Text quality analysis method and device, electronic equipment and storage medium

Abstract

The invention discloses a text quality analysis method and device, electronic equipment and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: acquiring a text file uploaded by a user side; a selection instruction of the user side is responded, a task type selected by the selection instruction is determined, and the task type is used for representing the priority of the text file; intercepting local content of the text file according to the task type; and performing text quality analysis on the local content to obtain a preliminary evaluation result of the text file. Through the method and the device, the technical problem of long waiting time when the text file is evaluated in related technologies is solved, the key information is quickly acquired, the evaluation efficiency and the response speed are remarkably improved, evaluation personnel are helped to make more accurate preliminary judgment, and the time cost is saved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a text quality analysis method, device, electronic device and storage medium. Background Art

[0002] In related technologies, with the continuous growth of market demand, the number of movies and TV series has increased year by year, and the creation and evaluation of scripts has become an indispensable and important part of the film and television industry. However, in the evaluation process of scripts and novels, there are many bottlenecks that need to be solved. At present, because the time when producers upload works is often concentrated in a specific period of time, the existing evaluation system faces severe challenges of high-load operation. Especially when extracting key information, the evaluation system is particularly slow. Statistics show that it takes an average of 4.5 minutes to process every 10,000 words of content, and for novels of one million words, the evaluation cycle may take 7 to 8 hours. This will undoubtedly bring great inconvenience and trouble to projects that need to provide evaluation opinions quickly.

[0003] Existing script and novel evaluation methods are inefficient during peak hours and cannot meet the industry's urgent need for rapid evaluation.

[0004] With respect to the above-mentioned problems existing in the related technologies, no effective solutions have been found so far. Summary of the invention

[0005] The embodiments of the present invention provide a text quality analysis method, device, electronic device and storage medium to solve the technical problems in the related art.

[0006] According to one aspect of an embodiment of the present application, a method for analyzing text quality is provided, including: obtaining a text file uploaded by a user terminal; responding to a selection instruction of the user terminal, determining a task type selected by the selection instruction, wherein the task type is used to characterize the priority of the text file; intercepting local content of the text file according to the task type; and performing text quality analysis on the local content to obtain a preliminary evaluation result of the text file.

[0007] Further, intercepting the local content of the text file according to the task type includes: if the task type is a non-urgent task, detecting the range selection instruction triggered by the user terminal, wherein the task type includes urgent tasks and non-urgent tasks, and the priority of the non-urgent task is lower than the priority of the urgent task; intercepting the local content of the text file according to the range selection instruction, wherein the range selection instruction is used to select the text range of the local content to be intercepted.

[0008] Further, detecting the range selection instruction triggered by the user terminal includes: displaying a first option and a second option on the user interface of the user terminal, wherein the first option is used to select a percentage and the second option is used to select a word count; detecting a first range selection instruction for the first option, or detecting a second range selection instruction for the second option.

[0009] Further, responding to the selection instruction of the user terminal and determining the task type selected by the selection instruction includes one of the following: responding to the type selection instruction of the user terminal and determining the task type selected by the type selection instruction; responding to the result viewing instruction of the user terminal, if the viewing method indicated by the result viewing instruction is online viewing, determining that the task type corresponding to the result viewing instruction is a first task type; if the viewing method indicated by the result viewing instruction is offline viewing, determining that the task type corresponding to the result viewing instruction is a second task type, wherein the priority of the first task type is higher than the priority of the second task type.

[0010] Furthermore, after determining the task type selected by the selection instruction, the method also includes: if the task type is an urgent task, reading the number of requests for urgent tasks by the login account within a preset period, wherein the urgent task corresponds to the highest priority; determining whether the number of requests is less than the preset number; if the number of requests is less than the preset number, inserting the text file into the head of the task queue; extracting all the contents of the text file from the task queue, and performing text quality analysis on the entire content to obtain a complete evaluation result of the text file.

[0011] Further, the local content is parsed for text quality to obtain a preliminary evaluation result of the text file, including: parsing the literary genre type of the text file; obtaining the product strategy of the literary genre type, wherein the product strategy is used to indicate the marketing strategy of the platform to attract readers; generating a personalized prompt for the text file based on the product strategy; inputting the local content and the personalized prompt into a generative artificial intelligence AIGC model, and outputting a preliminary evaluation result in the text file, wherein the preliminary evaluation result includes at least one of the following: world view, story outline, episode synopsis, chapter synopsis, character biography, character relationship diagram, plot point, and chronology of major events.

