Content creation process automatic management method supporting multi-node cooperation

Abstract

The invention relates to the technical field of creation process management, in particular to a content creation process automatic management method supporting multi-node cooperation, which comprises the following processes: step 1, process definition and visual arrangement: defining a content creation process according to requirements and targets of a project, and performing arrangement through a visual interface; and step 2, intelligent task allocation and priority ranking: performing task allocation by using an intelligent algorithm according to the properties and complexity of the tasks and the skills and experience of team members, and performing priority ranking according to the emergency degree and importance of the tasks. The problems of information isolated island and repeated work in the process due to neglect of cooperation and communication among multiple nodes and difficulty in effective management and coordination of complex tasks involving multiple links and multiple participants in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of creative process management, and particularly to an automated management method for content creation processes that supports multi-node collaboration. Background Art

[0002] The automated management method for content creation processes is an efficient and intelligent content production method. By means of advanced technical tools and management strategies, it automates all links of content creation, thereby significantly improving the efficiency and quality of content production. According to the content type and marketing objectives, content templates are designed and constructed, and the templates are decomposed into elements, including graphics, videos, music, etc. A template library is established, and relevant texts, pictures, videos, etc. are collected and sorted. The materials are classified and stored for subsequent rapid retrieval. Using artificial intelligence technology, the intelligence of content creation is realized, such as tools for natural language generation (NLG), text generation, image generation, etc., which can be used to generate content such as articles, pictures, videos, etc. AI tools can also perform tasks such as hot topic monitoring, benchmark monitoring, and material crawling, providing rich materials and inspiration for content creation. According to specific requirements, various small tools and browser plugins are developed or selected to assist content creation and management. The automated management method for content creation processes realizes the automated and intelligent management of content creation processes through steps such as constructing content templates and material libraries, selecting appropriate automated tools, content creation and automated management, content publishing and management, and continuous optimization and iteration. This method not only improves the efficiency and quality of content production, but also reduces labor costs and time costs, providing strong support for content creators and marketers.

[0003] 1. Although the existing automated management methods for content creation processes have improved the efficiency of content creation to a certain extent, there are still the following problems:

[0004] 2. Existing methods often adopt fixed process templates and are difficult to adapt to the personalized needs of different projects or different teams;

[0005] 3. While pursuing efficiency, the quality of content is often ignored, resulting in the generated content lacking creativity and attractiveness;

[0006] 4. Existing methods often focus on the automation of a single node while ignoring the collaboration and communication between multiple nodes, resulting in information silos and duplicate work in the process;

[0007] 5. For complex tasks involving multiple links and multiple participants, existing methods are often difficult to effectively manage and coordinate;

[0008] In view of the above problems, an automated management method for content creation processes that supports multi-node collaboration is provided. Summary of the Invention

[0009] The object of the present invention is to provide an automated management method for content creation processes that supports multi-node collaboration, so as to solve the problems raised in the above-mentioned background art. To achieve the above object, the present invention provides the following technical solution: An automated management method for content creation processes that supports multi-node collaboration, including the following processes:

[0010] Step 1, process definition and visual arrangement. According to the requirements and goals of the project, define the content creation process and arrange it through a visual interface;

[0011] Step 2, intelligent task assignment and priority ranking. According to the nature, complexity of the tasks, as well as the skills and experience of team members, use intelligent algorithms for task assignment, and conduct priority ranking according to the urgency and importance of the tasks;

[0012] Step 3, multi-node collaboration and communication. Establish a collaboration mechanism between multi-nodes, provide communication tools, and promote communication and collaboration among team members;

[0013] Step 4, real-time monitoring and feedback. Through real-time monitoring technology, continuously track the progress and status of tasks;

[0014] Step 5, content quality review and optimization. During the content creation process, conduct quality review and optimization on the generated content;

[0015] Step 6, process optimization and continuous improvement. According to the implementation situation and feedback of the project, optimize and improve the process.

[0016] Preferably, the quality review and optimization in Step 5 include grammar checking, spelling correction, content creativity, and attractiveness.

[0017] Preferably, the optimization and improvement of the process in Step 6 include adjusting the process structure, optimizing task assignment, and priority ranking.

[0018] Preferably, K-Means clustering algorithm is used for process definition and visual arrangement.

[0019] Preferably, the K-Means clustering algorithm includes: obtaining the frequencies of different types of plugins associated with each task, and forming data samples with the frequencies of different types of plugins associated with all tasks;

[0020] Using the K-means algorithm, divide the data samples into k task clusters;

[0021] Match the k task clusters with k executors so that the task clusters and executors correspond one by one

[0022] The plug-ins for the said task are divided into types of m preset dimensions, and the types of the preset dimensions include loading type, storing type, network type, transformation type, calculation type, command type, and quality control type.

