Text cleaning method and device

Abstract

The embodiment of the invention provides a text cleaning method. The text cleaning method comprises the steps of obtaining a plurality of target texts; inputting each target text into a preset text evaluation model to obtain a target coefficient for each target text; wherein the preset text evaluation model is used for evaluating the coefficient of the text according to the content of the input text; according to the target coefficient of each target text, filtering out a to-be-audited text from the plurality of target texts; and re-confirming the to-be-audited text, so as to clean or retain the to-be-audited text according to a re-confirmation result. According to the technical scheme provided by the embodiment of the invention, before whether the obtained texts are cleaned or not is confirmed again, the texts are graded through the model, the to-be-audited texts meeting the specific coefficients are filtered out, and the to-be-audited texts are confirmed again, so that the accuracy of data search is improved, and the efficiency of text cleaning work is also improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular, to a text cleaning method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] As the number of netizens continues to grow, the amount of online information generated by netizens is also increasing, which has put great pressure on real-time risk control. Many illegal contents are difficult to identify in real time and can only be screened and cleaned up by some technical means after the content is published.

[0003] In the area of ​​review, the platform may review published reviews multiple times to try to avoid any violations or false content.

[0004] However, due to the huge amount of information generated by the Internet every day, existing text cleaning methods are inefficient in tasks such as information screening.

[0005] It should be noted that the above content is not necessarily prior art, nor is it intended to limit the scope of patent protection of this application. Summary of the invention

[0006] Embodiments of the present application provide a text cleaning method, apparatus, computer device, computer-readable storage medium, and computer program product to solve or alleviate one or more of the technical problems raised above.

[0007] One aspect of an embodiment of the present application provides a text cleaning method, the method comprising: Get multiple target texts; Input each of the target texts into a preset text evaluation model to obtain a target coefficient for each of the target texts; wherein the preset text evaluation model is used to evaluate the coefficient of the text according to the content of the input text; Filtering the texts to be reviewed from the multiple target texts according to the target coefficients of the target texts; The text to be reviewed is reconfirmed to clear or retain the text to be reviewed based on the reconfirmation result.

[0008] Optionally, the method further comprises: Filtering the target text according to a preset filtering condition; When the target text satisfies the preset filtering condition, the target text is determined to be a text to be reviewed.

[0009] Optionally, the preset filtering condition includes a target device code range; The filtering of the target text according to the preset filtering condition comprises: Obtaining a sending device code corresponding to the target text; According to the target device code range and the sending device code, it is confirmed whether the target text meets the preset filtering condition.

[0010] Optionally, obtaining the target text includes: Receiving real-time data from a target database, wherein the real-time data includes real-time text; Determining the real-time text as the target text; The publishing time of the real-time text is within a preset time range of the current time.

[0011] Optionally, the method further comprises: The text to be reviewed and the corresponding coefficients are transferred to the approval node, so as to feedback the approval result through the approval node; If the approval result is that there is no error, determine to transfer the to-be-approved document to a target processing node; Wherein, if the approval result is an error, the text to be reviewed will not be transferred to the target processing node; The target processing node is used to reconfirm the text to be reviewed.

[0012] Optionally, the method further comprises: Obtain the target account associated with the text to be reviewed; Obtain the number of pending approval documents associated with the target account; When the approval result for the pending text is that no error occurs and the number of the pending text does not exceed a preset number, the pending text is filtered out and is not transferred to the target processing node.

[0013] Another aspect of an embodiment of the present application provides a text cleaning device, the device comprising: An acquisition module, used to acquire multiple target texts; An input module, used for inputting each of the target texts into a preset text evaluation model to obtain a target coefficient for each of the target texts; wherein the preset text evaluation model is used for evaluating the coefficient of the text according to the content of the input text; A filtering module, used for filtering the texts to be reviewed from the plurality of target texts according to the target coefficients of the target texts; A module is added to reconfirm the text to be reviewed, so as to clear or retain the text to be reviewed according to the reconfirmation result.

