理方法,其特征在于,所述方法包括以下步骤:接收到加入论坛社区应用的请求时,获取所述请求对应的用户信息,并根据所述用户信息对用户进行审核;在所述用户审核通过时,授予所述用户加入所述论坛社区应用的权限,并实时监测所述用户是否发布信息;在监测到所述用户发布信息时,对所述信息进行分词处理及语义分析,获得所述信息的分词;根据所述分词提取所述信息的标签或者关键词,并将所述标签或者关键词与所述论坛社区应用的知识体系库进行对比;若所述论坛社区应用的知识体系库中包括所述标签或者所述关键词,则允许用户发布所述信息,否则,禁止用户发布所述信息。
- 如权利要求1所述的论坛社区应用管理方法,其特征在于,所述获取所述请求对应的用户信息,并根据所述用户信息对用户进行审核的步骤包括:通过全切分算法对所述用户信息进行分词处理,获得所述用用户信息的分词;通过神经网络语言模型对所述用户信息的分词进行量化处理,获得所述用户信息的分词的词向量;将所述用户信息的分词的词向量输入至预设数据库模型中,获得所述用户信息的分词的词向量与所述预设数据库中的词向量的欧式距离;根据所述用户信息的分词的词向量与所述预设数据库中的词向量的欧式距离分析所述用户信息的语义,并根据所述用户信息的语义提取对应的违规内容数据库;若所述违规内容数据库包含所述用户信息,则确定所述用户审核不通过,否则确定所述用户审核通过。
- 如权利要求1所述的论坛社区应用管理方法,其特征在于,所述若所述论坛社区应用的知识体系库中包括所述标签或者所述关键词,则允许用户发布所述信息,否则,禁止用户发布所述信息的步骤之后,还包括:根据各个用户的账号或ID对用户的浏览记录、提问记录以及回答记录的信息进行采集;根据采集到的信息分析所述各个用户的喜好,其中,所述各个用户的喜好包括浏览的知识类型,回答的知识类别,并根据所述各个用户的喜好构建对应的用户画像;在接收到其他用户的提问时,分析所述其他用户提问对应的知识类别,并将所述知识类别与用户画像中的各个知识类别进行对比,获得其他用户提问的知识类别与各个用户之间的匹配度;将用户的提问推送至匹配度最高的用户进行回答。
- 如权利要求4所述的论坛社区应用管理方法,其特征在于,所述分析所述其他用户提问对应的知识类别,并将所述知识类别与用户画像中的各个知识类别进行对比,获得其他用户提问的知识类别与各个用户之间的匹配度的步骤之前,还包括:当接收到的提问为语音查询时,获取所述其他用户输入的第一语音数据,并对所述第一语音数据进行分割得到对应的音节,其中所述音节包括声母和韵母;通过训练好的语音识别模型对所述声母和韵母进行识别,得到对应的语音识别结果,并根据所述语音识别结果分析所述其他用户提问对应的知识类别。
- 如权利要求1所述的论坛社区应用管理方法,其特征在于,所述若所述论坛社区应用的知识体系库中包括所述标签或者所述关键词,则允许用户发布所述信息,否则,禁止用户发布所述信息的步骤之后,还包括:根据用户的账号或ID对用户在论坛社区应用的浏览时间进行记录;当监测到用户单次浏览时长超过第一时间阈值时,获取与用户画像相关的直播,并向用户进行推送;在接收到用户确认点击播放指令之后,对用户的播放时间进行记录,当监测到用户的播放时长达到第二时间阈值时,向用户发送关闭视频播放的提示信息。
- 一种论坛社区应用管理装置,其特征在于,所述装置包括:第一获取模块,用于接收到加入论坛社区应用的请求时,获取所述请求对应的用户信息,并根据所述用户信息对用户进行审核;权限授予模块,用于在所述用户审核通过时,授予所述用户加入所述论坛社区应用的权限,并实时监测所述用户是否发布信息;分词模块,用于在监测到所述用户发布信息时,对所述信息进行分词处理及语义分析,获得所述信息的分词;提取模块,用于根据所述分词提取所述信息的标签或者关键词,并将所述标签或者关键词与所述论坛社区应用的知识体系库进行对比;若所述论坛社区应用的知识体系库中包括所述标签或者所述关键词,则允许用户发布所述信息,否则,禁止用户发布所述信息。
- 如权利要求7所述的论坛社区应用管理装置,其特征在于,所述获取模块包括:分词单元,用于通过全切分算法对所述用户信息进行分词处理,获得所述用用户信息的分词;量化处理单元,用于通过神经网络语言模型对所述用户信息的分 词进行量化处理,获得所述用户信息的分词的词向量;输入单元,用于将所述用户信息的分词的词向量输入至预设数据库模型中,获得所述用户信息的分词的词向量与所述预设数据库中的词向量的欧式距离;分析单元,用于根据所述用户信息的分词的词向量与所述预设数据库中的词向量的欧式距离分析所述用户信息的语义,并根据所述用户信息的语义提取对应的违规内容数据库;若所述违规内容数据库包含所述用户信息,则确定所述用户审核不通过,否则确定所述用户审核通过。
- 如权利要求7所述的论坛社区应用管理装置,其特征在于,所述论坛社区应用管理装置还包括:采集模块,用于根据各个用户的账号或ID对用户的浏览记录、提问记录以及回答记录的信息进行采集;分析模块,用于根据采集到的信息分析所述各个用户的喜好,其中,所述各个用户的喜好包括浏览的知识类型,回答的知识类别,并根据所述各个用户的喜好构建对应的用户画像;在接收到其他用户的提问时,分析所述其他用户提问对应的知识类别,并将所述知识类别与用户画像中的各个知识类别进行对比,获得其他用户提问的知识类别与各个用户之间的匹配度;推送模块,用于将用户的提问推送至匹配度最高的用户进行回答。
