Academic virtual community user social driving method, device and equipment and storage medium

Abstract

The present application relates to the technical field of data processing, and discloses a kind of academic virtual community user social driving method, device, equipment and storage medium, by predicting the discipline version block heat change trend of target social driving period, then according to hardware resource deployment information, consider the discipline version block heat change trend of target operation area in target social driving period and the hardware resource allocation information of last social driving period, with hardware configuration parameter and position deployment information to construct constraint condition set, with minimum server switching influence as optimization target, optimize solving hardware resource scheduling sub-strategy, simultaneously, consider the availability of candidate subject social driving activity and remaining hardware resources, as much as possible to the candidate subject social driving activity is added to the user social driving of target academic virtual community, avoid the influence caused by the regional activity difference of discipline version block to community stable operation, maintain the continuous operation of community high activity, high heat and high stability.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a social-driven method, apparatus, device, and storage medium for users of an academic virtual community. Background Technology

[0002] Academic virtual communities are online platforms built on Internet technology, aiming to provide a space for academic groups such as scholars, researchers, and students to communicate and collaborate across time and space. Their core features include: (1) focusing on academic fields (such as specific disciplines or research directions), with content revolving around knowledge production, dissemination, and application; (2) supporting users to interact through various forms such as posting, commenting, private messaging, and meetings, promoting the collision of ideas and cooperation; (3) providing storage and sharing functions for academic resources such as documents, data, and tools; and (4) building a user system through mechanisms such as points, levels, and certification to enhance a sense of belonging and activity.

[0003] User-driven social interaction refers to designing social mechanisms, functions, or content to stimulate users' active participation in community interactions, forming sustained social behaviors, and thereby enhancing community activity, cohesion, and academic value. Therefore, to achieve the ultimate goal of academic virtual communities in promoting knowledge dissemination, academic collaboration, and innovation through social connections, it is necessary to maximize the activity of academic virtual communities. However, the operation of existing academic virtual communities and user-driven social interaction methods have the following limitations:

[0004] Firstly, there are various approaches to driving user social interaction in academic virtual communities (such as academic hot events like the Nobel Prize announcement, proactive community operations, and external traffic generation for content sections). Different methods of driving user social interaction will generate varying degrees of high traffic to academic virtual communities in different subject sections and at different durations, putting different pressures on the hardware resources of academic virtual communities (mainly the various hardware parameters of servers for handling concurrent data). In order to ensure the stable operation and continuous activity of the community, when driving or responding to user social interaction in academic virtual communities, it is necessary to consider the limitations imposed by hardware resources to avoid problems such as community crashes and unexpected delays.

[0005] Secondly, when academic virtual communities are driven by user social interaction across different disciplines, regional differences in community activity often emerge. For example, the most active sectors in the Yangtze River Delta region are biomedical engineering and blockchain technology, in the Beijing-Tianjin-Hebei region are artificial intelligence and aerospace technology, in the Guangdong-Hong Kong-Macao Greater Bay Area are semiconductors and cross-border data flow, and in the Chengdu-Chongqing region are electronic information and automotive engineering. When driving user social interaction in academic virtual communities, it is also necessary to pay attention to the fact that regional differences in activity across different disciplines may cause server overload in some areas.

[0006] Thirdly, due to the regional differences in community activity within academic virtual communities, when allocating servers and subject sections, it is also necessary to consider the communication distance between the server and the corresponding active area of ​​the subject section. If a subject section is allocated a server with sufficient hardware resources and processing power, but the server's deployment location is far away from the corresponding active area of ​​the community, this situation will also cause high latency in the community interaction process and affect the social experience.

[0007] Fourth, given the large number of user-driven social activities, in order to maximize the overall activity level of the academic virtual community, it is necessary to run as many user-driven social activities as possible, within the limits of server hardware resources. How to arrange and run user-driven social activities under the aforementioned constraints has become a challenge.

[0008] Therefore, how to rationally and scientifically implement user-driven social activities in academic virtual communities, and intelligently allocate scheduling strategies between different subject sections and servers within the limits of server hardware resources, to avoid the impact of regional differences in activity levels across different subject sections on the stable operation of the community, and potentially run more user-driven social activities to maintain the community's high activity, high popularity, and high stability, is a technical problem that urgently needs to be solved. Summary of the Invention

[0009] This invention provides a social-driven method, apparatus, device, and storage medium for users of an academic virtual community, aiming to solve at least one of the above-mentioned technical problems.

[0010] To achieve the above objectives, this invention provides a social-driven method for users of an academic virtual community, comprising the following steps:

[0011] Obtain the community attributes of the target academic virtual community; wherein, the community attributes include subject section division information and hardware resource deployment information;

[0012] Based on the subject section division information, collect subject association information of each subject section in the target operating area and construct a set of popularity driving factors. Using the set of popularity driving factors, predict the trend of subject section popularity change in the target operating area during the target social driving period.

[0013] Based on the hardware resource information and deployment location information of several distributed community servers in the hardware resource deployment information, and considering the subject section popularity value and popularity influence area in each social driving cycle of the target operating area during the target social driving period, as well as the hardware resource allocation information of the previous social driving period, a user social driving strategy for the target social driving period is generated.