[0014] Another aspect of an embodiment of the present application provides a computer device, including: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein: the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method as described above.

[0015] Another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method described above is implemented.

[0016] Another aspect of an embodiment of the present application provides a computer program product, including a computer program, which implements the method described above when executed by a processor.

[0017] The embodiments of the present application using the above-mentioned technical solution may include the following advantages: before reconfirming whether to clean the acquired texts, these texts are scored through the model, and the texts to be reviewed that meet specific coefficients are filtered out, and the texts to be reviewed are reconfirmed, which improves the accuracy of data search and also helps to improve the efficiency of text cleaning work. BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0018] Figure 1 A diagram schematically shows an operating environment of a text cleaning method according to Embodiment 1 of the present application; Figure 2 A flowchart of a text cleaning method according to Embodiment 1 of the present application is schematically shown; Figure 3 A newly added flow chart of the text cleaning method according to the first embodiment of the present application is schematically shown; Figure 4 Schematically shows Figure 3 Flow chart of sub-steps of step S300; Figure 5 Schematically shows Figure 2 Flow chart of sub-steps of step S200; Figure 6 Another newly added flow chart of the text cleaning method according to the first embodiment of the present application is schematically shown; Figure 7 A further newly added flow chart of the text cleaning method according to the first embodiment of the present application is schematically shown; Figure 8 The application flow chart of the text cleaning method according to the first embodiment of the present application is schematically shown; Fig. 9 A block diagram schematically shows a text cleaning device according to the second embodiment of the present application; and Fig.10 The hardware architecture diagram of the computer device according to the third embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0020] It should be noted that the descriptions involving "first", "second", etc. in the embodiments of the present application are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0021] In the description of the present application, it should be understood that the numerical labels before the steps do not indicate the order in which the steps are executed, but are only used to facilitate the description of the present application and to distinguish each step, and therefore should not be understood as a limitation on the present application.

[0022] First, the following terms are explained: Cleaning: In the world of content review, “cleaning” refers to the process of re-reviewing or reviewing content that has already been published or reviewed.

[0023] Danmu: subtitles that pop up and move in a predetermined direction when watching a video on the Internet. There is no fixed word for Danmu in English, and it is usually called: comment, danmaku, barrage, bullet screen, bullet-screen comment, etc. Danmu allows viewers to comment or feel something, but unlike ordinary video sharing websites that only display comments in the dedicated comment area under the player, it will appear in real time on the video screen in the form of sliding subtitles to ensure that all viewers can notice it. Danmu can be managed by the Danmu system. Some Danmu systems can use CSS (Cascading StyleSheets) or JavaScript language to provide specific Danmu forms, such as the appearance or disappearance of Danmu in a specific position, control the speed of Danmu pop-up, Danmu position, etc. In addition, the Danmu that appears fixed at the bottom or top of the screen will also be used as subtitles for videos without subtitles.

[0024] LLMs: Large Language Models, a class of large-scale machine learning models based on deep learning, used to handle natural language processing tasks.

[0025] Roberta: is a pre-trained language model that can be used for natural language processing tasks such as text classification, sentiment analysis, question answering systems, and text summarization.

[0026] MessageJudge: It is an intelligent text review framework based on deep learning that can be used to filter and manage various text contents.

[0027] Text updates: short, real-time posts or messages published by users to share personal opinions, status updates, short comments or quick responses to a topic.

[0028] Private Message: refers to a one-to-one private communication between users.

[0029] Text column: refers to longer articles or comments posted by users.

[0030] Account signature: refers to a personalized text or picture set by the user.

[0031] Asynchronous processing: refers to the process in which a task is executed without blocking the further execution of the program. When a program initiates an asynchronous request, it does not wait for the request to be completed, but continues to execute subsequent operations.