[0012] Furthermore, after obtaining the preliminary evaluation result of the text file, the method also includes: detecting a continue processing instruction for the text file, wherein the continue processing instruction is used to indicate whether to continue text quality analysis of the remaining content of the text file; if the continue processing instruction is a continue parsing instruction, determining an evaluation result generation rule for the remaining content, configuring a task priority of the remaining content based on the evaluation result generation rule, and generating a full-text evaluation result of the remaining content based on the task priority; if the continue processing instruction is a terminate parsing instruction, ending the parsing task of the text file.

[0013] According to another aspect of an embodiment of the present application, a text quality analysis device is also provided, including: an acquisition module, used to acquire a text file uploaded by a user terminal; a determination module, used to respond to a selection instruction of the user terminal, and determine the task type selected by the selection instruction, wherein the task type is used to characterize the priority of the text file; an interception module, used to intercept local content of the text file according to the task type; and a first analysis module, used to perform text quality analysis on the local content to obtain a preliminary evaluation result of the text file.

[0014] Furthermore, the interception module includes: a detection unit, used to detect the range selection instruction triggered by the user terminal if the task type is a non-urgent task, wherein the task type includes urgent tasks and non-urgent tasks, and the priority of the non-urgent task is lower than the priority of the urgent task; an interception unit, used to intercept the local content of the text file according to the range selection instruction, wherein the range selection instruction is used to select the text range of the local content to be intercepted.

[0015] Further, the detection unit includes: a display subunit, used to display a first option and a second option on the user interface of the user terminal, wherein the first option is used to select a percentage and the second option is used to select a word count; a detection subunit, used to detect a first range selection instruction for the first option, or to detect a second range selection instruction for the second option.

[0016] Further, the determination module includes one of the following: a first determination unit, used to respond to the type selection instruction of the user terminal and determine the task type selected by the type selection instruction; a second determination unit, used to respond to the result viewing instruction of the user terminal, if the viewing method indicated by the result viewing instruction is online viewing, determine that the task type corresponding to the result viewing instruction is a first task type; if the viewing method indicated by the result viewing instruction is offline viewing, determine that the task type corresponding to the result viewing instruction is a second task type, wherein the priority of the first task type is higher than the priority of the second task type.

[0017] Furthermore, the device also includes: a reading module, which is used to read the number of requests for emergency tasks by the login account within a preset period after the determination module determines the task type selected by the selection instruction, if the task type is an emergency task, wherein the emergency task corresponds to the highest priority; a judgment module, which is used to judge whether the number of requests is less than the preset number; an insertion module, which is used to insert the text file into the head of the task queue if the number of requests is less than the preset number; and a second parsing module, which is used to extract all the contents of the text file from the task queue, and perform text quality analysis on the entire content to obtain a complete evaluation result of the text file.

[0018] Furthermore, the first parsing module includes: a parsing unit for parsing the literary genre type of the text file; an acquisition unit for acquiring the product strategy of the literary genre type, wherein the product strategy is used to indicate the marketing strategy of the platform to attract readers; a generation unit for generating a personalized prompt for the text file based on the product strategy; an output unit for inputting the local content and the personalized prompt into a generative artificial intelligence AIGC model, and outputting a preliminary evaluation result in the text file, wherein the preliminary evaluation result includes at least one of the following: world view, story outline, episode synopsis, chapter synopsis, character biography, character relationship diagram, plot point, and chronology of major events.

[0019] Furthermore, the device also includes: a detection module, which is used to detect a continue processing instruction for the text file after the first parsing module obtains the preliminary evaluation result of the text file, wherein the continue processing instruction is used to indicate whether to continue text quality analysis of the remaining content of the text file; a processing module, which is used to determine an evaluation result generation rule for the remaining content if the continue processing instruction is a continue parsing instruction, configure the task priority of the remaining content based on the evaluation result generation rule, and generate a full-text evaluation result of the remaining content based on the task priority; if the continue processing instruction is a terminate parsing instruction, end the parsing task of the text file.

[0020] According to another aspect of an embodiment of the present application, a storage medium is further provided, which includes a stored program, and the above steps are executed when the program is run.

[0021] According to another aspect of an embodiment of the present application, there is also provided an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; wherein: the memory is used to store computer programs; and the processor is used to execute the steps in the above method by running the program stored in the memory.

[0022] The embodiment of the present application also provides a computer program product including instructions, which, when executed on a computer, enables the computer to execute the steps in the above method.