- 如权利要求10所述的论坛社区应用管理装置,其特征在于,所述论坛社区应用管理装置还包括:分割模块,用于当接收到的提问为语音查询时,获取所述其他用户输入的第一语音数据,并对所述第一语音数据进行分割得到对应的音节,其中所述音节包括声母和韵母;识别模块,用于通过训练好的语音识别模型对所述声母和韵母进行识别,得到对应的语音识别结果,并根据所述语音识别结果分析所述其他用户提问对应的知识类别。
- 如权利要求7所述的论坛社区应用管理装置,其特征在于,所述论坛社区应用管理装置还包括:第一记录模块,用于根据用户的账号或I D对用户在论坛社区应用的浏览时间进行记录;第二获取模块,用于当监测到用户单次浏览时长超过第一时间阈值时,获取与用户画像相关的直播,并向用户进行推送;第二记录模块,用于在接收到用户确认点击播放指令之后,对用户的播放时间进行记录,当监测到用户的播放时长达到第二时间阈值时,向用户发送关闭视频播放的提示信息。
- 一种论坛社区应用管理设备,其特征在于,所述论坛社区应用管理设备包括存储器、处理器和存储在所述存储器上并可在所述处理器上运行的计算机可读指令,所述计算机可读指令被所述处理器执行时实现如下步骤:接收到加入论坛社区应用的请求时,获取所述请求对应的用户信息,并根据所述用户信息对用户进行审核;在所述用户审核通过时,授予所述用户加入所述论坛社区应用的权限,并实时监测所述用户是否发布信息;在监测到所述用户发布信息时,对所述信息进行分词处理及语义分析,获得所述信息的分词;根据所述分词提取所述信息的标签或者关键词,并将所述标签或者关键词与所述论坛社区应用的知识体系库进行对比;若所述论坛社区应用的知识体系库中包括所述标签或者所述关 键词,则允许用户发布所述信息,否则,禁止用户发布所述信息。
- 如权利要求13所述的论坛社区应用管理设备,其特征在于,所述计算机可读指令被所述处理器执行时还实现如下步骤:通过全切分算法对所述用户信息进行分词处理,获得所述用用户信息的分词;通过神经网络语言模型对所述用户信息的分词进行量化处理,获得所述用户信息的分词的词向量;将所述用户信息的分词的词向量输入至预设数据库模型中,获得所述用户信息的分词的词向量与所述预设数据库中的词向量的欧式距离;根据所述用户信息的分词的词向量与所述预设数据库中的词向量的欧式距离分析所述用户信息的语义,并根据所述用户信息的语义提取对应的违规内容数据库;若所述违规内容数据库包含所述用户信息,则确定所述用户审核不通过,否则确定所述用户审核通过。
- 如权利要求13所述的论坛社区应用管理设备,其特征在于,所述计算机可读指令被所述处理器执行时还实现如下步骤:根据各个用户的账号或ID对用户的浏览记录、提问记录以及回答记录的信息进行采集;根据采集到的信息分析所述各个用户的喜好,其中,所述各个用 户的喜好包括浏览的知识类型,回答的知识类别,并根据所述各个用户的喜好构建对应的用户画像;在接收到其他用户的提问时,分析所述其他用户提问对应的知识类别,并将所述知识类别与用户画像中的各个知识类别进行对比,获得其他用户提问的知识类别与各个用户之间的匹配度;将用户的提问推送至匹配度最高的用户进行回答。
- 如权利要求16所述的论坛社区应用管理设备,其特征在于,所述计算机可读指令被所述处理器执行时还实现如下步骤:当接收到的提问为语音查询时,获取所述其他用户输入的第一语音数据,并对所述第一语音数据进行分割得到对应的音节,其中所述音节包括声母和韵母;通过训练好的语音识别模型对所述声母和韵母进行识别,得到对应的语音识别结果,并根据所述语音识别结果分析所述其他用户提问对应的知识类别。
- 如权利要求13所述的论坛社区应用管理设备,其特征在于,所述计算机可读指令被所述处理器执行时还实现如下步骤:根据用户的账号或ID对用户在论坛社区应用的浏览时间进行记录;当监测到用户单次浏览时长超过第一时间阈值时,获取与用户画像相关的直播,并向用户进行推送;在接收到用户确认点击播放指令之后,对用户的播放时间进行记录,当监测到用户的播放时长达到第二时间阈值时,向用户发送关闭视频播放的提示信息。
- 一种可读存储介质,其特征在于,所述可读存储介质上存储有计算机可读指令,其中所述计算机可读指令被处理器执行时,实现如下步骤:接收到加入论坛社区应用的请求时,获取所述请求对应的用户信息,并根据所述用户信息对用户进行审核;在所述用户审核通过时,授予所述用户加入所述论坛社区应用的权限,并实时监测所述用户是否发布信息;在监测到所述用户发布信息时,对所述信息进行分词处理及语义分析,获得所述信息的分词;根据所述分词提取所述信息的标签或者关键词,并将所述标签或者关键词与所述论坛社区应用的知识体系库进行对比;若所述论坛社区应用的知识体系库中包括所述标签或者所述关键词,则允许用户发布所述信息,否则,禁止用户发布所述信息。
- 如权利要求19所述的可读存储介质,其特征在于,所述获取所述请求对应的用户信息,并根据所述用户信息对用户进行审核的步骤包括:通过全切分算法对所述用户信息进行分词处理,获得所述用用户信息的分词;通过神经网络语言模型对所述用户信息的分词进行量化处理,获得所述用户信息的分词的词向量;将所述用户信息的分词的词向量输入至预设数据库模型中,获得所述用户信息的分词的词向量与所述预设数据库中的词向量的欧式距离;根据所述用户信息的分词的词向量与所述预设数据库中的词向量的欧式距离分析所述用户信息的语义,并根据所述用户信息的语义提取对应的违规内容数据库;若所述违规内容数据库包含所述用户信息,则确定所述用户审核不通过,否则确定所述用户审核通过。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811213006.1 | 2018-10-18 | ||