[0014] Extract the hardware resource scheduling sub-strategy and the social driving sub-strategy from the user social driving strategy, and execute the server resource allocation and user social driving of the subject section respectively.

[0015] Optionally, the steps for obtaining the community attributes of the target academic virtual community include:

[0016] Query the backend management system of the target academic virtual community, parse the subject section structure information stored in the backend management system, and extract several subject section categories of the target academic virtual community;

[0017] Query the deployment information of the first server of the target academic virtual community in the public cloud service platform and the deployment information of the second server in the self-built IDC data center. Based on the deployment information of the first server and the second server, determine the deployment server set of the target academic virtual community.

[0018] By using several subject-specific categories as subject-specific category information and the deployment server set as hardware resource deployment information, the community attributes of the target academic virtual community are generated.

[0019] Optionally, based on the subject section division information, the step of collecting subject association information for each subject section in the target operating area and constructing a set of popularity driving factors specifically includes:

[0020] Based on several subject category division information, a set of subject keywords is generated for each subject category using data augmentation.

[0021] Using the aforementioned subject keyword set, several subject-related information entries are matched in the subject-related information database using keyword matching. Popularity driving factors are extracted from these entries, and a popularity driving factor set is constructed.

[0022] The aforementioned subject-related information is configured to be at least one of the following: academic hot events, community operation activities, or external channel traffic events published by several subject-related hot event publishing pages or publishing platforms recorded in the subject-related information database.

[0023] The heat driving factors are configured as the heat influence characteristics of academic hot events, community operation activities, or external channel traffic events.

[0024] Optionally, the step of predicting the trend of subject-specific popularity in the target operating area during the target social media-driven period using the set of popularity-driving factors specifically includes:

[0025] Obtain information on the changes in the popularity of subject sections within a historical period, extract the subject section popularity value and the area of ​​influence of each subject section category from the information on the changes in the popularity of subject sections, and construct a popularity training sample by combining the information on the changes in the popularity value of subject sections, the information on the changes in the area of ​​influence of the popularity, and the features of the popularity influence.

[0026] Call the pre-built initial neural network model, train the initial neural network model using the heat training samples, and obtain the heat prediction model of the completed pilgrimage when the training reaches the target number of times or converges.

[0027] By utilizing several heat influence features from the heat driving factor set, a heat influence feature set is constructed and used as a heat prediction sample. The heat prediction sample is then input into the heat prediction model to predict the heat change trend of subject sections in the target operating area during the target social driving period.

[0028] Optionally, based on the hardware resource information and deployment location information of several distributed community servers in the hardware resource deployment information, and considering the subject section popularity value and influence area in each social driving cycle of the target operating region during the target social driving period, as well as the hardware resource allocation information of the previous social driving period, the user social driving strategy steps for the target social driving period are generated, specifically including:

[0029] Extract the hardware resource information and deployment location information of several distributed community servers from the hardware resource deployment information, and consider the subject section popularity value and popularity influence area in each social driving cycle and the hardware resource allocation information of the previous social driving period in the subject section popularity change trend of the target operation area during the target social driving period.

[0030] The first constraint is that the sum of the hardware resource requirements corresponding to the popularity of the subject sections assigned to each distributed community server in each social driving cycle of the target social driving period is higher than the hardware resource configuration parameters corresponding to the hardware resource information of the distributed community server. The second constraint is that the popularity influence area of ​​the subject sections assigned to each distributed community server in each social driving cycle of the target social driving period covers the deployment location information of the distributed community server. The optimization objective is to minimize the sum of the popularity of the subject sections in the two social driving cycles when all subject sections are assigned to different distributed community servers in two adjacent social driving cycles. The optimization solution is to solve for the hardware resource allocation information of the subject sections assigned to several distributed community servers in each social driving cycle of the target social driving period.

[0031] Based on the hardware resource allocation information of several subject sections allocated to several distributed community servers in each social driving cycle during the target social driving period, a user social driving strategy is generated.

[0032] Optionally, based on the hardware resource allocation information of several subject-specific modules allocated to several distributed community servers within each social-driving cycle of the target social-driving period, the user social-driving strategy steps are generated, specifically including:

[0033] Based on the hardware resource allocation information of several subject sections allocated to several distributed community servers in each social driving cycle during the target social driving period, several hardware resource scheduling sub-strategies for distributed community servers are generated.

[0034] Calculate the difference between the hardware resource configuration parameters of each distributed community server and the sum of the hardware resource requirement parameters for each social driving cycle under the target social driving time period under the hardware resource allocation information, and generate a list of remaining hardware resource parameters for each distributed community server in each social driving cycle of the target social driving time period.

[0035] Obtain a candidate set of subject-based social activities, extract several candidate subject-based social activities imported in chronological order from the candidate set, predict the subject section popularity trend of each candidate subject-based social activity based on the popularity impact characteristics of each candidate subject-based social activity, and determine the subject section popularity value and popularity impact area for each social driving cycle.