[0023] The embodiments of the present invention propose a text quality analysis method, device, electronic device and storage medium, which obtain a text file uploaded by a user terminal; respond to a selection instruction of the user terminal, determine the task type selected by the selection instruction, wherein the task type is used to characterize the priority of the text file; intercept local content of the text file according to the task type; perform text quality analysis on the local content to obtain a preliminary evaluation result of the text file, quickly analyze the local content of the uploaded content, significantly reduce user waiting time, solve the technical problem of long waiting time when evaluating text files in related technologies, quickly obtain key information, significantly improve evaluation efficiency and response speed, help evaluators make more accurate preliminary judgments, and save time costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0025] Figure 1 is a hardware structure block diagram of a computer according to an embodiment of the present invention;

[0026] Figure 2 is a flow chart of a text quality analysis method according to an embodiment of the present invention;

[0027] Figure 3 is a flowchart of script parsing in an embodiment of the present invention;

[0028] Figure 4 is a structural block diagram of a text quality analysis device according to an embodiment of the present invention;

[0029] Figure 5 It is a structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] The method embodiment provided in the first embodiment of the present application can be executed in a mobile phone, a computer, a server or a similar computing device. Taking running on a computer as an example, Figure 1 is a hardware structure block diagram of a computer according to an embodiment of the present invention. Figure 1 As shown, the computer may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the computer may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0033] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as a computer program corresponding to a text quality analysis method in an embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0034] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0035] In this embodiment, a method for analyzing text quality is provided. Figure 2 is a flow chart of a text quality analysis method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0036] S202, obtaining a text file uploaded by the user;

[0037] The text file in this embodiment is a file in a text format (such as txt, word, etc.), and can also be a media file in a multimedia format including text and pictures.

[0038] S204, responding to the selection instruction of the user terminal, determining the task type selected by the selection instruction, wherein the task type is used to represent the priority of the text file;

[0039] Optionally, the task types include urgent tasks and non-urgent tasks. Urgent tasks are the highest priority tasks, while non-urgent tasks can be guaranteed to include multiple levels of priority.

[0040] S206, intercepting partial content of the text file according to the task type;

[0041] Optionally, the local content may be text content at a specified position or any position of a text file, such as the content of a fixed number of text pages at the front, summary content, and the content of a fixed number of words at the back.

[0042] After intercepting the local content, the script content is inserted into the task queue based on the priority corresponding to the task type. The text quality analysis process extracts the task text from the task queue in turn and performs text quality analysis. Optionally, the amount of local content data is negatively correlated with the priority level of the task type. The higher the priority level, the less the amount of local content data. The less the data, the faster the evaluation speed, so that high-priority text files can be evaluated first.

[0043] S208, performing text quality analysis on the local content to obtain a preliminary evaluation result of the text file.

[0044] The preliminary evaluation results of this embodiment include key information of the text file, which is used to describe the storyline and character attributes of the text file. The key information may include multiple items, each corresponding to a key element, such as world view, story outline, episode and chapter synopsis, character biographies, character relationship diagrams, plot points, etc. Among them, the world view is used to describe the fictional world where the story is located and its rules and background; the story outline is used to summarize the main plot and development direction of the whole story; the episode and chapter synopsis is used to summarize the main events and plot trends episode by episode or chapter by chapter; the character biographies are used to describe the background, personality and motivation of the main characters; the character relationship diagram is used to illustrate the relationship and interaction between the main characters; the plot points are used to mark the important turning points and climaxes in the story.

[0045] Optionally, the waiting time of the preliminary evaluation result can also be predicted based on the occupancy of the computing power resources of the evaluation device and the position of the local content in the task queue. The occupancy of the computing power resources can be GPU usage, memory occupancy, etc. The higher the occupancy of the computing power resources, the longer the waiting time, and the closer the position of the local content in the task queue is, the shorter the waiting time.

[0046] The solution of this embodiment can be applied to the evaluation platform to perform literary evaluation on text files, providing an efficient evaluation tool that can more quickly know the preliminary evaluation results of text quality analysis; the solution of this embodiment can also be applied to self-examination for content creators, helping authors to quickly understand the quality information of their works, so as to better create and optimize.

[0047] By adopting the scheme of this embodiment, a text file uploaded by a user terminal is obtained; in response to a selection instruction of the user terminal, a task type selected by the selection instruction is determined, wherein the task type is used to characterize the priority of the text file; local content of the text file is intercepted according to the task type; text quality analysis is performed on the local content to obtain a preliminary evaluation result of the text file, and the local content of the uploaded content is quickly analyzed, which significantly reduces the user waiting time, solves the technical problem of long waiting time when evaluating text files in related technologies, quickly obtains key information, significantly improves evaluation efficiency and response speed, helps evaluators make more accurate preliminary judgments, and saves time costs.