[0032] Secondly, in order to facilitate those skilled in the art to understand the technical solutions provided in the embodiments of the present application, the relevant technologies are described below: As the number of netizens continues to grow, the amount of online information generated by netizens is also increasing, which has put a lot of pressure on real-time risk control. Many illegal contents are difficult to identify in real time, and can only be screened and cleaned up by some technical means after the content is published. Therefore, a good cleaning platform is very important.

[0033] However, the inventors have found that due to the huge amount of information generated on the Internet every day, existing cleaning methods are inefficient in information screening and other tasks.

[0034] To this end, the embodiment of the present application provides a technical solution for cleaning texts. In this technical solution, before reconfirming whether to clean the acquired texts, the texts are scored through the model, and the texts to be reviewed that meet the specific coefficients are filtered out, and the texts to be reviewed are reconfirmed, which improves the accuracy of data search and also helps to improve the efficiency of text cleaning work. See below for details.

[0035] Finally, for ease of understanding, an exemplary operating environment is provided below.

[0036] like Figure 1 As shown, the operating environment diagram includes: a server 2, a network 4, and one or more clients 6, wherein: The server 2 may be a device such as a rack server, a blade server, a tower server or a cabinet server (including an independent server or a server cluster composed of multiple servers), etc. The server 2 may include multiple processing nodes, each of which may process the data received from the client 6 in a corresponding processing manner.

[0037] The server 2 may be configured to communicate with the client 6, etc., via a network 4. The network 4 includes various network devices, such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices, and / or the like. The network may include physical links, such as coaxial cable links, twisted pair cable links, optical fiber links, combinations thereof, etc., or wireless links, such as cellular links, satellite links, Wi-Fi links, etc.

[0038] The client 6 may be an electronic device running an operating system such as Windows, Android™ or iOS, such as a smart phone, a tablet device, a laptop computer, a virtual reality device, a gaming device, a set-top box, a vehicle-mounted terminal, or a smart TV. Based on the above operating system, various application programs may be run, such as a text input program, through which corresponding text (such as comments, text dynamics, etc.) may be input and sent to the server 2 via the network 4.

[0039] It should be noted that the above devices are exemplary, and the number and type of devices are adjustable in different scenarios or according to different needs.

[0040] The following uses the server 2 as the execution subject to introduce the technical solution of the present application through multiple embodiments. It should be noted that these embodiments can be implemented in a variety of different forms and should not be interpreted as being limited to the embodiments described here.

[0041] Embodiment 1 Figure 2 The flowchart of the text cleaning method according to the first embodiment of the present application is schematically shown.

[0042] like Figure 2 As shown, the text cleaning method may include steps S200 to S206, wherein: Step S200, obtaining multiple target texts.

[0043] Step S202, input each of the target texts into a preset text evaluation model to obtain a target coefficient for each of the target texts; wherein the preset text evaluation model is used to evaluate the coefficient of the text according to the content of the input text.

[0044] Step S204: filtering out the texts to be reviewed from the multiple target texts according to the target coefficients of the target texts.

[0045] Step S206, reconfirming the text to be reviewed, and clearing or retaining the text to be reviewed according to the reconfirmation result.

[0046] The text cleaning method provided in this embodiment scores the acquired texts through a model before reconfirming whether to clean the texts, filters out the texts to be reviewed that meet specific coefficients, and reconfirms the texts to be reviewed, which improves the accuracy of data search and also helps to improve the efficiency of text cleaning work.

[0047] The following combination Figure 2 , each step in steps S200~S206 and other optional steps are described in detail.

[0048] Step S200 , get multiple target texts.

[0049] In specific implementation, the target text may include comments, bullet screens, text dynamics, private messages, etc. sent by users. In some embodiments, the target text may also include text columns, account signatures, and other texts.

[0050] Step S202, input each of the target texts into a preset text evaluation model to obtain a target coefficient for each of the target texts; wherein the preset text evaluation model is used to evaluate the coefficient of the text according to the content of the input text.

[0051] In a specific implementation, the text evaluation model may be LLMs, Roberta, MessageJudge, etc. In other embodiments, the text evaluation model may also be other available models for identifying inappropriate content or illegal content in a text.