[0023] Preferably, using the K-means algorithm to divide the data samples into k task clusters includes: initializing k different cluster centers, and for the current k cluster centers, dividing the data samples into k clusters according to the principle of the shortest distance;

[0024] Recalculating the cluster centers for the k divided clusters to obtain the calculated k cluster centers: determining whether the calculated k cluster centers are the same as the current k cluster centers;

[0025] If they are not the same, then taking the calculated k cluster centers as the current k cluster centers again, repeating the above steps until it is determined that the calculated k cluster centers are the same as the current k cluster centers, and taking the k divided clusters as the k task clusters;

[0026] The initialization of k different cluster centers includes: randomly setting k different cluster centers: c 1 ←d i , 1 ≤ 1 ≤ k, 1 ≤ i ≤ n;

[0027] where i is a random positive integer in [1, n], n is the quantity of elements in the set: n = card(D); D is a data sample containing n tasks and each task has m preset dimensions: D = {d i |d i = {v i1 , v i1 , …, v im}, 1 ≤ i ≤ n}.

[0028] Preferably, the division of the data samples into k clusters according to the principle of the shortest distance includes: according to the principle of the shortest distance, dividing the data sample D into the k clusters c j :

[0029]

[0030] where the distance dist(d i , c j ) uses the Euclidean distance algorithm:

[0031] Preferably, the recalculation of the cluster centers for the k divided clusters includes: respectively calculating the mean values of the coordinates of the elements in the k clusters and taking them as the calculated k cluster centers c`j:

[0032]

[0033] Preferably, the frequency of occurrence of a certain type of plug-in associated with a certain task is: the ratio of the number of times the plug-in of this type needs to be used to the number of times all types of plug-ins need to be used in the data processing process, as feedback by the data processing tool for this task.

[0034] Preferably, the matching of the k task clusters and the k executors includes: randomly selecting a task cluster from the un-matched task clusters, and finding the task with the shortest distance to the cluster center according to the cluster center of this task cluster;

[0035] Executing the task with the shortest distance in the un-matched executors respectively to obtain the executor with the shortest execution time, and matching the executor with the shortest execution time with the task cluster where this task is located; repeating the above steps until all task clusters are matched.

[0036] Compared with the prior art, the beneficial effects of the present invention are:

[0037] In this case, according to the requirements and goals of the project, the content creation process is defined and arranged through a visual interface. According to the nature, complexity of the tasks, as well as the skills and experience of the team members, intelligent algorithms are used for task allocation, and priority sorting is carried out according to the urgency and importance of the tasks. A collaboration mechanism between multiple nodes is established, communication tools are provided to promote communication and collaboration among team members. Through real-time monitoring technology, the progress and status of tasks are continuously tracked. During the content creation process, quality review and optimization of the generated content are carried out. According to the implementation situation and feedback of the project, the process is optimized and improved, solving the problems that the prior art often uses a fixed process template, which is difficult to meet the personalized needs of different projects or different teams, often ignores the quality of the content while pursuing efficiency, resulting in the generated content lacking creativity and attractiveness, the existing methods often focus on the automation of a single node while ignoring the collaboration and communication between multiple nodes, resulting in information islands and duplicate work in the process, and for complex tasks involving multiple links and multiple participants, the existing methods are often difficult to effectively manage and coordinate. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a flowchart of a method for automated management of a content creation process supporting multi-node collaboration according to the present invention;

[0039] Figure 2 It is a block diagram of quality review and optimization of a method for automated management of a content creation process supporting multi-node collaboration according to the present invention;

[0040] Figure 3 It is a block diagram of process optimization and improvement of a method for automated management of a content creation process supporting multi-node collaboration according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0041] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0042] Please refer to Figures 1 to 3 , the present invention provides a technical solution: an automated management method for content creation processes supporting multi-node collaboration, including the following processes:

[0043] Step 1, process definition and visual arrangement. According to the requirements and goals of the project, define the content creation process and arrange it through a visual interface. In the automated management method for content creation processes supporting multi-node collaboration, process definition and visual arrangement play a crucial role. Through process definition, the tasks and responsibilities of each node can be clearly divided, ensuring that each node understands its own work content and expected results. The process definition details the specific operations and requirements of each step, which helps team members work according to unified standards, reducing operation errors and communication costs. Through reasonable process design, the collaboration method between each node can be optimized, reducing unnecessary waiting and repetitive work, thereby improving the overall collaboration efficiency. Visual arrangement intuitively displays the content creation process in a graphical manner, enabling team members to clearly understand the structure and steps of the entire process, reducing the difficulty of understanding. Through the visual interface, managers can monitor the execution status of the process in real time, including the task progress and resource consumption of each node, so as to discover and solve problems in a timely manner. Visual arrangement supports dynamic adjustment and optimization of the process. When business requirements change, it can be quickly modified on the visual interface to adapt to the new business scenario. Visual arrangement enables team members to more intuitively understand each other's work content and progress, which helps to strengthen team collaboration and communication, and jointly promote the smooth progress of the project. In the automated management method for content creation processes, process definition and visual arrangement are usually combined. After defining the tasks and operation steps of each node through process definition, then use visual arrangement to present these tasks and steps in a graphical manner;

[0044] Step 2: Intelligent task allocation and priority ranking. Based on the nature, complexity of tasks, as well as the skills and experience of team members, intelligent algorithms are used for task allocation, and priority ranking is carried out according to the urgency and importance of tasks. The intelligent task allocation system can match based on task characteristics (such as urgency, importance, required skills, etc.) and employees' work capabilities, historical performance, and current workload to ensure that tasks are assigned to the most suitable candidates. This data- and algorithm-based task allocation method is more objective and accurate compared to traditional manual allocation, and can reduce situations of unfair allocation or ineffective task execution caused by human factors. Through intelligent task allocation, enterprises can make more reasonable use of human resources, avoid situations where some employees are overloaded while others are idle. This helps balance the workload, improve work efficiency, and also contributes to employees' career development and job satisfaction. The intelligent task allocation system usually has real-time monitoring and feedback functions. Team members can understand the task progress and the work situation of other members in real time, which helps enhance team collaboration and communication, promotes information sharing and knowledge transfer, and thus improves the creative ability and efficiency of the entire team. In the content creation process that supports multi-node collaboration, intelligent task allocation and priority ranking are usually applied in combination. The intelligent task allocation system can dynamically adjust and optimize according to the priority of tasks and the actual situation of employees to ensure that key tasks are given priority. At the same time, priority ranking can also provide an important reference basis for intelligent task allocation, making task allocation more reasonable and efficient;

[0045] Step 3: Multi-node collaboration and communication. Establish a collaboration mechanism between multi-nodes, provide communication tools, and promote communication and collaboration among team members. Multi-node collaboration can decompose and allocate each link of content creation to different teams or individuals, and each node focuses on its own professional field or skills, thus enabling parallel processing. This division of labor and cooperation method can significantly shorten the overall cycle of content creation and improve creation efficiency. Each node is usually composed of professional personnel with relevant skills and experience, and they can provide high-quality content output. Multi-node collaboration means that the content between different nodes can complement and verify each other, thus reducing errors and omissions and improving the accuracy and integrity of the content. Multi-node collaboration encourages team members from different backgrounds and fields to communicate and cooperate. This cross-field cooperation helps stimulate new ideas and concepts. Through sharing and discussion, team members can inspire each other and jointly explore new creation directions and styles;

[0046] Step 4: Real-time monitoring and feedback. Through real-time monitoring technology, the progress and status of tasks can be continuously tracked. Real-time monitoring can continuously track each link of the content creation process to ensure that each node operates according to the predetermined plan and requirements. Through monitoring, bottlenecks and problems in the process can be discovered and solved in a timely manner, thereby avoiding process interruptions or delays and ensuring the smooth progress of the entire creation process. Real-time monitoring can understand the progress and completion of tasks at each node in real time, thereby helping managers to reasonably allocate resources and adjust plans. When a node has a backlog of tasks or a lag in progress, the task allocation of other nodes can be adjusted in time to balance the overall workload and improve the efficiency of task execution. Through real-time monitoring, potential creation risks can be discovered in a timely manner, such as substandard content quality and deviation from the creation direction. Once these risks are discovered, measures can be taken immediately to intervene and correct them, thereby avoiding the expansion of risks and causing greater losses. Feedback is one of the important results of real-time monitoring. It can help creators understand the acceptance and response of their works among the audience. By collecting and analyzing the feedback from the audience, creators can understand the advantages and disadvantages of their works, so as to make targeted improvements and optimizations to improve the quality of creation. Feedback is not only an evaluation of the creator himself, but also a reflection of the effectiveness of team collaboration. Through feedback, team members can understand each other's work performance and contributions, so as to clarify their own responsibilities and positions. At the same time, feedback can also promote exchanges and communication between team members, enhance the cohesion and execution of teamwork, and provide guidance and reference for subsequent creations. By analyzing the audience's feedback and preferences, creators can more accurately grasp the audience's needs and expectations, and thus create works that better meet the audience's tastes and needs;

