An intelligent campus teaching resource management method and system based on artificial intelligence

Abstract

The present application belongs to the technical field of resource allocation management, and provides a kind of intelligent campus teaching resource management method and system based on artificial intelligence, comprising: obtaining the learning resource search record in the present stage learning process of student, and the next stage teaching resource allocation situation of school, screening out main learning resource, according to the search record to carry out search effective frequency analysis, obtain search effective value, carry out search conversion analysis of main learning resource, obtain search conversion value, and determine search dominant platform and non-search dominant platform in combination with the reserve proportion of main learning resource in each resource platform, integrate to obtain search conversion platform group, carry out search jam risk analysis to search channel, judge whether conversion channel allocation is needed, if needed, according to search conversion record and conversion nearby analysis, in combination with search conversion value, conversion channel is distributed, which is beneficial to the rational allocation of teaching resources and improves resource utilization.

Description

Technical Field

[0001] This invention belongs to the field of resource allocation and management technology, specifically a smart campus teaching resource management method and system based on artificial intelligence. Background Technology

[0002] In the current field of smart campus teaching resource management, existing technical solutions still have significant shortcomings in terms of accurate resource matching, collaborative retrieval across multiple resource platforms, and optimization of retrieval channels, making it difficult to meet the needs of students to efficiently access learning resources and schools to conduct refined teaching management.

[0003] In existing technologies, learners need to search for knowledge points they haven't mastered through different resource platforms. During the search process, cross-platform conversion is often necessary because a single platform cannot meet their needs. However, current search and conversion channels between various resource platforms often suffer from incompatibility. They are not dynamically allocated based on learners' actual conversion needs, relying solely on fixed basic channel configurations. This results in frequent blockages on high-frequency conversion paths due to insufficient channels, while low-frequency conversion paths have idle channels. Furthermore, there is no adaptation or optimization based on the conversion relationships between the dominant and non-dominant search platforms. This incompatibility not only prolongs the time learners spend accessing key learning resources and reduces search efficiency but also wastes channel resources.

[0004] Therefore, this invention provides a smart campus teaching resource management method and system based on artificial intelligence. Summary of the Invention

[0005] In order to overcome the shortcomings of the prior art, at least one technical problem raised in the background art is solved.

[0006] The technical solution adopted by this invention to solve its technical problem is: a smart campus teaching resource management method system based on artificial intelligence, comprising:

[0007] Obtain each student's learning resource search records during the current learning process, as well as the school's key teaching resources for the next stage, and filter out the main learning resources;

[0008] We obtain students' search and acquisition records of major learning resources on different resource platforms, as well as search and conversion records between different resource platforms. We conduct effective search frequency analysis based on the search and acquisition records, and search and conversion analysis of major learning resources between different resource platforms based on the search and conversion records. We also determine the dominant search platform and non-dominant search platform by combining the reserve ratio of major learning resources in each resource platform.

[0009] By integrating the search conversion records between different resource platforms, the search-dominant platform and the non-search-dominant platform are integrated to obtain the search conversion platform group. Within the search conversion platform group, the search blocking risk analysis of the search channels between the search-dominant platform and the non-search-dominant platform is carried out, and the search conversion platform groups that need to be allocated conversion channels are screened.

[0010] Based on the search conversion platform group that needs to be selected for conversion channel allocation, the conversion proximity analysis is performed on each resource platform according to the search conversion records, and the conversion channels between the search-dominant platform and the non-search-dominant platform are allocated.

[0011] Furthermore, the main learning resources are obtained through the screening process as follows:

[0012] Obtain the current learning resource search records of each student, and calculate the ratio of the number of searches for each learning resource to the total number of searches for learning resources to obtain the resource search percentage.

[0013] Obtain information on the allocation of educational resources for the next phase from the school's academic affairs office, and identify key teaching resources.

[0014] Learning resources whose resource retrieval frequency is greater than or equal to the preset resource retrieval threshold and appear in key teaching resources are marked as primary learning resources.

[0015] Furthermore, the process of analyzing the effective frequency of the retrieved records is as follows:

[0016] Obtain the search records of major learning resources across different resource platforms;

[0017] Based on any resource platform, the number of times different students search for the same main learning resource on different resource platforms is recorded as the total number of searches, and the number of times the search requirements are met is recorded as the number of times the target is met.

[0018] The ratio of the number of times the criteria were met to the total number of searches is used to obtain the effective search value.