[0048] In one implementation of the present embodiment, intercepting the local content of the text file according to the task type includes: if the task type is a non-urgent task, detecting a range selection instruction triggered by the user terminal, wherein the task type includes urgent tasks and non-urgent tasks, and the priority of the non-urgent task is lower than the priority of the urgent task; intercepting the local content of the text file according to the range selection instruction, wherein the range selection instruction is used to select a text range of the local content to be intercepted.

[0049] In one example, detecting a range selection instruction triggered by the user terminal includes: displaying a first option and a second option on a user interface of the user terminal, wherein the first option is used to select a percentage and the second option is used to select a word count; detecting a first range selection instruction for the first option, or detecting a second range selection instruction for the second option.

[0050] Optionally, the first option and the second option are respectively preset with a maximum selection range, such as the first option can only select a maximum of 50%, and the second option can only select a maximum of 1,000 words or 50% of the total number of words.

[0051] In order to quickly provide valuable evaluation information, high-priority parsing tasks are prioritized, especially tasks for quickly parsing local content of uploaded manuscripts, such as the top 20%. Local content can usually represent the theme, style, and key plot of the work. Through this method, the system can generate key information within minutes. It effectively reduces the time cost of the initial evaluation, allowing users to have a preliminary and effective understanding of the work in the shortest time.

[0052] In the process of capturing partial contents of the text file, the screenshot can be taken according to the target range to the specified position of the text file, such as the first 20% of the content starting from the starting position, or partial contents can be captured from the middle position of the text file, such as capturing the chapter content corresponding to the middle climax part, or sub-contents can be captured from multiple positions of the text file and then combined into partial contents, such as capturing the introduction or summary content of each chapter as the sub-content corresponding to each position.

[0053] In this embodiment, responding to the selection instruction of the user terminal and determining the task type selected by the selection instruction includes one of the following: responding to the type selection instruction of the user terminal and determining the task type selected by the type selection instruction; responding to the result viewing instruction of the user terminal, if the viewing method indicated by the result viewing instruction is online viewing, determining that the task type corresponding to the result viewing instruction is a first task type; if the viewing method indicated by the result viewing instruction is offline viewing, determining that the task type corresponding to the result viewing instruction is a second task type, wherein the priority of the first task type is higher than the priority of the second task type.

[0054] In this embodiment, the user can directly select the task type, such as urgent task / ordinary task, non-urgent task, and non-urgent task can be divided into several priority levels, such as high priority task, low priority task, first priority task, second priority task, etc. If the lowest priority is selected, the entire content of the text file will be fully analyzed for text quality. In addition, the priority of the task can also be matched according to the result viewing method selected by the user. For online viewing scenarios, a higher priority can be matched to avoid users waiting for a long time in front of the interface. For offline viewing scenarios (pushing results to the user end), a relatively low priority can be matched to achieve better computing power allocation.

[0055] For works that users think have potential but are not in a hurry to conduct a complete evaluation, the system provides a low-priority full-text analysis service. The low-priority strategy aims to reasonably arrange computing resources to ensure the smooth execution of high-priority tasks and urgent tasks, while completing these low-priority analysis requirements within a certain time window. In this way, the system can balance the load and improve the efficiency and reliability of the overall operation.

[0056] In an implementation scenario of the present embodiment, after determining the task type selected by the selection instruction, the method also includes: if the task type is an urgent task, reading the number of requests for urgent tasks by the login account within a preset period, wherein the urgent task corresponds to the highest priority; determining whether the number of requests is less than the preset number; if the number of requests is less than the preset number, inserting the text file into the head of the task queue; extracting all the contents of the text file from the task queue, and performing text quality analysis on the entire content to obtain a complete evaluation result of the text file.

[0057] Optionally, the preset number of times is 1 and the preset period is one week.

[0058] You can choose to submit as a normal task or an urgent task. If you submit as a normal task, you can set the scope of the first outline generation. After submission, this task will be executed with P1 priority. If you choose an urgent task (one opportunity per person per week), you can directly parse the full text with P0 as the highest priority and directly generate a world view, story outline, character biography, character relationship diagram, etc.

[0059] For urgent projects, the system allows users to submit full-text analysis tasks with the highest priority. After receiving such requests, the system will concentrate all available computing resources to complete the full-text analysis as quickly as possible. This mechanism ensures that in extreme cases, such as the emergency launch of film and television projects, the short opening of the market window, etc., the system can respond quickly and provide comprehensive and detailed content evaluation.