[0036] Considering the subject section popularity value and popularity influence area of ​​each social driving cycle, as well as the deployment location information and hardware resource remaining parameter list of each distributed community server, under the condition that the hardware resource requirements of the candidate subject social driving activities and the requirement that the deployment location of the distributed community server falls within the popularity influence area are met, the action of adding the candidate subject social driving activities to the target social driving period in the order of importing in chronological order is repeatedly executed until the requirements can no longer be met, so as to obtain the allocation information of each candidate subject social driving activity and the distributed community server in the target social driving period;

[0037] Based on the selected candidate subject social-driven activities and the allocation information of each candidate subject social-driven activity with the distributed community server in the target social-driven period, several social-driven sub-strategies for the distributed community server are generated.

[0038] Optionally, the hardware resource scheduling sub-strategy and the social driving sub-strategy are extracted from the user social driving strategy, and the server resource allocation and user social driving steps of the subject section are executed respectively, specifically including:

[0039] Extract the hardware resource scheduling sub-strategy and the social driving sub-strategy from the user social driving strategy. Use the hardware resource scheduling sub-strategy to control several distributed community servers to perform server resource allocation for each subject section in each social driving cycle of the target social driving period.

[0040] Using the aforementioned social-driven sub-strategy, the virtual community management terminal is driven to execute user social-driven activities for candidate subjects in the distributed community servers and corresponding subject sections, and to control the allocation of server resources for the subject sections corresponding to the newly added candidate subject social-driven activities in each social-driven cycle of the target social-driven period on several distributed community servers.

[0041] Furthermore, to achieve the above objectives, the present invention also provides a social driving device for users of an academic virtual community, comprising:

[0042] The acquisition module is used to acquire the community attributes of the target academic virtual community; wherein, the community attributes include subject section division information and hardware resource deployment information;

[0043] The prediction module is used to collect subject association information of each subject section in the target operating area based on the subject section division information and construct a set of popularity driving factors. Using the set of popularity driving factors, the module predicts the trend of subject section popularity change in the target operating area during the target social driving period.

[0044] The generation module is used to generate a user social driving strategy for the target social driving period based on the hardware resource information and deployment location information of several distributed community servers in the hardware resource deployment information, taking into account the subject section popularity value and popularity influence area in each social driving cycle in the target operating area during the target social driving period and the hardware resource allocation information of the previous social driving period.

[0045] The execution module is used to extract the hardware resource scheduling sub-policy and the social driving sub-policy from the user social driving strategy, and execute the server resource allocation and user social driving of the subject section respectively.

[0046] Furthermore, to achieve the above objectives, the present invention also provides an academic virtual community user social driving device, which includes: a memory, a processor, and an academic virtual community user social driving driver stored in the memory and executable on the processor. When the academic virtual community user social driving driver is executed by the processor, it implements the steps of the academic virtual community user social driving method as described above.

[0047] In addition, to achieve the above objectives, the present invention also provides a storage medium storing an academic virtual community user social driver program, wherein the academic virtual community user social driver program, when executed by a processor, implements the steps of the above-described academic virtual community user social driver method.

[0048] The beneficial effects of this invention are as follows: It proposes a method, apparatus, device, and storage medium for user social driving in academic virtual communities. By predicting the trend of subject section popularity during the target social driving period, and considering the trend of subject section popularity in the target operating area during the target social driving period and the hardware resource allocation information of the previous social driving period based on hardware resource deployment information, a set of constraints is constructed using hardware configuration parameters and location deployment information. With the goal of minimizing the impact of server switching, the hardware resource scheduling sub-strategy is optimized. At the same time, considering the availability of candidate subject social driving activities and remaining hardware resources, as many candidate subject social driving activities as possible are added to the user social driving of the target academic virtual community, avoiding the impact of regional activity differences of subject sections on the stable operation of the community, and maintaining the continuous operation of the community with high activity, high popularity, and high stability. Attached Figure Description

[0049] Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention;

[0050] Figure 2 This is a flowchart illustrating the social-driven method for users in an academic virtual community, as described in this embodiment of the invention.

[0051] Figure 3 This is a structural block diagram of the social driving device for academic virtual community users in an embodiment of the present invention. Detailed Implementation

[0052] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0053] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0054] like Figure 1 As shown, Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention.

[0055] like Figure 1As shown, the device may include: a processor 1001, such as a CPU; a communication bus 1002; a user interface 1003; a network interface 1004; and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0056] Those skilled in the art will understand that Figure 1 The structure of the device shown does not constitute a limitation on the device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0057] like Figure 1 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a social driver for academic virtual community users.

[0058] exist Figure 1 In the terminal shown, network interface 1004 is mainly used to connect to the backend server and communicate with it; user interface 1003 is mainly used to connect to the client (user end) and communicate with it; while processor 1001 can be used to call the academic virtual community user social driver stored in memory 1005 and perform the following operations:

[0059] Obtain the community attributes of the target academic virtual community; wherein, the community attributes include subject section division information and hardware resource deployment information;

[0060] Based on the subject section division information, collect subject association information of each subject section in the target operating area and construct a set of popularity driving factors. Using the set of popularity driving factors, predict the trend of subject section popularity change in the target operating area during the target social driving period.

[0061] Based on the hardware resource information and deployment location information of several distributed community servers in the hardware resource deployment information, and considering the subject section popularity value and popularity influence area in each social driving cycle of the target operating area during the target social driving period, as well as the hardware resource allocation information of the previous social driving period, a user social driving strategy for the target social driving period is generated.