[0052] In this embodiment, before cleaning, the acquired text content is scored by the text evaluation model. This can help the cleaning system to initially grasp the violation risk of the text to be cleaned, thereby optimizing the allocation of computing resources, improving the cleaning efficiency, and ensuring that the cleaning system can focus on the text with high review requirements.

[0053] Step S204 , according to the target coefficient of each of the target texts, filtering out the texts to be reviewed from the multiple target texts.

[0054] In specific implementation, a coefficient threshold may be pre-defined, and texts whose coefficients exceed the threshold may be judged as texts to be reviewed with a higher risk of violation.

[0055] In this embodiment, whether the target text is a text to be reviewed is determined based on the coefficient of the target text, so that the risk level of text violation can be quantified, and accurate risk control and response strategies can be implemented.

[0056] In an optional embodiment, if Figure 3 As shown, the method also includes: S300: Filter the target text according to a preset filtering condition.

[0057] S302: When the target text satisfies the preset filtering condition, determine that the target text is a text to be reviewed.

[0058] In specific implementation, the preset filtering conditions may include specific accounts, specific content, video numbers or video tags, etc. For example, when the target text includes certain specific illegal content (such as rumors or false information), the target text is determined to be a text to be reviewed with a high risk of illegality.

[0059] In this embodiment, various filtering conditions are set to determine whether the target text violates the regulations. Through technical means such as keyword matching and semantic analysis, potential illegal content can be automatically screened and identified, thereby improving monitoring efficiency and accuracy.

[0060] In an optional embodiment, the preset filtering condition includes a target device code range, such as Figure 4 As shown, step S300 includes: S400, obtaining a sending device code corresponding to the target text.

[0061] S402: confirm whether the target text satisfies the preset filtering condition according to the target device code range and the sending device code.

[0062] In actual applications, it may happen that certain devices are used to frequently publish illegal content.

[0063] Therefore, in this embodiment, the cleaning system can be set to focus on monitoring the text content sent by certain devices by recording the device code corresponding to the device, and judge these texts as texts to be reviewed with a higher risk of violation. In this way, the monitoring efficiency and response speed of these high-risk devices can be improved, and measures can be taken in time to prevent the spread of illegal content.

[0064] In actual applications, there will be a large number of illegal contents coming from the same IP address. Under the premise of compliance and obtaining the consent of the content creator, the cleaning system can determine whether to identify the target text as a text to be reviewed by sending the IP address of the target text. In this way, these high-risk IP addresses can be analyzed in detail to timely discover and prevent the spread of illegal content, thereby improving the efficiency of the cleaning system.

[0065] In an optional embodiment, if Figure 5 As shown, step S200 includes: S500, receiving real-time data from a target database, where the real-time data includes real-time text.

[0066] S502, determining the real-time text as the target text; wherein the publishing time of the real-time text is within a preset time range of the current time.

[0067] In specific implementation, a corresponding target database can be set for each business, such as a bullet screen database, a comment database, and a private message database. According to actual needs, the preset time range can be set to 3 hours, 6 hours, etc. The cleanup system can also be set to asynchronously obtain the corresponding real-time data from the target database and save it, thereby avoiding excessive query pressure on the database.

[0068] In other embodiments, the cleaning system may also determine the target text based on historical data obtained from the target database whose publishing time exceeds a preset time range.

[0069] In this embodiment, the cleaning system can obtain the real-time text that has just been published from the target database for cleaning. Thus, through real-time cleaning, potential risk content can be quickly identified and responded to, so that the content can be reviewed and processed soon after it is published, effectively reducing the spread and impact of harmful information.

[0070] In an optional embodiment, if Figure 6 As shown, the method also includes: S600: The text to be reviewed and the corresponding coefficients are transferred to the approval node, so that the approval result is fed back through the approval node.