[0019] Furthermore, the process of performing retrieval and conversion analysis of major learning resources across various resource platforms based on retrieval and conversion records is as follows:

[0020] The statistics record the number of resource platform conversions when the search requirements of the resource platform are not met during the main learning resource search process. This number is recorded as the total number of search conversions.

[0021] The number of times each student achieved the required search results after converting their data on the resource platform is recorded as the number of valid search conversions.

[0022] The search conversion value is obtained by comparing the number of effective search conversions with the total number of search conversions.

[0023] Furthermore, the process for determining the dominant retrieval platform and the non-dominant retrieval platform is as follows:

[0024] The amount of main learning resources in each resource platform is statistically analyzed and compared with the total amount of main learning resources in each platform to obtain the reserve ratio of main learning resources in each platform, which is recorded as the resource reserve value.

[0025] The search target value is obtained by comparing the effective search value with the search conversion value. The search target value is then multiplied by the resource reserve value to obtain the platform dominant value.

[0026] The platform dominance value of each resource platform is calculated and compared. The resource platform with the largest platform dominance value is designated as the retrieval dominance platform, and the other resource platforms are designated as non-retrieval dominance platforms.

[0027] Furthermore, the process of obtaining the retrieval and conversion platform group is as follows:

[0028] Mark resource platforms with search conversion records and count all resource platforms with search conversion records;

[0029] The non-search-dominant platforms that have search conversion with the search-dominant platform will be integrated to form a search conversion platform group.

[0030] Furthermore, the process of performing retrieval blocking risk analysis and screening the retrieval conversion platform groups that require conversion channel allocation is as follows:

[0031] The number of times the conversion failed due to retrieval channel blockage during the retrieval conversion process is recorded as the number of blockages.

[0032] The retrieval blocking value is obtained by comparing the number of blocking instances with the total number of retrieval conversions.

[0033] If the retrieval blocking value is greater than the retrieval blocking threshold, it is necessary to convert the retrieval channels between the dominant platform and the non-dominant retrieval platform and mark the retrieval conversion platform group as the retrieval conversion platform group that needs to be converted.

[0034] Furthermore, the process of converting and analyzing resources from various platforms based on proximity is as follows:

[0035] The most recent time point in the search transition between the dominant search platform and the non-dominant search platform is statistically analyzed. The difference between the current time and the most recent time point is calculated to obtain the search transition time difference. These differences are then summed to obtain the transition time.

[0036] By comparing the search conversion time difference with the conversion time and performing a ratio analysis, we can obtain the search proximity value between the search-dominant platform and each non-search-dominant platform.

[0037] Furthermore, the process of allocating the conversion channel between the retrieval-dominant platform and the non-retrieval-dominant platform is as follows:

[0038] The channel conversion value is obtained by comparing the retrieved conversion value with the nearest retrieved value.

[0039] The conversion values ​​of all channels are calculated and summed to obtain the total conversion value. The conversion values ​​of each channel are then compared with the total conversion value to obtain the conversion channel allocation value.

[0040] Based on the conversion channel allocation value, conversion channels are allocated between the retrieval-dominant platform and each non-retrieval-dominant platform.

[0041] An artificial intelligence-based smart campus teaching resource management system includes:

[0042] Comparison and filtering module: Obtain each student's learning resource search records during the current learning process, as well as the school's key teaching resources for the next stage, and filter out the main learning resources;

[0043] Analysis and Determination Module: Obtain the search and acquisition records of students for major learning resources on different resource platforms and the search conversion records between different resource platforms. Analyze the effective search frequency based on the search and acquisition records and the search conversion records to analyze the search conversion of major learning resources between different resource platforms. Combined with the reserve ratio of major learning resources in each resource platform, determine the dominant search platform and the non-dominant search platform.

[0044] Collection and Integration Module: By integrating the search conversion records between different resource platforms, the module integrates the search-dominant platform and the non-search-dominant platform to obtain the search conversion platform group. Within the search conversion platform group, the module performs a search blocking risk analysis on the search channels between the search-dominant platform and the non-search-dominant platform, and filters the search conversion platform groups that need to be allocated conversion channels.

[0045] Conversion Allocation Module: Based on the search conversion platform group that needs to be allocated conversion channels, the module performs a proximity analysis on each resource platform according to the search conversion records and allocates conversion channels between the search-dominant platform and the non-search-dominant platform.