[0060] In one implementation of the present embodiment, text quality analysis is performed on the local content to obtain a preliminary evaluation result of the text file, including: analyzing the literary genre type of the text file; obtaining the product strategy of the literary genre type, wherein the product strategy is used to indicate the marketing strategy of the platform to attract readers; generating a personalized prompt for the text file based on the product strategy; inputting the local content and the personalized prompt into a generative artificial intelligence AIGC model, and outputting a preliminary evaluation result in the text file, wherein the preliminary evaluation result includes at least one of the following: world view, story outline, episode synopsis, chapter synopsis, character biography, character relationship diagram, plot point, and chronology of major events.

[0061] The literary genre type in this embodiment may be a novel, a play, or a poem, an essay, a drama, a fable, a fairy tale, etc.

[0062] In another embodiment, text quality analysis is performed on the local content to obtain a preliminary evaluation result of the text file, including: analyzing the literary genre type of the text file; if the literary genre type is a script type, splitting the text file into multiple first sub-texts according to scenes; identifying a first preliminary evaluation result of the text file from the multiple first sub-texts, wherein the preliminary evaluation result includes: story outline, episode synopsis, character biographies, character relationship diagram, plot points, and a chronology of major events; if the literary genre type is a novel type, splitting the text file into multiple second sub-texts according to chapters; identifying a second preliminary evaluation result of the text file from the multiple second sub-texts, wherein the second preliminary evaluation result includes: worldview, story outline, chapter synopsis, character biographies, character relationship diagram, and a chronology of major events.

[0063] In this embodiment, the text file can be a novel, a script (such as a TV script, a film and television script, a short video script) or other literary genre types. By parsing the uploaded text file, regular expressions and large models can be used to automatically extract the episode number or scene number in the text file and complete the disassembly.

[0064] Optionally, after obtaining the preliminary evaluation result of the text file, the method further includes: detecting a continue processing instruction for the text file, wherein the continue processing instruction is used to indicate whether to continue text quality analysis of the remaining content of the text file; if the continue processing instruction is a continue parsing instruction, determining an evaluation result generation rule for the remaining content, configuring a task priority of the remaining content based on the evaluation result generation rule, and generating a full-text evaluation result of the remaining content based on the task priority; if the continue processing instruction is a terminate parsing instruction, ending the parsing task of the text file.

[0065] Optionally, configuring the task priority of the remaining content based on the evaluation result generation rule includes: if the evaluation result generation rule is a streaming segmentation generation rule, configuring the remaining content as a first priority; if the evaluation result generation rule is an overall generation rule, configuring the remaining content as a second priority, wherein the first priority is higher than the second priority, and the first priority is lower than the processing priority of the local content.

[0066] Optionally, a continue processing instruction may be generated based on the preliminary evaluation result. If the quality score of the preliminary evaluation result is higher than a preset score, a continue parsing instruction is generated; otherwise, a terminate parsing instruction is generated.

[0067] After the task is completed, the results will be pushed or displayed through the mobile terminal or web terminal. You can view it directly on the mobile terminal or on the web terminal. When viewing partial outline results on the web terminal, subsequent outlines will be automatically generated in batches through streaming to ensure that the user's reading is not affected. You can also choose not to read in streaming mode on the current page and directly parse the full text to generate the entire world view, story outline, character biography, character relationship diagram, and use the intelligent assistant to assist in understanding the content of the novel.

[0068] The solution of this embodiment provides an analytical method to improve evaluation efficiency, aiming to significantly increase the speed of script and novel evaluation, ensure the accuracy of the evaluation process, and better respond to market demand and timeliness. In this way, the entire film and television industry chain will be able to benefit from it and achieve a double leap in efficiency and quality.

[0069] Take the text file as a script as an example, Figure 3 It is a flow chart of script parsing in an embodiment of the present invention. After the script is uploaded, it is determined whether it is an urgent task. If so, it is configured to perform full-text parsing with the highest priority. If it is not an urgent task and the user chooses to parse partial content (20%) of the script, it is configured to perform parsing with high priority. After obtaining the preliminary evaluation results, based on the user's instructions, it is selected to continue parsing the full text with a low priority or to stop generating the evaluation results of the full text.