[0071] S602, when the approval result is that there is no error, determine to transfer the to-be-approved document to a target processing node; wherein, S604, when the approval result is an error, the to-be-approved document is not transferred to the target processing node; The target processing node is used to reconfirm the text to be reviewed.

[0072] In this embodiment, the cleaning system will review the texts to be reviewed confirmed in the above process. In the specific implementation, the approval node can be set to review the files of the texts to be reviewed exported by the cleaning system, and some of the texts that are not in violation of the rules can be removed. The approval node can also be set to review and modify the model parameters, filtering conditions, etc. set in the above filtering process.

[0073] This can improve the flexibility and accuracy of approval, ensure that only texts that are truly in violation of regulations are processed, and improve the efficiency and response speed of the overall system.

[0074] In an optional embodiment, if Figure 7 As shown, the method also includes: S700: Obtain a target account number associated with the text to be reviewed.

[0075] S702, obtaining the number of documents to be approved that are associated with the target account.

[0076] S704: When the approval result of the to-be-approved text is no error and the number of the to-be-approved text does not exceed a preset number, the to-be-approved text is filtered out and not transferred to the target processing node.

[0077] In this embodiment, the cleaning system can filter out texts sent by accounts that send fewer texts to be reviewed. This can reduce the workload of text cleaning and improve cleaning efficiency, while ensuring that accounts that send more texts to be reviewed are monitored, so as to more effectively control and manage the spread of texts to be reviewed.

[0078] Step S206 , reconfirm the text to be reviewed, and clean up or retain the text to be reviewed according to the reconfirmation result.

[0079] In specific implementation, the cleaning system can be set to delete the pending review texts that are confirmed as violations in the cleaning task from the relevant platform so that they are not displayed to users. According to actual needs, the cleaning system can also be set to ban the account that sent the pending review texts that are confirmed as violations.

[0080] In this embodiment, the cleaning task performs a second confirmation on the filtered text to be reviewed, determines whether it is illegal content, and performs corresponding processing. In this way, the accuracy and fairness of content review can be ensured, misjudgment and missed judgment can be reduced, and the efficiency and effect of the overall review process can be improved.

[0081] In order to make this application easier to understand, the following Figure 8 An exemplary application is provided. S11, the cleaning system obtains 100 texts from the database, all of which were generated within 3 hours, including 50 comment texts, 20 bullet texts, 10 text dynamics, 10 private messages, and 10 account signatures.

[0082] S12, these 100 texts are evaluated through the text evaluation model, and there are 30 texts to be reviewed with scores exceeding 90 points.

[0083] S13, 10 texts involving certain false information keywords are filtered out from the remaining 70 texts to be reviewed.

[0084] S14, among the remaining 60 texts, there are 5 texts whose sending device number is A, and these 5 texts are included in the texts to be reviewed.

[0085] S15, among the remaining 55 texts, there are 5 texts sent from IP B, and these 5 texts are included in the texts to be reviewed.

[0086] S16, the 50 filtered texts to be reviewed are reviewed, and it is found that the review results of 20 of the texts to be reviewed are errors.

[0087] S17, among the 30 pending texts with no error in the approval results, 10 texts were sent by accounts that sent less than 5 pending texts, and these 10 texts were filtered out from the pending texts.

[0088] S18, adding the remaining 20 pending review texts with no errors in the approval results to the cleanup task.

[0089] S19, executing the cleanup task, found that 15 of the texts to be reviewed were confirmed to be illegal content, and the corresponding accounts were banned.