[0062] Extract the hardware resource scheduling sub-strategy and the social driving sub-strategy from the user social driving strategy, and execute the server resource allocation and user social driving of the subject section respectively.

[0063] The specific embodiments of the present invention applied to the device are basically the same as the embodiments of the application of the social-driven method for users of academic virtual communities described below, and will not be repeated here.

[0064] This invention provides a social-driven method for users in an academic virtual community, referring to... Figure 2 , Figure 2 This is a flowchart illustrating an embodiment of the social-driven method for users in an academic virtual community according to the present invention.

[0065] In this embodiment, a social-driven method for users of an academic virtual community includes the following steps:

[0066] S100: Obtain the community attributes of the target academic virtual community; wherein, the community attributes include subject section division information and hardware resource deployment information;

[0067] S200: Based on the subject section division information, collect subject association information of each subject section in the target operating area and construct a set of popularity driving factors. Using the set of popularity driving factors, predict the trend of subject section popularity change in the target operating area during the target social driving period.

[0068] S300: Based on the hardware resource information and deployment location information of several distributed community servers in the hardware resource deployment information, considering the subject section popularity value and popularity influence area in each social driving cycle of the target operating area in the subject section popularity change trend of the target social driving period and the hardware resource allocation information of the previous social driving period, generate the user social driving strategy for the target social driving period.

[0069] S400: Extract the hardware resource scheduling sub-strategy and social driving sub-strategy from the user social driving strategy, and execute the server resource allocation and user social driving of the subject section respectively.

[0070] It should be noted that the operation of existing academic virtual communities and the user-driven social interaction methods have the following limitations: First, there are various routes for user-driven social interaction in academic virtual communities (such as academic hot events like the announcement of the Nobel Prize, community-initiated operational activities, and external traffic generation for content sections, etc.). Different user-driven social interaction methods will generate varying degrees of high traffic access to academic virtual communities in different subject sections and at different durations, putting different pressures on the hardware resources of academic virtual communities (mainly the various hardware parameters of servers for processing concurrent data). In order to ensure the stable operation and continuous activity of the community, when implementing or responding to user-driven social interaction in academic virtual communities, it is necessary to consider the limitations brought about by hardware resources to avoid problems such as community crashes and unexpected delays. Secondly, academic virtual communities often exhibit regional differences in community activity when driven by user interaction across different subject areas. For example, in the Yangtze River Delta region, highly active areas include biomedical engineering and blockchain technology; in the Beijing-Tianjin-Hebei region, artificial intelligence and aerospace technology; in the Guangdong-Hong Kong-Macau Greater Bay Area, semiconductors and cross-border data flow; and in the Chengdu-Chongqing region, electronic information and automotive engineering. When driving user interaction in academic virtual communities, it is necessary to consider that these regional differences in activity across different subject areas may cause server overload in some regions. Thirdly, due to the regional differences in community activity within academic virtual communities, the communication distance between servers and the corresponding active areas of subject areas must be considered when allocating servers and subject areas. If a subject area is allocated a server with sufficient hardware resources and processing power, but the server's deployment location is far removed from the corresponding active area of ​​the community, this will also cause high latency in the community interaction process, affecting the social experience. Fourth, given the large number of user-driven social activities, in order to maximize the overall activity level of the academic virtual community, it is necessary to run as many user-driven social activities as possible, within the limits of server hardware resources. How to arrange and run user-driven social activities under the aforementioned constraints has become a challenge.

[0071] To address the aforementioned issues, this embodiment predicts the trend of subject-specific section popularity during the target social-driven period. Then, based on hardware resource deployment information, it considers the trend of subject-specific section popularity in the target operating region during the target social-driven period and the hardware resource allocation information from the previous social-driven period. A constraint set is constructed using hardware configuration parameters and location deployment information. With the goal of minimizing server switching impact, the hardware resource scheduling sub-strategy is optimized. Simultaneously, considering the availability of candidate subject-specific social-driven activities and remaining hardware resources, as many candidate subject-specific social-driven activities as possible are incorporated into the user social drive of the target academic virtual community. This avoids the impact of regional differences in subject-specific section activity on the stable operation of the community, maintaining the community's high activity, high popularity, and high stability.

[0072] In a preferred embodiment, the step of obtaining the community attributes of the target academic virtual community specifically includes:

[0073] S110: Query the backend management system of the target academic virtual community, parse the subject section structure information stored in the backend management system, and extract several subject section categories of the target academic virtual community.

[0074] S120: Query the deployment information of the first server of the target academic virtual community in the public cloud service platform and the deployment information of the second server in the self-built IDC data center, and determine the deployment server set of the target academic virtual community based on the deployment information of the first server and the deployment information of the second server;

[0075] S130: Use several subject category categories as subject category division information and the deployment server set as hardware resource deployment information to generate the community attributes of the target academic virtual community.

[0076] In this embodiment, by querying the backend management system of the target academic virtual community, several subject-specific categories of the target academic virtual community are parsed out. Then, by querying the deployment information of the first server in the public cloud service platform and the deployment information of the second server in the self-built IDC data center of the target academic virtual community, the deployment server set of the target academic virtual community is determined. In this way, the community attributes of the target academic virtual community are constructed, and the hardware and software architecture of the target academic virtual community are analyzed and summarized, providing data support for the subsequent scheduling and connection between subject-specific categories and servers.