[0046] The beneficial effects of this invention are as follows:

[0047] This process involves acquiring each student's resource search records during their current learning phase, comparing them against the school's resource allocation for the next phase, and identifying key learning resources. Based on search records across different resource platforms and conversion records between them, effective search values ​​and conversion values ​​are determined. Furthermore, considering the proportion of key learning resources on each platform, dominant and non-dominant search platforms are identified. This facilitates precise matching of students' current learning difficulties with the school's next teaching focus, improving the efficiency of resource utilization. Simultaneously, identifying the most efficient dominant search platform provides a basis for subsequent resource platform integration and rational allocation of learning resources. The conversion records between resource platforms also help determine the dominant search platform. The platform and non-search-dominant platforms are integrated to form a search conversion platform group. The risk of blocking in the search channels between the search-dominant and non-search-dominant platforms within this group is analyzed. If such blocking occurs, the conversion channels between the search-dominant and non-search-dominant platforms are allocated based on the search conversion value and the nearest conversion analysis. This facilitates the integration of related non-dominant platforms with the dominant platform at the core, improves the matching degree between the conversion channels and students' actual search needs, enhances the adaptability of the conversion channels to search conversion across different resource platforms, and ultimately improves the smoothness and efficiency of students accessing key learning resources across platforms. This makes the cross-platform scheduling of smart campus teaching resources more aligned with actual teaching and learning needs. Attached Figure Description

[0048] The invention will now be further described with reference to the accompanying drawings.

[0049] Figure 1 This is a flowchart illustrating the steps of a smart campus teaching resource management method based on artificial intelligence, as described in an embodiment of the present invention.

[0050] Figure 2 This is a logic judgment diagram of a smart campus teaching resource management method based on artificial intelligence, as described in an embodiment of the present invention.

[0051] Figure 3 This is a flowchart of a smart campus teaching resource management system based on artificial intelligence, as described in an embodiment of the present invention. Detailed Implementation

[0052] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0053] Example 1: Please refer to Figure 1 - Figure 2As shown in the embodiment of the present invention, a smart campus teaching resource management method based on artificial intelligence is mainly aimed at the problem of mismatched search and conversion channels when students search for knowledge points (learning resources) they have not yet mastered through multiple online education platforms such as library platforms, academic affairs platforms, and learning platforms in a smart campus scenario. Specifically, this manifests as a lack of clear core objectives in channel allocation, failure to combine platform search efficiency with the intensity of conversion needs, and an inability to accurately identify and dynamically adapt to blocking risks, resulting in chaotic search paths for students, low conversion efficiency, and wasted or blocked channel resources. The method includes the following steps:

[0054] Step 1: Obtain each student's learning resource search records during the current learning process, as well as the school's key teaching resources for the next stage, and filter out the main learning resources;

[0055] In step one, the learning resource search records of each student at this stage are obtained from different resource platforms and statistically analyzed to obtain a learning resource search record database.

[0056] Among them, different resource platforms refer to the different online education platforms used by students when searching for learning materials, such as library platforms, academic affairs platforms, and learning platforms;

[0057] The current stage refers to the learning stage of the student in the current month, and the next stage refers to the teaching planning stage of the month immediately following the current month.

[0058] In the learning resource search record database, the number of times each learning resource was searched was obtained. The ratio of the number of times each learning resource was searched to the total number of times learning resources were searched was calculated to obtain the resource search frequency value.

[0059] Obtain information from the school's academic affairs office regarding the allocation of educational resources for the next stage, including the mastery of each knowledge point, and receive key teaching resources.

[0060] Learning resources whose resource retrieval frequency is greater than or equal to the preset resource retrieval threshold and appear in key teaching resources are marked as primary learning resources;

[0061] Understandably, the purpose of selecting key learning resources is to accurately pinpoint the intersection between students' current learning needs and the school's teaching plan, ensuring that the selected resources address students' current learning difficulties and align with the school's teaching goals and priorities for the next stage. Furthermore, it can improve the efficiency of resource utilization, effectively promote students' learning outcomes, and enhance teaching quality. Through the selection of key learning resources, teachers can prepare teaching content more effectively, and students can clarify their learning direction, thereby achieving a mutually beneficial learning experience.