[0090] Embodiment 2 Fig. 9 The block diagram of the text cleaning device according to the second embodiment of the present application is schematically shown. The device can be divided into one or more program modules, one or more program modules are stored in a storage medium, and are executed by one or more processors to complete the embodiment of the present application. The program module referred to in the embodiment of the present application refers to a series of computer program instruction segments that can complete specific functions. The following description will specifically introduce the functions of each program module in this embodiment. Fig. 9 As shown, the device 1000 may include: an acquisition module 1100, an input module 1200, a filtering module 1300, and an adding module 1400, wherein: An acquisition module 1100 is used to acquire multiple target texts; An input module 1200 is used to input each of the target texts into a preset text evaluation model to obtain a target coefficient for each of the target files; wherein the preset text evaluation model is used to evaluate the coefficient of the text according to the content of the input text; A filtering module 1300 is used to filter out the texts to be reviewed from the multiple target texts according to the target coefficients of the target files; A module 1400 is added to reconfirm the text to be reviewed, so as to clear or retain the text to be reviewed according to the reconfirmation result.

[0091] As an optional embodiment, the device 1000 may also be used for: Filtering the target text according to a preset filtering condition; When the target text satisfies the preset filtering condition, the target text is determined to be a text to be reviewed.

[0092] As an optional embodiment, the preset filtering condition includes a target device code range, and the apparatus 1000 may also be used for: Obtaining a sending device code corresponding to the target text; According to the target device code range and the sending device code, it is confirmed whether the target text meets the preset filtering condition.

[0093] As an optional embodiment, the device 1000 may also be used for: Receiving real-time data from a target database, wherein the real-time data includes real-time text; Determining the real-time text as the target text; The publishing time of the real-time text is within a preset time range of the current time.

[0094] As an optional embodiment, the device 1000 may also be used for: The text to be reviewed and the corresponding coefficients are transferred to the approval node, so as to feedback the approval result through the approval node; If the approval result is that there is no error, determine to transfer the to-be-approved document to a target processing node; Wherein, if the approval result is an error, the text to be reviewed will not be transferred to the target processing node; The target processing node is used to reconfirm the text to be reviewed.

[0095] As an optional embodiment, the device 1000 may also be used for: Obtain the target account associated with the text to be reviewed; Obtain the number of pending approval documents associated with the target account; When the approval result for the pending text is an error, and the number of the pending text exceeds a preset number, the pending text is filtered out and is not transferred to the target processing node.

[0096] Embodiment 3 Fig.10 The schematic diagram of the hardware architecture of a computer device 10000 suitable for implementing a text cleaning method according to the third embodiment of the present application is shown. In some embodiments, the computer device 10000 may be a terminal device such as a smart phone, a wearable device, a tablet computer, a personal computer, a vehicle terminal, a game console, a virtual device, a workbench, a digital assistant, a set-top box, a robot, etc. In other embodiments, the computer device 10000 may be a rack server, a blade server, a tower server, or a cabinet server (including an independent server, or a server cluster composed of multiple servers), etc. Fig.10 As shown, the computer device 10000 includes but is not limited to: a memory 10010, a processor 10020, and a network interface 10030 that can communicate with each other through a system bus. Among them: The memory 10010 includes at least one type of computer-readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 10010 can be an internal storage module of the computer device 10000, such as a hard disk or memory of the computer device 10000. In other embodiments, the memory 10010 can also be an external storage device of the computer device 10000, such as a plug-in hard disk equipped on the computer device 10000, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 10010 can also include both the internal storage module of the computer device 10000 and its external storage device. In this embodiment, the memory 10010 is generally used to store the operating system and various application software installed in the computer device 10000, such as program codes of the text cleaning method, etc. In addition, the memory 10010 can also be used to temporarily store various data that have been output or are to be output.

[0097] In some embodiments, the processor 10020 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other chips. The processor 10020 is generally used to control the overall operation of the computer device 10000, such as performing control and processing related to data interaction or communication with the computer device 10000. In this embodiment, the processor 10020 is used to run the program code stored in the memory 10010 or process data.

[0098] The network interface 10030 may include a wireless network interface or a wired network interface, and the network interface 10030 is generally used to establish a communication link between the computer device 10000 and other computer devices. For example, the network interface 10030 is used to connect the computer device 10000 to an external terminal through a network, and to establish a data transmission channel and a communication link between the computer device 10000 and the external terminal. The network may be a wireless or wired network such as an intranet, the Internet, the Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G network, Bluetooth, Wi-Fi, etc.