[0077] In a preferred embodiment, the step of collecting subject-related information for each subject section in the target operating area and constructing a set of popularity driving factors based on the subject section division information specifically includes:

[0078] S210: Based on several subject category division information, generate a subject keyword set for each subject category by data augmentation;

[0079] S220: Using the aforementioned subject keyword set, several subject-related information entries are matched in the subject-related information database using keyword matching, and the popularity driving factors in the subject-related information entries are extracted to construct a popularity driving factor set.

[0080] The aforementioned subject-related information is configured to be at least one of the following: academic hot events, community operation activities, or external channel traffic events published by several subject-related hot event publishing pages or publishing platforms recorded in the subject-related information database.

[0081] The heat driving factors are configured as the heat influence characteristics of academic hot events, community operation activities, or external channel traffic events.

[0082] Based on this, using the aforementioned set of popularity-driving factors, the steps for predicting the popularity trend of subject-specific sections in the target operating area during the target social media-driven period specifically include:

[0083] S230: Obtain information on the changes in the popularity of subject sections within a historical period, extract the subject section popularity value and the popularity influence area for each subject section category from the information on the changes in the popularity of subject sections, and construct the information on the changes in the popularity value of subject sections, the information on the changes in the popularity influence area, and the popularity influence features as popularity training samples;

[0084] S240: Call the pre-built initial neural network model, train the initial neural network model using the heat training samples, and obtain the heat prediction model of the completed pilgrimage when the training reaches the target number of times or converges.

[0085] S250: Using several heat influence features from the heat driving factor set, construct a heat influence feature set as a heat prediction sample, input the heat prediction sample into the heat prediction model, and predict the heat change trend of subject sections in the target operating area during the target social driving period.

[0086] In this embodiment, the acquired subject section division information is used to generate a subject keyword set through data expansion. Then, subject-related information is extracted from academic hot events, community operation activities, and external channel traffic events in the subject-related information database, and a set of popularity driving factors is constructed based on this. A pre-trained popularity prediction model is then used to predict the popularity trend of subject sections. This popularity trend can reflect the changes in the popularity value and the area of ​​influence of each subject section. When considering the scheduling and connection of subject sections with servers, the relevant information on the popularity trend of subject sections can play a significant guiding role, enabling the target academic virtual community to maintain high activity and high popularity for a longer period of time, provided that the hardware is supported.

[0087] In a preferred embodiment, based on the hardware resource information and deployment location information of several distributed community servers in the hardware resource deployment information, considering the subject section popularity value and influence area of ​​each social driving cycle in the target operating region during the target social driving period, and the hardware resource allocation information of the previous social driving period, the steps to generate the user social driving strategy for the target social driving period specifically include:

[0088] S310: Extract the hardware resource information and deployment location information of several distributed community servers from the hardware resource deployment information, and consider the subject section popularity value and popularity influence area of ​​each social driving cycle and the hardware resource allocation information of the previous social driving period in the subject section popularity change trend of the target operation area during the target social driving period.

[0089] S320: The first constraint is that the sum of the hardware resource requirement parameters corresponding to the popularity of the subject sections assigned to each distributed community server in each social driving cycle of the target social driving period is higher than the hardware resource configuration parameters corresponding to the hardware resource information of the distributed community server. The second constraint is that the popularity influence area corresponding to the subject sections assigned to each distributed community server in each social driving cycle of the target social driving period covers the deployment location information of the distributed community server. The optimization objective is to minimize the sum of the popularity of the subject sections in the two social driving cycles when all subject sections are assigned to different distributed community servers in two adjacent social driving cycles. The optimization solution is to solve the hardware resource allocation information of the subject sections assigned to the distributed community servers in each social driving cycle of the target social driving period.

[0090] S330: Generate user social driving strategies based on the hardware resource allocation information of several subject sections allocated to several distributed community servers in each social driving cycle of the target social driving period.

[0091] Furthermore, based on the hardware resource allocation information of several subject-specific modules allocated to several distributed community servers within each social-driving cycle of the target social-driving period, the user social-driving strategy steps are generated, specifically including:

[0092] S331: Based on the hardware resource allocation information of several subject sections allocated to several distributed community servers in each social driving cycle during the target social driving period, generate several hardware resource scheduling sub-policies for distributed community servers.

[0093] S332: Calculate the difference between the hardware resource configuration parameters of each distributed community server and the sum of the hardware resource requirement parameters for each social driving cycle under the target social driving time period under the hardware resource allocation information, and generate a list of remaining hardware resource parameters for each distributed community server in each social driving cycle of the target social driving time period.

[0094] S333: Obtain a candidate set of subject-based social driving activities, extract several candidate subject-based social driving activities imported in chronological order from the candidate set of subject-based social driving activities, predict the subject section popularity trend of each candidate subject-based social driving activity based on the popularity influence characteristics of each candidate subject-based social driving activity, and determine the subject section popularity value and popularity influence area for each social driving cycle.