[0062] Step 2: Obtain the search and acquisition records of students for the main learning resources on different resource platforms, as well as the search conversion records between different resource platforms. Analyze the effective search frequency based on the search acquisition records to obtain the effective search value. Analyze the search conversion records between the main learning resources on each resource platform to obtain the search conversion value. Based on the effective search value and the search conversion value, and in combination with the reserve ratio of the main learning resources on each resource platform, determine the dominant search platform and the non-dominant search platform among the resource platforms.

[0063] In step two, at this stage, the retrieval records of the main learning resources on different resource platforms are obtained;

[0064] Based on any resource platform, obtain the number of times different students search for the main learning resources, which is recorded as the total number of searches, and the number of times the search requirements are met, which is recorded as the number of times the target is met;

[0065] The ratio of the number of times the target was met to the total number of searches is used to obtain the effective search value. The effective search value can also be used to determine the effective utilization rate of the main learning resources of different resource platforms and to filter out the resource platform with the highest effective search value.

[0066] Understandably, the physical meaning of the search validity value is that when students use the resource platform to search for their main learning resources, the number of times they meet the search requirements is out of the total number of searches. The lower the search validity value, the lower the efficiency of students in searching for their main learning resources on the corresponding resource platform; the higher the search validity value, the higher the efficiency of students in searching for their main learning resources on the corresponding resource platform.

[0067] The conversion records of different students when they switched resource platforms because the search requirements were not met during the main learning resource search process were statistically analyzed, and the number of main learning resource search conversions between resource platforms was obtained and recorded as the total number of search conversions;

[0068] It should be noted that meeting the search requirements means that the student successfully obtains the main learning resources needed during the search process on the resource platform, and that the content of the resources is complete, accurate, and can meet the student's current learning needs. Conversely, failing to meet the search requirements means that the student fails to obtain the main learning resources needed during the search process on the resource platform.

[0069] The number of times each student achieved the required search results after converting their data on the resource platform is recorded as the number of valid search conversions.

[0070] For example, when a student searches for a major learning resource (a knowledge point), they search through the Learning Tong platform. However, if the search requirements are not met on the Learning Tong platform, they switch to the library platform to search and meet the search requirements. This action of the student switching from the Learning Tong platform to the library platform is recorded as a valid search conversion number.

[0071] The search conversion value is obtained by dividing the number of effective search conversions by the total number of search conversions.

[0072] Understandably, the physical meaning of the search conversion value is that it is obtained by processing the ratio of the number of effective search conversions to the total number of search conversions. It represents the proportion of students who, after failing to meet the requirements of the resource platform, switched to other resource platforms and successfully obtained the main learning resources they needed. The higher the search conversion value, the higher the success rate of students obtaining the main learning resources through platform conversion.

[0073] Based on the proportion of major learning resources in each resource platform, and combined with the effective search value and search conversion value, the dominant and non-dominant search platforms are determined, as follows:

[0074] Specifically, the amount of main learning resources in each resource platform is counted and compared with the total amount of main learning resources to obtain the reserve ratio of main learning resources in each resource platform, which is recorded as the resource reserve value.

[0075] It should be noted that the resource reserve value refers to the proportion of each resource platform's reserve of major learning resources to the total reserve of major learning resources. The resource reserve value can intuitively reflect the richness of major learning resources on different resource platforms, and provides a data basis for subsequently determining the dominant and non-dominant search platforms.

[0076] The search target value is obtained by comparing the effective search value with the search conversion value. The search target value is then multiplied by the resource reserve value to obtain the platform dominant value.

[0077] The platform dominance value of each resource platform is calculated and compared. The resource platform with the largest platform dominance value is designated as the search dominance platform, and the other resource platforms are designated as non-search dominance platforms.

[0078] It is understandable that the physical meaning of the platform dominance value is that the search target value is obtained by the ratio of the search effective value to the search conversion value. The larger the search effective value, the more abundant the main learning resources in the resource platform. The smaller the search conversion value, the more abundant the main learning resources in the resource platform. The larger the search target value obtained after processing the ratio of the search effective value to the search conversion value, the more abundant the main learning resources in the resource platform. The platform dominance value is obtained by multiplying the search target value and the resource reserve value. The larger the resource reserve value, the more abundant the main learning resources in the resource platform. Therefore, the larger the search target value and the larger the resource reserve value, the larger the platform dominance value obtained by multiplying them. The reason why the resource platform with the largest platform dominance value is the search dominance platform is that the main learning resources in the corresponding resource platform are the most abundant.