[0070] This solution is based on a fast evaluation method with dynamic priority adjustment. This method innovatively optimizes the evaluation process and focuses on parsing the first 20% of the uploaded content to quickly extract and provide key information to users. This mechanism allows users to form a preliminary impression and make a preliminary judgment on the work in a very short time, greatly shortening the initial response time of the evaluation. For works that are considered to be of high quality after preliminary analysis, users can choose to continue full-text analysis, thereby ensuring that high-quality content receives further in-depth evaluation support.

[0071] In addition, the system design takes into account the flexible needs of users and supports users to submit full-text analysis tasks with the highest priority according to actual needs. This function significantly reduces the waiting time during bottleneck periods and comprehensively improves the evaluation efficiency. Through this two-layer optimization strategy, not only the speed and effectiveness of preliminary judgments are guaranteed, but also strong technical support is provided for batch and in-depth evaluations.

[0072] Based on the priority dynamic adjustment mechanism of this embodiment, the parsing task priority is dynamically adjusted according to the system load and user needs, resource allocation is optimized, and the system response speed is improved. Based on the fast parsing technology, the first 20% of the uploaded content of the text file with high priority P1 is quickly parsed, which significantly reduces the user waiting time and improves the user experience. By quickly obtaining key information, it helps the evaluator to make a more accurate preliminary judgment and save time costs. Provide multi-level parsing services, provide the highest priority, high priority and low priority parsing services, priority P0>P1>P2>P3, the highest priority P0, directly parse the full text, each user has one opportunity per week, high priority P1, parse part of the content, the default is 20%, the user can set it by himself, up to 50%; priority P2, that is, when the user has generated an outline in reading P1, the system generates the remaining content in a streaming manner with P2 priority; low priority P3, after the content in P1 is parsed, if the user thinks the quality is high and hopes to directly generate the remaining part, he can submit the full text parsing of the remaining content, and the system continues to parse the remaining content with P3 priority. Meet the needs of different users, improve service flexibility, support the highest priority full-text analysis tasks, provide rapid response for emergency projects, and enhance the competitiveness of the company's services and market response speed.

[0073] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0074] In this embodiment, a text quality analysis device is also provided to implement the above-mentioned embodiments and preferred implementation modes, which have been described and will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0075] Figure 4 is a structural block diagram of a text quality analysis device according to an embodiment of the present invention, such as Figure 4 As shown, the device includes: an acquisition module 40, a determination module 42, an interception module 44, and a first analysis module 46, wherein:

[0076] The acquisition module 40 is used to acquire the text file uploaded by the user;

[0077] A determination module 42, configured to respond to a selection instruction of the user terminal and determine a task type selected by the selection instruction, wherein the task type is used to characterize a priority of the text file;

[0078] An interception module 44, used for intercepting partial content of the text file according to the task type;

[0079] The first analysis module 46 is used to perform text quality analysis on the local content to obtain a preliminary evaluation result of the text file.

[0080] Optionally, the interception module includes: a detection unit, used to detect the range selection instruction triggered by the user terminal if the task type is a non-urgent task, wherein the task type includes urgent tasks and non-urgent tasks, and the priority of the non-urgent task is lower than the priority of the urgent task; an interception unit, used to intercept the local content of the text file according to the range selection instruction, wherein the range selection instruction is used to select the text range of the local content to be intercepted.

[0081] Optionally, the detection unit includes: a display subunit, used to display a first option and a second option on the user interface of the user terminal, wherein the first option is used to select a percentage and the second option is used to select a word count; a detection subunit, used to detect a first range selection instruction for the first option, or to detect a second range selection instruction for the second option.

[0082] Optionally, the determination module includes one of the following: a first determination unit, used to respond to the type selection instruction of the user terminal, and determine the task type selected by the type selection instruction; a second determination unit, used to respond to the result viewing instruction of the user terminal, if the viewing method indicated by the result viewing instruction is online viewing, determine that the task type corresponding to the result viewing instruction is a first task type; if the viewing method indicated by the result viewing instruction is offline viewing, determine that the task type corresponding to the result viewing instruction is a second task type, wherein the priority of the first task type is higher than the priority of the second task type.

[0083] Optionally, the device also includes: a reading module, which is used to read the number of requests for emergency tasks made by the login account within a preset period after the determination module determines the task type selected by the selection instruction, if the task type is an emergency task, wherein the emergency task corresponds to the highest priority; a judgment module, which is used to judge whether the number of requests is less than the preset number; an insertion module, which is used to insert the text file into the head of the task queue if the number of requests is less than the preset number; and a second parsing module, which is used to extract all the contents of the text file from the task queue, and perform text quality analysis on the entire content to obtain a complete evaluation result of the text file.