[0095] S334: Considering the subject section popularity value and popularity influence area of ​​each social driving cycle, the deployment location information of each distributed community server, and the list of remaining hardware resource parameters, under the condition that the hardware resource requirements of the candidate subject social driving activities and the requirement that the deployment location of the distributed community server falls into the popularity influence area are met, repeatedly execute the action of adding the candidate subject social driving activities to the target social driving period in the order of importing in chronological order until the requirements can no longer be met, and obtain the allocation information of each candidate subject social driving activity and the distributed community server in the target social driving period;

[0096] S335: Based on the selected candidate subject social-driven activities and the allocation information of each candidate subject social-driven activity with the distributed community server in the target social-driven period, generate several distributed community server social-driven sub-strategies.

[0097] In this embodiment, by acquiring the subject-specific section division information and hardware resource deployment information of the target academic virtual community, collecting the subject-related information of each subject section in the target operating area and constructing a set of popularity driving factors, the popularity trend of subject sections during the target social driving period is predicted. Then, based on the hardware resource information and deployment location information of several distributed community servers in the hardware resource deployment information, considering the popularity value and popularity influence area of ​​each social driving cycle in the popularity trend of subject sections in the target operating area during the target social driving period, and the hardware resource allocation information of the previous social driving period, a set of constraints is constructed with hardware configuration parameters and location deployment information. With the minimum server switching impact as the optimization objective, the hardware resource scheduling sub-strategy is optimized and solved. At the same time, considering the availability of candidate subject social driving activities and remaining hardware resources, as many candidate subject social driving activities as possible are added to the user social driving of the target academic virtual community.

[0098] In a preferred embodiment, the hardware resource scheduling sub-strategy and the social driving sub-strategy are extracted from the user social driving strategy, and the server resource allocation and user social driving steps of the subject section are executed respectively, specifically including:

[0099] S410: Extract the hardware resource scheduling sub-strategy and social driving sub-strategy from the user social driving strategy, and use the hardware resource scheduling sub-strategy to control several distributed community servers to perform server resource allocation for each subject section in each social driving cycle of the target social driving period.

[0100] S420: Using the aforementioned social-driven sub-strategy, the virtual community management terminal is driven to execute user social-driven activities for candidate disciplines in the distributed community server and corresponding subject sections, and to control the allocation of server resources for the subject sections corresponding to the newly added candidate discipline social-driven activities in each social-driven cycle of the target social-driven period on several distributed community servers.

[0101] In this embodiment, by rationally and scientifically implementing user-driven social activities in the academic virtual community, and intelligently allocating scheduling strategies between different subject sections and servers under user-driven social activities when server hardware resources allow, the impact of regional differences in activity levels of different subject sections on the stable operation of the community can be avoided. Furthermore, more user-driven social activities can be run, maintaining the continuous operation of the community with high activity, high popularity, and high stability.

[0102] Reference Figure 3 , Figure 3 This is a structural block diagram of an embodiment of the academic virtual community user social driving device of the present invention.

[0103] like Figure 3As shown, the academic virtual community user social driving device proposed in this embodiment of the invention includes:

[0104] The acquisition module 10 is used to acquire the community attributes of the target academic virtual community; wherein, the community attributes include subject section division information and hardware resource deployment information;

[0105] Prediction module 20 is used to collect subject association information of each subject section in the target operating area based on the subject section division information and construct a set of popularity driving factors. Using the set of popularity driving factors, it predicts the trend of subject section popularity change in the target operating area during the target social driving period.

[0106] The generation module 30 is used to generate a user social driving strategy for the target social driving period based on the hardware resource information and deployment location information of several distributed community servers in the hardware resource deployment information, taking into account the subject section popularity value and popularity influence area in each social driving cycle in the subject section popularity change trend of the target operating area during the target social driving period and the hardware resource allocation information of the previous social driving period.

[0107] The execution module 40 is used to extract the hardware resource scheduling sub-strategy and the social driving sub-strategy from the user social driving strategy, and execute the server resource allocation and user social driving of the subject section respectively.

[0108] Other embodiments or specific implementations of the academic virtual community user social driving device of the present invention can be referred to the above-described method embodiments, and will not be repeated here.

[0109] Furthermore, the present invention also proposes an academic virtual community user social driving device, which includes: a memory, a processor, and an academic virtual community user social driver stored in the memory and executable on the processor. When the academic virtual community user social driver is executed by the processor, it implements the steps of the academic virtual community user social driving method as described above.

[0110] The specific implementation of the academic virtual community user social driving device in this application is basically the same as the various embodiments of the academic virtual community user social driving method described above, and will not be repeated here.

[0111] Furthermore, this invention also proposes a readable storage medium, which includes a computer-readable storage medium storing a social driver program for users of an academic virtual community. The readable storage medium may be... Figure 1The memory 1005 in the terminal can also be at least one of ROM (Read-Only Memory) / RAM (Random Access Memory), magnetic disk, optical disk, etc. The readable storage medium includes several instructions to cause an academic virtual community user social driving device with a processor to execute the academic virtual community user social driving method described in various embodiments of the present invention.

[0112] The specific implementation in the readable storage medium of this application is basically the same as the various embodiments of the above-described academic virtual community user social-driven method, and will not be repeated here.