[0079] Example 2: Please refer to Figure 1 - Figure 2 As shown in the embodiment of the present invention, a smart campus teaching resource management method based on artificial intelligence includes the following steps:

[0080] Step 3: By integrating the search conversion records between various resource platforms, the search-dominant platform and the non-search-dominant platform are integrated to obtain the search conversion platform group. Within the search conversion platform group, the search blocking risk analysis is performed on the search channels between the search-dominant platform and the non-search-dominant platform, and the search conversion platform groups that need to be allocated conversion channels are selected.

[0081] In step three, resource platforms with search conversion records are marked, and all resource platforms with search conversion records are counted.

[0082] Based on the search-dominant platform obtained in step two, the non-search-dominant platforms that have search conversion with the search-dominant platform will be integrated to obtain a search conversion platform group;

[0083] It should be noted that the purpose of obtaining the search conversion platform group is to understand the search conversion situation between non-search-dominant platforms and search-dominant platforms. With the search-dominant platform as the core hub, the non-search-dominant platforms that have search conversion associations with the search-dominant platform are integrated. This can specifically solve the problems of repeated conversions and confusing search paths caused by the dispersion of platforms when students search for main learning resources. With the integration of the search conversion platform group, students do not need to blindly switch between multiple unrelated non-search-dominant platforms. They only need to start from the dominant platform to quickly connect to supplementary resource platforms with conversion records, which can significantly shorten the search path, reduce search time costs, and improve the efficiency of obtaining main learning resources.

[0084] From the perspective of smart campus teaching resource management, the retrieval and conversion platform group can coordinate and link the main learning resources scattered in different non-retrieval-dominant platforms with the main learning resources of the retrieval-dominant platform. This helps managers to understand the complementary relationship of resources between platforms and the flow of retrieval traffic, providing data support for subsequent resource allocation. For example, based on the conversion records in the retrieval and conversion platform group, high-frequency demand main learning resources in non-retrieval-dominant platforms can be migrated to the retrieval-dominant platform for supplementation, or resource entry points for non-dominant platforms can be set up in the dominant platform to realize the management of main learning resources.

[0085] Furthermore, the establishment of the search conversion platform group can provide a directional basis for the subsequent allocation of conversion channels between search-dominant and non-search-dominant platforms;

[0086] The process of analyzing the retrieval blocking risk between each non-retrieval-dominant platform and the retrieval-dominant platform is as follows:

[0087] Based on the retrieval conversion records, the number of times the conversion failed due to retrieval channel blockage during the retrieval conversion process is recorded as the number of blockages;

[0088] The retrieval blocking value is obtained by comparing the number of blocking instances with the total number of retrieval conversions.

[0089] Understandably, the physical meaning of the retrieval blocking value lies in reflecting the frequency of conversion failures caused by retrieval channel issues when a non-retrieval-dominant platform converts to a retrieval-dominant platform within the retrieval conversion platform group.

[0090] Compare the calculated retrieval blocking value with the retrieval blocking threshold;

[0091] If the retrieval blocking value is less than or equal to the retrieval blocking threshold, then there is no need to convert the retrieval channels between the retrieval-dominant platform and the non-retrieval-dominant platform.

[0092] If the retrieval blocking value is greater than the retrieval blocking threshold, it is necessary to convert the retrieval channels between the retrieval-dominant platform and the non-retrieval-dominant platform, and mark the retrieval conversion platform group as the retrieval conversion platform group that needs to be converted.

[0093] Step 4: Based on the search conversion platform group that needs to be allocated conversion channels, perform a conversion proximity analysis on each resource platform according to the search conversion records, and allocate conversion channels between the search-dominant platform and the non-search-dominant platform in combination with the search conversion values;

[0094] Based on the search conversion platform group, the time interval between different students' search conversions is obtained. The most recent time point between the search-dominant platform and the non-search-dominant platform is counted. The difference between the current time and the most recent time point is processed to obtain the search conversion time difference.

[0095] The time difference between the search conversion between the dominant search platform and each non-dominant search platform is calculated, and then summed to obtain the conversion time.

[0096] By comparing the search conversion time difference with the conversion time, we can obtain the search proximity value between the search-dominant platform and each non-search-dominant platform.