[0099] It should be pointed out that Fig.10 Only a computer device having components 10010 - 10030 is shown, but it should be understood that implementation of all of the components shown is not a requirement, and more or fewer components may alternatively be implemented.

[0100] In this embodiment, the text cleaning method stored in the memory 10010 can also be divided into one or more program modules and executed by one or more processors (such as processor 10020) to complete the embodiment of the present application.

[0101] Embodiment 4 An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the text cleaning method in the embodiment are implemented.

[0102] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the computer-readable storage medium can be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium can also be an external storage device of a computer device, such as a plug-in hard disk equipped on the computer device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the computer-readable storage medium can also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the computer-readable storage medium is generally used to store an operating system and various application software installed on the computer device, such as the program code of the text cleaning method in the embodiment, etc. In addition, the computer-readable storage medium can also be used to temporarily store various types of data that have been output or are to be output.

[0103] Embodiment 5 An embodiment of the present application also provides a computer program product, including a computer program, which implements the method in the above embodiment when executed by a processor.

[0104] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present application can be implemented by general-purpose computer devices, they can be concentrated on a single computer device, or distributed on a network composed of multiple computer devices, optionally, they can be implemented by executable program codes of computer devices, so that they can be stored in a storage device and executed by the computer device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0105] It should be noted that the above are only preferred embodiments of the present application, and the patent protection scope of the present application is not limited thereto. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A text cleaning method, characterized in that: The method comprises: Get multiple target texts; Input each of the target texts into a preset text evaluation model to obtain a target coefficient for each of the target texts; wherein the preset text evaluation model is used to evaluate the coefficient of the text according to the content of the input text; Filtering the texts to be reviewed from the multiple target texts according to the target coefficients of the target texts; The text to be reviewed is reconfirmed to clear or retain the text to be reviewed based on the reconfirmation result.

2. The method according to claim 1, characterized in that The method further comprises: Filtering the target text according to a preset filtering condition; When the target text satisfies the preset filtering condition, the target text is determined to be a text to be reviewed.

3. The method according to claim 2, characterized in that The preset filtering conditions include the target device code range; The filtering of the target text according to the preset filtering condition comprises: Obtaining a sending device code corresponding to the target text; According to the target device code range and the sending device code, it is confirmed whether the target text meets the preset filtering condition.

4. The method according to any one of claims 1 to 3, characterized in that: The obtaining of the target text comprises: Receiving real-time data from a target database, wherein the real-time data includes real-time text; Determining the real-time text as the target text; The publishing time of the real-time text is within a preset time range of the current time.

5. The method according to claim 1, characterized in that The method further comprises: The text to be reviewed and the corresponding coefficients are transferred to the approval node, so as to feedback the approval result through the approval node; If the approval result is that there is no error, determine to transfer the to-be-approved document to a target processing node; Wherein, if the approval result is an error, the text to be reviewed will not be transferred to the target processing node; The processing node is used to reconfirm the text to be reviewed.

6. The method according to claim 5, characterized in that The method further comprises: Obtain the target account associated with the text to be reviewed; Obtain the number of pending approval documents associated with the target account; When the approval result for the pending text is that no error occurs and the number of the pending text does not exceed a preset number, the pending text is filtered out and is not transferred to the target processing node.

7. A text cleaning device, characterized in that: The device comprises: An acquisition module, used to acquire multiple target texts; An input module, used for inputting each of the target texts into a preset text evaluation model to obtain a target coefficient for each of the target texts; wherein the preset text evaluation model is used for evaluating the coefficient of the text according to the content of the input text; A filtering module, used for filtering the texts to be reviewed from the plurality of target texts according to the target coefficients of the target texts; A module is added to reconfirm the text to be reviewed, so as to clear or retain the text to be reviewed according to the reconfirmation result.

8. A computer device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; wherein: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to claims 1 to 6 are implemented.

Images