[0047] Step 5: Content quality review and optimization. During the content creation process, the generated content is reviewed and optimized. The primary task of content quality review is to ensure that the content complies with laws and regulations, platform rules and socialist core values. Through review, we can timely discover and filter out illegal, vulgar, false and other bad content, maintain the legality and health of platform content, and high-quality content can attract and retain users and improve user experience. Content quality review ensures that the information obtained by users is valuable and in-depth by screening and optimizing content, thereby improving user satisfaction and loyalty to the platform. Content quality review helps to timely discover and deal with content that may cause legal risks and moral disputes, and reduce the legal risks and public opinion pressure faced by the platform due to content problems. Content optimization is the process of improving and enhancing existing content. Through optimization, errors and omissions in the content can be corrected to improve the accuracy and completeness of the content. At the same time, we can also make targeted adjustments and improvements to the content according to user needs and feedback to make it more in line with user expectations and needs. The optimized content is usually more vivid, interesting, and easy to understand, which can attract more users' attention and reading. This helps to improve the dissemination effect and influence of the content, expand the popularity and influence of the platform, and search engines usually prefer to display high-quality and valuable content. Through content optimization, the ranking and exposure of the content in search engines can be improved, thereby attracting more potential users' attention and visits;

[0048] Step six: process optimization and continuous improvement: optimize and improve the process based on the project execution and feedback.

[0049] In this embodiment, the quality review and optimization in step five include grammar checking, spelling correction, content creativity and attractiveness.

[0050] In this embodiment, the optimization and improvement of the process in step six includes adjusting the process structure, optimizing task allocation and priority sorting.

[0051] In this embodiment, the process definition and visual arrangement adopt the K-Means clustering algorithm.

[0052] In this embodiment, the K-Means clustering algorithm includes: obtaining the frequency of occurrence of different types of plug-ins associated with each task, and forming the frequency of occurrence of different types of plug-ins associated with all tasks into a data sample;

[0053] Using the K-means algorithm, the data samples are divided into k task clusters;

[0054] Match k task clusters with k executors so that task clusters and executors correspond one to one

[0055] The plug-ins of the task are divided into types of m preset dimensions, and the types of preset dimensions include loading type, storing type, network type, transformation type, calculation type, command type, and quality control type.

[0056] In this embodiment, using the K-means algorithm, the data samples are divided into k task clusters, including: initializing k different cluster centers, and for the current k cluster centers, dividing the data samples into k clusters according to the principle of the shortest distance;

[0057] Recalculating the cluster centers for the k divided clusters to obtain the calculated k cluster centers: determining whether the calculated k cluster centers are the same as the current k cluster centers;

[0058] If they are not the same, then take the calculated k cluster centers as the current k cluster centers again, and repeat the above steps until it is determined that the calculated k cluster centers are the same as the current k cluster centers, and take the k divided clusters as the k task clusters;

[0059] Initializing k different cluster centers includes: randomly setting k different cluster centers: c 1 ←d i , 1 ≤ 1 ≤ k, 1 ≤ i ≤ n;

[0060] where i is a random positive integer in [1, n], n is the quantity of elements in the set: n = card(D); D is a data sample containing n tasks and each task has m preset dimensions: D = {d i |d i = {v i1 , v i1 , …, v im}, 1 ≤ i ≤ n}.

[0061] In this embodiment, dividing the data samples into k clusters according to the principle of the shortest distance includes: according to the principle of the shortest distance, dividing the data sample D into the k clusters c j :

[0062]

[0063] where the distance dist(d i , c j ) adopts the Euclidean distance algorithm:

[0064] In this embodiment, recalculating the cluster centers for the k divided clusters includes: respectively calculating the mean values of the coordinates of the elements in the k clusters and taking them as the calculated k cluster centers c`j:

[0065]

[0066] In this embodiment, the frequency of a certain type of plug-in associated with a certain task is: the ratio of the number of times the plug-in of this type needs to be used to the number of times all types of plug-ins need to be used in the data processing process, as feedback by the data processing tool for this task.

[0067] In this embodiment, matching k task clusters and k executors includes: randomly selecting a task cluster from the un-matched task clusters, and finding the task with the shortest distance to the cluster center according to the cluster center of this task cluster;

[0068] Executing the task with the shortest distance in the un-matched executors respectively to obtain the executor with the shortest execution time, and matching the executor with the shortest execution time with the task cluster where this task is located; repeating the above steps until all task clusters are matched.