[0097] For example, if the academic affairs platform is the primary search platform, and there was a transfer from the library platform to the academic affairs platform 1 day ago, and a transfer from the learning platform to the academic affairs platform 7 days ago, then the nearest search value between the academic affairs platform and the library platform would be... The search value for the academic affairs platform and the learning platform is based on proximity. ;

[0098] Understandably, the significance of the search proximity value lies in reflecting the frequency with which students switch from non-search-dominant platforms to search-dominant platforms when searching for major learning resources by analyzing the time interval between the student's search switching between different resource platforms and the current time. The smaller the search proximity value, the more likely the student is to switch from the corresponding non-search-dominant platform to the search-dominant platform for resource retrieval in the near future, reflecting the stronger the resource complementarity and search correlation between the corresponding non-search-dominant platform and the search-dominant platform.

[0099] The channel conversion value is obtained by comparing the retrieved conversion value with the nearest retrieved value.

[0100] The conversion values ​​of all channels are calculated and summed to obtain the total conversion value. The conversion values ​​of each channel are then compared with the total conversion value to obtain the conversion channel allocation value.

[0101] Based on the conversion channel allocation value, conversion channels are allocated between the retrieval-dominant platform and the non-retrieval-dominant platform;

[0102] Obtain the number of conversion channels between the search-dominant platform and the non-search-dominant platform, and multiply the number of conversion channels with the corresponding conversion channel allocation value to obtain the number of conversion channels between the search-dominant platform and each non-search-dominant platform.

[0103] It should be noted that the number of conversion channels refers to the number of channels set up between the primary search platform and the non-primary search platform for resource retrieval conversion. These channels are used to ensure that students can smoothly switch between the primary search platform and the non-primary search platform when searching for major learning resources.

[0104] It should also be noted that the purpose of allocating conversion channels between search-dominant and non-search-dominant platforms is to rationally allocate search channel resources by quantifying the search conversion correlation strength between various resource platforms, so as to ensure that the conversion path between search-dominant and non-search-dominant platforms is efficient and smooth for students. Specifically, the higher the channel allocation value, the closer the search correlation between the non-search-dominant platform and the search-dominant platform, and the more frequent the student's conversion needs. Therefore, more conversion channels need to be allocated to reduce the risk of search blocking. Conversely, platforms with lower channel allocation values ​​should have fewer channels to avoid resource idleness.

[0105] Working principle of the invention:

[0106] This process involves acquiring each student's resource search records during their current learning phase, comparing them against the school's resource allocation for the next phase, and identifying key learning resources. Based on search records across different resource platforms and conversion records between them, effective search values ​​and conversion values ​​are determined. Furthermore, considering the proportion of key learning resources on each platform, dominant and non-dominant search platforms are identified. This facilitates precise matching of students' current learning difficulties with the school's next teaching focus, improving the efficiency of resource utilization. Simultaneously, identifying the most efficient dominant search platform provides a basis for subsequent resource platform integration and rational allocation of learning resources. The conversion records between resource platforms also help determine the dominant search platform. The platform and non-search-dominant platforms are integrated to form a search conversion platform group. The search conversion platform group is analyzed to see if there is a risk of blocking between the search-dominant and non-search-dominant platforms. If so, the conversion channels between the search-dominant and non-search-dominant platforms are allocated according to the search conversion value and the conversion proximity analysis. This is conducive to integrating and associating non-dominant platforms with the dominant platform as the core, improving the matching degree between the conversion channels and the actual search needs of students, and enhancing the adaptability of the conversion channels to search conversion between different resource platforms. Ultimately, it improves the smoothness and efficiency of students' access to major learning resources across platforms, and makes the cross-platform scheduling of smart campus teaching resources more in line with actual teaching and learning needs.

[0107] Example 3: Please refer to Figure 3 As shown in the embodiment of the present invention, a smart campus teaching resource management system based on artificial intelligence includes the following modules:

[0108] Comparison and filtering module: Obtain each student's learning resource search records during the current learning process, as well as the school's key teaching resources for the next stage, and filter out the main learning resources;

[0109] Analysis and Determination Module: Obtain the search and acquisition records of students for major learning resources on different resource platforms and the search conversion records between different resource platforms. Analyze the effective search frequency based on the search and acquisition records and the search conversion records to analyze the search conversion of major learning resources between different resource platforms. Combined with the reserve ratio of major learning resources in each resource platform, determine the dominant search platform and the non-dominant search platform.