[0113] It is understood that in the description of this specification, references to terms such as "one embodiment," "another embodiment," "other embodiments," or "first embodiment to Nth embodiment," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0114] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0115] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this 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. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0116] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A user-driven social interaction method for academic virtual communities, characterized in that, Includes the following steps: Obtain the community attributes of the target academic virtual community; wherein, the community attributes include subject section division information and hardware resource deployment information; Based on the subject section division information, collect subject association information of each subject section in the target operating area and construct a set of popularity driving factors. Using the set of popularity driving factors, predict the trend of subject section popularity change in the target operating area during the target social driving period. Based on the hardware resource information and deployment location information of several distributed community servers in the hardware resource deployment information, and considering the subject section popularity value and influence area in each social driving cycle of the target operating region during the target social driving period, as well as the hardware resource allocation information of the previous social driving period, a user social driving strategy for the target social driving period is generated; specifically including: Extract the hardware resource information and deployment location information of several distributed community servers from the hardware resource deployment information, and consider the subject section popularity value and popularity influence area in each social driving cycle and the hardware resource allocation information of the previous social driving period in the subject section popularity change trend of the target operation area during the target social driving period. The first constraint is that the sum of the hardware resource requirements corresponding to the popularity of the subject sections assigned to each distributed community server in each social driving cycle of the target social driving period is higher than the hardware resource configuration parameters corresponding to the hardware resource information of the distributed community server. The second constraint is that the popularity influence area of ​​the subject sections assigned to each distributed community server in each social driving cycle of the target social driving period covers the deployment location information of the distributed community server. The optimization objective is to minimize the sum of the popularity of the subject sections in the two social driving cycles when all subject sections are assigned to different distributed community servers in two adjacent social driving cycles. The optimization solution is to solve for the hardware resource allocation information of the subject sections assigned to several distributed community servers in each social driving cycle of the target social driving period. Based on the hardware resource allocation information of several subject sections allocated to several distributed community servers in each social driving cycle during the target social driving period, a user social driving strategy is generated. Based on the hardware resource allocation information of several subject sections allocated to several distributed community servers in each social driving cycle during the target social driving period, several hardware resource scheduling sub-strategies for distributed community servers are generated. Calculate the difference between the hardware resource configuration parameters of each distributed community server and the sum of the hardware resource requirement parameters for each social driving cycle under the target social driving time period under the hardware resource allocation information, and generate a list of remaining hardware resource parameters for each distributed community server in each social driving cycle of the target social driving time period. Obtain a candidate set of subject-based social activities, extract several candidate subject-based social activities imported in chronological order from the candidate set, predict the subject section popularity trend of each candidate subject-based social activity based on the popularity impact characteristics of each candidate subject-based social activity, and determine the subject section popularity value and popularity impact area for each social driving cycle. Considering the subject section popularity value and popularity influence area of ​​each social driving cycle, as well as the deployment location information and hardware resource remaining parameter list of each distributed community server, under the condition that the hardware resource requirements of the candidate subject social driving activities and the requirement that the deployment location of the distributed community server falls within the popularity influence area are met, the action of adding the candidate subject social driving activities to the target social driving period in the order of importing in chronological order is repeatedly executed until the requirements can no longer be met, so as to obtain the allocation information of each candidate subject social driving activity and the distributed community server in the target social driving period; Based on the selected candidate subject social-driven activities and the allocation information of each candidate subject social-driven activity with the distributed community server in the target social-driven period, several social-driven sub-strategies for the distributed community server are generated. Extract the hardware resource scheduling sub-strategy and the social driving sub-strategy from the user social driving strategy, and execute the server resource allocation and user social driving of the subject section respectively.

2. The academic virtual community user social-driven method as described in claim 1, characterized in that, The steps to obtain the community attributes of a target academic virtual community include: Query the backend management system of the target academic virtual community, parse the subject section structure information stored in the backend management system, and extract several subject section categories of the target academic virtual community; Query the deployment information of the first server of the target academic virtual community in the public cloud service platform and the deployment information of the second server in the self-built IDC data center. Based on the deployment information of the first server and the second server, determine the deployment server set of the target academic virtual community. By using several subject-specific categories as subject-specific category information and the deployment server set as hardware resource deployment information, the community attributes of the target academic virtual community are generated.

3. The academic virtual community user social-driven method as described in claim 1, characterized in that, Based on the subject-specific section division information, the steps of collecting subject-related information for each subject section in the target operating area and constructing a set of popularity driving factors specifically include: Based on several subject category division information, a set of subject keywords is generated for each subject category using data augmentation. Using the aforementioned subject keyword set, several subject-related information entries are matched in the subject-related information database using keyword matching. Popularity driving factors are extracted from these entries, and a popularity driving factor set is constructed. The aforementioned subject-related information is configured to be at least one of the following: academic hot events, community operation activities, or external channel traffic events published by several subject-related hot event publishing pages or publishing platforms recorded in the subject-related information database. The heat driving factors are configured as the heat influence characteristics of academic hot events, community operation activities, or external channel traffic events.