CN201811213006.1A CN109635073A (zh) | 2018-10-18 | 2018-10-18 | 论坛社区应用管理方法、装置、设备及计算机可读存储介质 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020077825A1 true WO2020077825A1 (zh) | 2020-04-23 |
Family
ID=66066375
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2018/122746 WO2020077825A1 (zh) | 2018-10-18 | 2018-12-21 | 论坛社区应用管理方法、装置、设备及可读存储介质 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109635073A (zh) |
WO (1) | WO2020077825A1 (zh) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110377900A (zh) * | 2019-06-17 | 2019-10-25 | 深圳壹账通智能科技有限公司 | 网络内容发布的审核方法、装置、计算机设备及存储介质 |
CN110929055B (zh) * | 2019-11-15 | 2023-05-02 | 北京达佳互联信息技术有限公司 | 多媒体质量检测方法、装置、电子设备及存储介质 |
CN111488555A (zh) * | 2020-04-02 | 2020-08-04 | 上海七印信息科技有限公司 | 版权认证方法、装置、计算机设备和存储介质 |
CN111523062B (zh) * | 2020-04-24 | 2024-02-27 | 浙江口碑网络技术有限公司 | 多维度信息展示方法及装置 |
CN111901622B (zh) * | 2020-07-31 | 2021-11-16 | 联想(北京)有限公司 | 一种控制方法、装置及电子设备 |
CN114896967B (zh) * | 2022-06-06 | 2024-01-19 | 山东浪潮爱购云链信息科技有限公司 | 一种采购平台中论坛问题的处理方法、设备、存储介质 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102214227A (zh) * | 2011-06-23 | 2011-10-12 | 华南理工大学 | 基于互联网层次结构存储的自动舆情监控方法 |
CN103347009A (zh) * | 2013-06-20 | 2013-10-09 | 新浪网技术(中国)有限公司 | 一种信息过滤方法及装置 |
CN103744881A (zh) * | 2013-12-20 | 2014-04-23 | 百度在线网络技术(北京)有限公司 | 一种问答平台的问题分发方法和问题分发系统 |
US20140379719A1 (en) * | 2013-06-24 | 2014-12-25 | Tencent Technology (Shenzhen) Company Limited | System and method for tagging and searching documents |
CN106095801A (zh) * | 2016-05-30 | 2016-11-09 | 海智(天津)大数据服务有限公司 | 一种基于大数据技术所见即所得的名称申报系统及方法 |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013250931A (ja) * | 2012-06-04 | 2013-12-12 | Canon Inc | 情報取得システム、プログラム、サーバ、情報取得方法 |
CN106204156A (zh) * | 2016-07-20 | 2016-12-07 | 天涯社区网络科技股份有限公司 | 一种用于网络论坛的广告投放方法及装置 |
-
2018
- 2018-10-18 CN CN201811213006.1A patent/CN109635073A/zh active Pending
- 2018-12-21 WO PCT/CN2018/122746 patent/WO2020077825A1/zh active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102214227A (zh) * | 2011-06-23 | 2011-10-12 | 华南理工大学 | 基于互联网层次结构存储的自动舆情监控方法 |
CN103347009A (zh) * | 2013-06-20 | 2013-10-09 | 新浪网技术(中国)有限公司 | 一种信息过滤方法及装置 |
US20140379719A1 (en) * | 2013-06-24 | 2014-12-25 | Tencent Technology (Shenzhen) Company Limited | System and method for tagging and searching documents |
CN103744881A (zh) * | 2013-12-20 | 2014-04-23 | 百度在线网络技术(北京)有限公司 | 一种问答平台的问题分发方法和问题分发系统 |