[0110] Collection and Integration Module: By integrating the search conversion records between different resource platforms, the module integrates the search-dominant platform and the non-search-dominant platform to obtain the search conversion platform group. Within the search conversion platform group, the module performs a search blocking risk analysis on the search channels between the search-dominant platform and the non-search-dominant platform, and filters the search conversion platform groups that need to be allocated conversion channels.

[0111] Conversion Allocation Module: Based on the search conversion platform group that needs to be allocated conversion channels, the module performs a proximity analysis on each resource platform according to the search conversion records and allocates conversion channels between the search-dominant platform and the non-search-dominant platform.

[0112] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A smart campus teaching resource management method based on artificial intelligence, characterized in that: Includes the following steps: Obtain each student's learning resource search records during the current learning process, as well as the school's key teaching resources for the next stage, and filter out the main learning resources; The system obtains students' search and acquisition records of major learning resources on different resource platforms, as well as search and conversion records between different resource platforms. Based on the search and acquisition records, it performs effective search frequency analysis, and based on the search and conversion records, it performs search and conversion analysis of major learning resources between different resource platforms. Combined with the reserve ratio of major learning resources in each resource platform, it determines the dominant search platform and the non-dominant search platform. The effective frequency analysis of the retrieval includes: Obtain the search records of major learning resources across different resource platforms; Based on any resource platform, the number of times different students search for the same main learning resource on different resource platforms is recorded as the total number of searches, and the number of times the search requirements are met is recorded as the number of times the target is met. The ratio of the number of times the criteria were met to the total number of searches is used to obtain the effective search value. The retrieval conversion analysis includes: The statistics record the number of resource platform conversions when the search requirements of the resource platform are not met during the main learning resource search process. This number is recorded as the total number of search conversions. The number of times each student achieved the required search results after converting their data on the resource platform is recorded as the number of valid search conversions. The search conversion value is obtained by dividing the number of effective search conversions by the total number of search conversions. The identified dominant retrieval platforms and non-dominant retrieval platforms include: The amount of main learning resources in each resource platform is statistically analyzed and compared with the total amount of main learning resources in each platform to obtain the reserve ratio of main learning resources in each platform, which is recorded as the resource reserve value. The search target value is obtained by comparing the effective search value with the search conversion value. The search target value is then multiplied by the resource reserve value to obtain the platform dominant value. The platform dominance value of each resource platform is calculated and compared. The resource platform with the largest platform dominance value is designated as the search dominance platform, and the other resource platforms are designated as non-search dominance platforms. By integrating the search conversion records between different resource platforms, the search-dominant platform and the non-search-dominant platform are integrated to obtain the search conversion platform group. Within the search conversion platform group, the search blocking risk analysis of the search channels between the search-dominant platform and the non-search-dominant platform is carried out, and the search conversion platform groups that need to be allocated conversion channels are screened. Based on the search conversion platform group that needs to be screened for conversion channel allocation, the conversion proximity analysis is performed on each resource platform according to the search conversion records. The conversion channel allocation value is used to allocate conversion channels between the search-dominant platform and the non-search-dominant platform. The conversion channel allocation value is calculated from the search conversion value and the search proximity value. The conversion proximity analysis includes: statistically analyzing the most recent time point of conversion between the dominant retrieval platform and the non-dominant retrieval platform, calculating the difference between the current time and the most recent time point to obtain the retrieval conversion time difference, and summing the results to obtain the conversion time. By comparing the search conversion time difference with the conversion time and performing a ratio analysis, we can obtain the search proximity value between the search-dominant platform and each non-search-dominant platform.

2. The method for managing smart campus teaching resources based on artificial intelligence according to claim 1, characterized in that: The process of selecting the main learning resources is as follows: Obtain the current learning resource search records of each student, and calculate the ratio of the number of searches for each learning resource to the total number of searches for learning resources to obtain the resource search percentage. Obtain information on the allocation of educational resources for the next phase from the school's academic affairs office, and identify key teaching resources. Learning resources whose resource retrieval frequency is greater than or equal to the preset resource retrieval threshold and appear in key teaching resources are marked as primary learning resources.

3. The method for managing smart campus teaching resources based on artificial intelligence according to claim 1, characterized in that: The process of obtaining the retrieval and conversion platform group is as follows: Mark resource platforms with search conversion records and count all resource platforms with search conversion records; The non-search-dominant platforms that have search conversion with the search-dominant platform will be integrated to form a search conversion platform group.