[0069] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions in the specification are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A content creation process automation management method supporting multi-node collaboration, characterized in that: The process includes: Step 1: Process definition and visual arrangement: define the content creation process according to the project requirements and goals, and arrange it through a visual interface; Step 2: Intelligent task allocation and prioritization: Based on the nature and complexity of tasks and the skills and experience of team members, intelligent algorithms are used to allocate tasks and prioritize them according to their urgency and importance. Step 3: Multi-node collaboration and communication: Establish a collaboration mechanism between multiple nodes, provide communication tools, and promote communication and collaboration among team members; Step 4: Real-time monitoring and feedback: Use real-time monitoring technology to continuously track the progress and status of tasks; Step 5: Content quality review and optimization: During the content creation process, the quality of the generated content is reviewed and optimized; Step six: process optimization and continuous improvement: optimize and improve the process based on the project execution and feedback.

2. According to claim 1, a method for automating content creation process management supporting multi-node collaboration is characterized in that: The quality review and optimization in step five includes grammar checking, spelling correction, content creativity and attractiveness.

3. The method for automated management of content creation process supporting multi-node collaboration according to claim 1, characterized in that: The optimization and improvement of the process in step six includes adjusting the process structure, optimizing task allocation and priority sorting.

4. The method for automated management of content creation process supporting multi-node collaboration according to claim 1, characterized in that: The K-Means clustering algorithm is used for process definition and visual arrangement.

5. The method for automated management of content creation process supporting multi-node collaboration according to claim 4, characterized in that: The K-Means clustering algorithm includes: obtaining the frequency of occurrence of different types of plug-ins associated with each task, and forming a data sample with the frequency of occurrence of different types of plug-ins associated with all tasks; Using the K-means algorithm, the data sample is divided into k task clusters; Match k task clusters with k executors so that task clusters and executors correspond one to one The plug-ins of the task are divided into m preset dimension types, and the preset dimension types include loading type, storage type, network type, transformation type, calculation type, command type and quality control type.

6. The method for automated management of content creation process supporting multi-node collaboration according to claim 4, characterized in that: The method of using the K-means algorithm to divide the data sample into k task clusters includes: initializing k different cluster centers, and dividing the data sample into k clusters according to the shortest distance principle for the current k cluster centers; Recalculate the cluster centers of the k divided clusters to obtain the calculated k cluster centers: determine whether the calculated k cluster centers are the same as the current k cluster centers; If they are not the same, the calculated k cluster centers are used as the current k cluster centers again, and the above steps are repeated until it is determined that the calculated k cluster centers are the same as the current k cluster centers, and the divided k clusters are used as k task clusters; Initializing k different cluster centers includes: randomly setting k different cluster centers: c1←d i , 1≤1≤k, 1≤i≤n; Where i is a random positive integer in [1, n], n is the number of elements in the set: n = card (D); D is a data sample containing n tasks and each task has m preset dimensions: D = {d i |d i = {v i1 ,v i1 ,…,v im },1≤i≤n}.

7. The method for automated management of content creation process supporting multi-node collaboration according to claim 6, characterized in that: The method of dividing the data sample into k clusters according to the shortest distance principle includes: dividing the data sample D into k clusters c corresponding to the current k cluster centers according to the shortest distance principle. j : C j ={d i |dist(d i ,c j )=1m ≤i i ≤ n k dist(d i c i )}; Among them, the distance dist(d i ,c j )Using the Euclidean distance algorithm:

8. The method for automated management of content creation process supporting multi-node collaboration according to claim 7, characterized in that: The recalculation of the cluster centers of the k divided clusters includes: respectively calculating the mean of the coordinates of each element in the k clusters and using them as the calculated k cluster centers c`j:

9. The method for automated management of content creation process supporting multi-node collaboration according to claim 4, characterized in that: in, The frequency of a certain type of plug-in associated with a task is the ratio of the number of plug-ins of this type required to be used in the data processing process to the number of plug-ins of all types required, as fed back by the data processing tool for the task.

10. The method for automated management of content creation process supporting multi-node collaboration according to claim 4, characterized in that: The matching of the k task clusters and the k executors includes: randomly selecting a task cluster from unmatched task clusters, and finding a task with the shortest distance to the cluster center according to the cluster center of the task cluster; The task with the shortest distance is executed separately in the unmatched executors to obtain the executor with the shortest execution time, and the executor with the shortest execution time is matched with the task cluster where the task is located; the above steps are repeated until all task clusters are matched.

Images