[0084] Optionally, the first parsing module includes: a parsing unit for parsing the literary genre type of the text file; an acquisition unit for acquiring a product strategy of the literary genre type, wherein the product strategy is used to indicate a marketing strategy of a platform to attract readers; a generation unit for generating a personalized prompt for the text file based on the product strategy; an output unit for inputting the local content and the personalized prompt into a generative artificial intelligence AIGC model, and outputting a preliminary evaluation result in the text file, wherein the preliminary evaluation result includes at least one of the following: world view, story outline, episode synopsis, chapter synopsis, character biography, character relationship diagram, plot point, and chronology of major events.

[0085] Optionally, the device also includes: a detection module, used to detect a continue processing instruction for the text file after the first parsing module obtains the preliminary evaluation result of the text file, wherein the continue processing instruction is used to indicate whether to continue text quality analysis of the remaining content of the text file; a processing module, used to determine an evaluation result generation rule for the remaining content if the continue processing instruction is a continue parsing instruction, configure the task priority of the remaining content based on the evaluation result generation rule, and generate a full-text evaluation result of the remaining content based on the task priority; if the continue processing instruction is a terminate parsing instruction, end the parsing task of the text file.

[0086] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0087] The embodiment of the present application also provides an electronic device, Figure 5 is a structural diagram of an electronic device according to an embodiment of the present invention, such as Figure 5As shown, it includes a processor 51, a communication interface 52, a memory 53 and a communication bus 54, wherein the processor 51, the communication interface 52 and the memory 53 communicate with each other through the communication bus 54, and the memory 53 is used to store computer programs; when the processor 51 is used to execute the program stored in the memory 53, the following steps are implemented: obtaining a text file uploaded by a user terminal; responding to a selection instruction of the user terminal, determining a task type selected by the selection instruction, wherein the task type is used to characterize the priority of the text file; intercepting local content of the text file according to the task type; performing text quality analysis on the local content to obtain a preliminary evaluation result of the text file.

[0088] Further, intercepting the local content of the text file according to the task type includes: if the task type is a non-urgent task, detecting the range selection instruction triggered by the user terminal, wherein the task type includes urgent tasks and non-urgent tasks, and the priority of the non-urgent task is lower than the priority of the urgent task; intercepting the local content of the text file according to the range selection instruction, wherein the range selection instruction is used to select the text range of the local content to be intercepted.

[0089] Further, detecting the range selection instruction triggered by the user terminal includes: displaying a first option and a second option on the user interface of the user terminal, wherein the first option is used to select a percentage and the second option is used to select a word count; detecting a first range selection instruction for the first option, or detecting a second range selection instruction for the second option.

[0090] Further, responding to the selection instruction of the user terminal and determining the task type selected by the selection instruction includes one of the following: responding to the type selection instruction of the user terminal and determining the task type selected by the type selection instruction; responding to the result viewing instruction of the user terminal, if the viewing method indicated by the result viewing instruction is online viewing, determining that the task type corresponding to the result viewing instruction is a first task type; if the viewing method indicated by the result viewing instruction is offline viewing, determining that the task type corresponding to the result viewing instruction is a second task type, wherein the priority of the first task type is higher than the priority of the second task type.

[0091] Furthermore, after determining the task type selected by the selection instruction, the method also includes: if the task type is an urgent task, reading the number of requests for urgent tasks by the login account within a preset period, wherein the urgent task corresponds to the highest priority; determining whether the number of requests is less than the preset number; if the number of requests is less than the preset number, inserting the text file into the head of the task queue; extracting all the contents of the text file from the task queue, and performing text quality analysis on the entire content to obtain a complete evaluation result of the text file.

[0092] Further, the local content is parsed for text quality to obtain a preliminary evaluation result of the text file, including: parsing the literary genre type of the text file; obtaining the product strategy of the literary genre type, wherein the product strategy is used to indicate the marketing strategy of the platform to attract readers; generating a personalized prompt for the text file based on the product strategy; inputting the local content and the personalized prompt into a generative artificial intelligence AIGC model, and outputting a preliminary evaluation result in the text file, wherein the preliminary evaluation result includes at least one of the following: world view, story outline, episode synopsis, chapter synopsis, character biography, character relationship diagram, plot point, and chronology of major events.

[0093] Furthermore, after obtaining the preliminary evaluation result of the text file, the method also includes: detecting a continue processing instruction for the text file, wherein the continue processing instruction is used to indicate whether to continue text quality analysis of the remaining content of the text file; if the continue processing instruction is a continue parsing instruction, determining an evaluation result generation rule for the remaining content, configuring a task priority of the remaining content based on the evaluation result generation rule, and generating a full-text evaluation result of the remaining content based on the task priority; if the continue processing instruction is a terminate parsing instruction, ending the parsing task of the text file.