CN106095801A (zh) * | 2016-05-30 | 2016-11-09 | 海智(天津)大数据服务有限公司 | 一种基于大数据技术所见即所得的名称申报系统及方法 |
Also Published As
Publication number | Publication date |
---|---|
CN109635073A (zh) | 2019-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020077825A1 (zh) | 论坛社区应用管理方法、装置、设备及可读存储介质 | |
KR102455616B1 (ko) | 멀티 모달리티를 기반으로 하는 주제 분류 방법, 장치, 기기 및 저장 매체 | |
KR101858206B1 (ko) | 지능형 챗봇 기반 대화형 현장 지원 서비스 제공 방법 | |
US9230547B2 (en) | Metadata extraction of non-transcribed video and audio streams | |
US10733197B2 (en) | Method and apparatus for providing information based on artificial intelligence | |
CN110888990B (zh) | 文本推荐方法、装置、设备及介质 | |
US10770062B2 (en) | Adjusting a ranking of information content of a software application based on feedback from a user | |
WO2020253350A1 (zh) | 网络内容发布的审核方法、装置、计算机设备及存储介质 | |
US20180197548A1 (en) | System and method for diarization of speech, automated generation of transcripts, and automatic information extraction | |
KR102324048B1 (ko) | 커뮤니티 질의 응답 데이터의 검증 방법, 장치, 컴퓨터 기기 및 저장 매체 | |
US9146987B2 (en) | Clustering based question set generation for training and testing of a question and answer system | |
KR102041621B1 (ko) | 인공지능 음성인식 기반 기계학습의 대규모 말뭉치 구축을 위한 대화형 말뭉치 분석 서비스 제공 시스템 및 구축 방법 | |
US10803253B2 (en) | Method and device for extracting point of interest from natural language sentences | |
US9311395B2 (en) | Systems and methods for manipulating electronic content based on speech recognition | |
WO2018045646A1 (zh) | 基于人工智能的人机交互方法和装置 | |
US9015168B2 (en) | Device and method for generating opinion pairs having sentiment orientation based impact relations | |
CN111090771B (zh) | 歌曲搜索方法、装置及计算机存储介质 | |
CN109101551B (zh) | 一种问答知识库的构建方法及装置 | |
CN110414004A (zh) | 一种核心信息提取的方法和系统 | |
CN111858913A (zh) | 一种自动生成文本摘要的方法和系统 | |
CN112395391B (zh) | 概念图谱构建方法、装置、计算机设备及存储介质 | |
Shekhawat | Sentiment classification of current public opinion on BREXIT: Naïve Bayes classifier model vs Python’s TextBlob approach | |
WO2020233381A1 (zh) | 基于语音识别的服务请求方法、装置及计算机设备 | |
Arguello et al. | Using query performance predictors to reduce spoken queries | |
CN114186041A (zh) | 一种答案输出方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18937080 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 06/08/2021) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 18937080 Country of ref document: EP Kind code of ref document: A1 |