4. The method for managing smart campus teaching resources based on artificial intelligence according to claim 1, characterized in that: The process of performing retrieval blocking risk analysis and screening retrieval conversion platform groups that require conversion channel allocation is as follows: The number of times the conversion failed due to retrieval channel blockage during the retrieval conversion process is recorded as the number of blockages. The retrieval blocking value is obtained by comparing the number of blocking instances with the total number of retrieval conversions. If the retrieval blocking value is greater than the retrieval blocking threshold, it is necessary to convert the retrieval channels between the dominant platform and the non-dominant retrieval platform and mark the retrieval conversion platform group as the retrieval conversion platform group that needs to be converted.

5. The method for managing smart campus teaching resources based on artificial intelligence according to claim 1, characterized in that: The process of allocating conversion channels between the retrieval-dominant platform and the non-retrieval-dominant platform through conversion channel allocation values ​​is as follows: The channel conversion value is obtained by comparing the retrieved conversion value with the nearest retrieved value. The conversion values ​​of all channels are calculated and summed to obtain the total conversion value. The conversion values ​​of each channel are then compared with the total conversion value to obtain the conversion channel allocation value. Based on the conversion channel allocation value, conversion channels are allocated between the retrieval-dominant platform and each non-retrieval-dominant platform.

6. A smart campus teaching resource management system based on artificial intelligence, characterized in that: include: Comparison and filtering module: Obtain each student's learning resource search records during the current learning process, as well as the school's key teaching resources for the next stage, and filter out the main learning resources; Analysis and Determination Module: Obtain the search and acquisition records of students for major learning resources on different resource platforms and the search conversion records between different resource platforms. Analyze the effective search frequency based on the search and acquisition records and analyze the search conversion records between major learning resources on each resource platform. Combined with the reserve ratio of major learning resources on each resource platform, determine the dominant search platform and non-dominant search platform. The effective frequency analysis of the retrieval includes: Obtain the search records of major learning resources across different resource platforms; Based on any resource platform, the number of times different students search for the same main learning resource on different resource platforms is recorded as the total number of searches, and the number of times the search requirements are met is recorded as the number of times the target is met. The ratio of the number of times the criteria were met to the total number of searches is used to obtain the effective search value. The retrieval conversion analysis includes: The statistics record the number of resource platform conversions when the search requirements of the resource platform are not met during the main learning resource search process. This number is recorded as the total number of search conversions. The number of times each student achieved the required search results after converting their data on the resource platform is recorded as the number of valid search conversions. The search conversion value is obtained by dividing the number of effective search conversions by the total number of search conversions. The identified dominant retrieval platforms and non-dominant retrieval platforms include: The amount of main learning resources in each resource platform is statistically analyzed and compared with the total amount of main learning resources in each platform to obtain the reserve ratio of main learning resources in each platform, which is recorded as the resource reserve value. The search target value is obtained by comparing the effective search value with the search conversion value. The search target value is then multiplied by the resource reserve value to obtain the platform dominant value. The platform dominance value of each resource platform is calculated and compared. The resource platform with the largest platform dominance value is designated as the search dominance platform, and the other resource platforms are designated as non-search dominance platforms. Collection and Integration Module: By integrating the search conversion records between different resource platforms, the module integrates the search-dominant platform and the non-search-dominant platform to obtain the search conversion platform group. Within the search conversion platform group, the module performs a search blocking risk analysis on the search channels between the search-dominant platform and the non-search-dominant platform, and filters the search conversion platform groups that need to be allocated conversion channels. Conversion Allocation Module: Based on the screening of retrieval conversion platform groups that require conversion channel allocation, the module performs conversion proximity analysis on each resource platform according to the retrieval conversion records, and allocates conversion channels between the retrieval-dominant platform and non-retrieval-dominant platforms through conversion channel allocation values. The conversion channel allocation values ​​are calculated from the retrieval conversion value and the retrieval proximity value. The conversion proximity analysis includes: statistically analyzing the most recent time point of conversion between the dominant retrieval platform and the non-dominant retrieval platform, calculating the difference between the current time and the most recent time point to obtain the retrieval conversion time difference, and summing the results to obtain the conversion time. By comparing the search conversion time difference with the conversion time and performing a ratio analysis, we can obtain the search proximity value between the search-dominant platform and each non-search-dominant platform.

Images