[0094] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0095] The communication interface is used for communication between the above terminal and other devices.

[0096] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0097] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0098] In another embodiment provided in the present application, a computer-readable storage medium is provided, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the text quality analysis method described in any of the above embodiments.

[0099] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the text quality analysis method described in any one of the above embodiments.

[0100] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive Solid State Disk (SSD)), etc.

[0101] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the protection scope of the present application.

[0102] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A text quality analysis method, characterized in that: include: Get the text file uploaded by the user; In response to the selection instruction of the user terminal, determining the task type selected by the selection instruction, wherein the task type is used to characterize the priority of the text file; intercepting partial content of the text file according to the task type; The local content is analyzed for text quality to obtain a preliminary evaluation result of the text file.

2. The method according to claim 1, characterized in that Intercepting the partial content of the text file according to the task type includes: If the task type is a non-urgent task, detecting a range selection instruction triggered by the user terminal, wherein the task type includes an urgent task and a non-urgent task, and the priority of the non-urgent task is lower than the priority of the urgent task; The partial content of the text file is intercepted according to the range selection instruction, wherein the range selection instruction is used to select a text range of the partial content to be intercepted.

3. The method according to claim 2, characterized in that Detecting the range selection instruction triggered by the user terminal includes: Displaying a first option and a second option on the user interface of the user terminal, wherein the first option is used to select a percentage and the second option is used to select a word count; A first range selection instruction for the first option is detected, or a second range selection instruction for the second option is detected.

4. The method according to claim 1, characterized in that In response to the selection instruction of the user terminal, determining the task type selected by the selection instruction includes one of the following: In response to the type selection instruction of the user terminal, determining the task type selected by the type selection instruction; In response to the result viewing instruction of the user terminal, if the viewing mode indicated by the result viewing instruction is online viewing, determining that the task type corresponding to the result viewing instruction is the first task type; If the viewing mode indicated by the result viewing instruction is offline viewing, it is determined that the task type corresponding to the result viewing instruction is a second task type, wherein the priority of the first task type is higher than that of the second task type.

5. The method according to claim 1, characterized in that After determining the task type selected by the selection instruction, the method further includes: If the task type is an urgent task, read the number of requests for urgent tasks by the login account within a preset period, wherein the urgent task corresponds to the highest priority; Determine whether the number of requests is less than a preset number; If the request number is less than the preset number, inserting the text file into the head of the task queue; The entire contents of the text file are extracted from the task queue, and text quality analysis is performed on the entire contents to obtain a complete evaluation result of the text file.

6. The method according to claim 1, characterized in that Perform text quality analysis on the local content to obtain a preliminary evaluation result of the text file, including: Analyzing the literary genre type of the text file; Obtaining a product strategy for the literary genre type, wherein the product strategy is used to indicate a marketing strategy for the platform to attract readers; Generate a personalized prompt for the text file based on the product strategy; The local content and the personalized prompt are input into a generative artificial intelligence AIGC model, and a preliminary evaluation result in the text file is output, wherein the preliminary evaluation result includes at least one of the following: world view, story outline, episode synopsis, chapter synopsis, character biographies, character relationship diagrams, plot points, and a chronology of major events.

7. The method according to claim 1, characterized in that After obtaining the preliminary evaluation result of the text file, the method further includes: detecting a continue processing instruction for the text file, wherein the continue processing instruction is used to indicate whether to continue to perform text quality analysis on the remaining content of the text file; If the continue processing instruction is a continue parsing instruction, determine the evaluation result generation rule for the remaining content, configure the task priority of the remaining content based on the evaluation result generation rule, and generate the full-text evaluation result of the remaining content based on the task priority; if the continue processing instruction is a terminate parsing instruction, end the parsing task of the text file.

8. A text quality analysis device, characterized in that: include: The acquisition module is used to obtain the text file uploaded by the user; A determination module, configured to respond to a selection instruction of the user terminal and determine a task type selected by the selection instruction, wherein the task type is used to characterize a priority of the text file; An interception module, used for intercepting partial content of the text file according to the task type; The first parsing module is used to perform text quality analysis on the local content to obtain a preliminary evaluation result of the text file.

9. An electronic device, characterized in that: The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the text quality analysis method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the text quality analysis method as claimed in any one of claims 1 to 7.

Images