4. The user social-driven method for academic virtual communities as described in claim 1, characterized in that, Using the aforementioned set of popularity-driving factors, the steps for predicting the popularity trend of subject-specific sections in a target operating area during a target social media-driven period specifically include: Obtain information on the changes in the popularity of subject sections within a historical period, extract the subject section popularity value and the area of ​​influence of each subject section category from the information on the changes in the popularity of subject sections, and construct a popularity training sample by combining the information on the changes in the popularity value of subject sections, the information on the changes in the area of ​​influence of the popularity, and the features of the popularity influence. Call the pre-built initial neural network model, train the initial neural network model using the heat training samples, and obtain the heat prediction model of the completed pilgrimage when the training reaches the target number of times or converges. By utilizing several heat influence features from the heat driving factor set, a heat influence feature set is constructed and used as a heat prediction sample. The heat prediction sample is then input into the heat prediction model to predict the heat change trend of subject sections in the target operating area during the target social driving period.

5. The academic virtual community user social-driven method as described in claim 1, characterized in that, Extract the hardware resource scheduling sub-strategy and the social driving sub-strategy from the user social driving strategy, and execute the server resource allocation and user social driving steps of the subject section respectively, specifically including: Extract the hardware resource scheduling sub-strategy and the social driving sub-strategy from the user social driving strategy. Use the hardware resource scheduling sub-strategy to control several distributed community servers to perform server resource allocation for each subject section in each social driving cycle of the target social driving period. Using the aforementioned social-driven sub-strategy, the virtual community management terminal is driven to execute user social-driven activities for candidate subjects in the distributed community servers and corresponding subject sections, and to control the allocation of server resources for the subject sections corresponding to the newly added candidate subject social-driven activities in each social-driven cycle of the target social-driven period on several distributed community servers.

6. A social-driven device for academic virtual communities, characterized in that, include: The acquisition module is used to acquire the community attributes of the target academic virtual community; wherein, the community attributes include subject section division information and hardware resource deployment information; The prediction module is used to collect subject association information of each subject section in the target operating area based on the subject section division information and construct a set of popularity driving factors. Using the set of popularity driving factors, the module predicts the trend of subject section popularity change in the target operating area during the target social driving period. The generation module is used to generate a user social driving strategy for the target social driving period based on the hardware resource information and deployment location information of several distributed community servers in the hardware resource deployment information, considering the subject section popularity value and influence area of ​​each social driving cycle in the target operating area during the target social driving period, and the hardware resource allocation information of the previous social driving period; specifically including: Extract the hardware resource information and deployment location information of several distributed community servers from the hardware resource deployment information, and consider the subject section popularity value and popularity influence area in each social driving cycle and the hardware resource allocation information of the previous social driving period in the subject section popularity change trend of the target operation area during the target social driving period. The first constraint is that the sum of the hardware resource requirements corresponding to the popularity of the subject sections assigned to each distributed community server in each social driving cycle of the target social driving period is higher than the hardware resource configuration parameters corresponding to the hardware resource information of the distributed community server. The second constraint is that the popularity influence area of ​​the subject sections assigned to each distributed community server in each social driving cycle of the target social driving period covers the deployment location information of the distributed community server. The optimization objective is to minimize the sum of the popularity of the subject sections in the two social driving cycles when all subject sections are assigned to different distributed community servers in two adjacent social driving cycles. The optimization solution is to solve for the hardware resource allocation information of the subject sections assigned to several distributed community servers in each social driving cycle of the target social driving period. Based on the hardware resource allocation information of several subject sections allocated to several distributed community servers in each social driving cycle during the target social driving period, a user social driving strategy is generated. Based on the hardware resource allocation information of several subject sections allocated to several distributed community servers in each social driving cycle during the target social driving period, several hardware resource scheduling sub-strategies for distributed community servers are generated. Calculate the difference between the hardware resource configuration parameters of each distributed community server and the sum of the hardware resource requirement parameters for each social driving cycle under the target social driving time period under the hardware resource allocation information, and generate a list of remaining hardware resource parameters for each distributed community server in each social driving cycle of the target social driving time period. Obtain a candidate set of subject-based social activities, extract several candidate subject-based social activities imported in chronological order from the candidate set, predict the subject section popularity trend of each candidate subject-based social activity based on the popularity impact characteristics of each candidate subject-based social activity, and determine the subject section popularity value and popularity impact area for each social driving cycle. Considering the subject section popularity value and popularity influence area of ​​each social driving cycle, as well as the deployment location information and hardware resource remaining parameter list of each distributed community server, under the condition that the hardware resource requirements of the candidate subject social driving activities and the requirement that the deployment location of the distributed community server falls within the popularity influence area are met, the action of adding the candidate subject social driving activities to the target social driving period in the order of importing in chronological order is repeatedly executed until the requirements can no longer be met, so as to obtain the allocation information of each candidate subject social driving activity and the distributed community server in the target social driving period; Based on the selected candidate subject social-driven activities and the allocation information of each candidate subject social-driven activity with the distributed community server in the target social-driven period, several social-driven sub-strategies for the distributed community server are generated. The execution module is used to extract the hardware resource scheduling sub-policy and the social driving sub-policy from the user social driving strategy, and execute the server resource allocation and user social driving of the subject section respectively.

7. A social-driven device for academic virtual communities, characterized in that, The academic virtual community user social driving device includes: a memory, a processor, and an academic virtual community user social driving driver stored in the memory and executable on the processor. When the academic virtual community user social driving driver is executed by the processor, it implements the steps of the academic virtual community user social driving method as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium stores an academic virtual community user social driver program, which, when executed by a processor, implements the steps of the academic virtual community user social driver method as described in any one of claims 1 to 5.

Images