Intelligent assessment and transformation management method for scientific and technological achievements

Abstract

The invention relates to the technical field of data analysis, and particularly discloses a scientific and technological achievement intelligent evaluation and transformation management method, which comprises the following steps: S1, evaluating scientific and technological achievements to obtain evaluation scores, and determining high-quality achievements in the scientific and technological achievements; s2, determining an initial keyword based on an actual demand and the keyword list, determining a target keyword, and generating a target point according to the target keyword; determining a comparison keyword, and generating a comparison point based on the comparison keyword; s3, clustering the comparison points to obtain a comparison point cluster, and adjusting the comparison point cluster according to the density of the comparison points to obtain a comparison cluster; and determining a comparison cluster where the target point is located, and determining a recommendation sequence of the high-quality achievements according to the Euclidean distance between the comparison point in the comparison cluster and the target point. According to the method, the conversion efficiency and effect of the scientific and technological achievements are improved by accurately matching the user demands and the high-quality scientific and technological achievements.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a method for intelligent evaluation and transformation management of scientific and technological achievements. Background Art

[0002] Scientific and technological achievements refer to knowledge, methods, products, processes, systems or theoretical results with practical value and scientific significance produced through scientific research, technological development, technological innovation, engineering practice and other activities. These achievements can promote the progress of science and technology and serve various goals such as economic development, social needs and environmental improvement.

[0003] The transformation of scientific and technological achievements refers to the process of applying innovative knowledge, technology, products, processes and other achievements formed in the scientific research process to actual production, commercial operations or social services, thereby realizing their economic value or social benefits. However, since the demand side cannot accurately match its actual needs with existing scientific and technological achievements, the conversion rate of scientific and technological achievements is low, which not only leads to a large number of high-quality scientific and technological achievements being idle or inefficiently used, but also causes the demand side to spend a lot of time and resources on technology selection. Summary of the invention

[0004] The purpose of the present invention is to provide a method for intelligent evaluation and transformation management of scientific and technological achievements to solve the following technical problems:

[0005] Since the demand side is unable to accurately match its actual needs with existing scientific and technological achievements, the conversion rate of scientific and technological achievements is low. This not only causes a large number of high-quality scientific and technological achievements to be idle or inefficiently used, but also causes the demand side to spend a lot of time and resources on technology selection.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] The intelligent evaluation and transformation management method of scientific and technological achievements includes the following steps:

[0008] S1: Obtain all scientific and technological achievements, evaluate the scientific and technological achievements based on preset evaluation steps to obtain evaluation scores, and when the evaluation scores are greater than or equal to preset values, mark the corresponding scientific and technological achievements as high-quality achievements;

[0009] S2: Determine the actual needs of the user, determine the keywords in the actual needs based on a preset keyword list, mark them as initial keywords, preprocess the initial keywords to obtain target keywords, establish an n-dimensional coordinate system, n represents the total number of the target keywords, generate target points (A1, A2, ..., An) in the n-dimensional coordinate system, An represents the nth target keyword;

[0010] Mark the target keyword in the high-quality results as a comparison keyword, and generate comparison points (B1, B2, ..., Bn) in the n-dimensional coordinate system based on the comparison keyword, where Bn represents the nth comparison keyword;

[0011] S3: setting a clustering radius, taking the comparison point as the cluster center, clustering the comparison points to obtain comparison point clusters, determining the comparison point density of the comparison point clusters, sorting the comparison point clusters in descending order according to the comparison point density, and removing the comparison point clusters in the sorting in sequence from the last comparison point cluster, until after removing a comparison point cluster, there are comparison points that do not belong to the comparison point cluster, and marking the comparison point clusters that have not been removed at this time as comparison clusters;

[0012] Determine the comparison cluster C where the target point is located, calculate the Euclidean distance D between the comparison point and the target point in the comparison cluster C, sort the comparison points in the comparison cluster C in ascending order according to the size of the Euclidean distance D to obtain a recommended order, and recommend the high-quality results to the user in the order of the recommended order.

[0013] As a further solution of the present invention: in step S1, the process of determining the evaluation score specifically includes:

[0014] Determine the evaluation information of the scientific and technological achievements, the evaluation information includes the number of citations, the degree of technological leadership, the degree of user satisfaction, and the evaluation score of the scientific and technological achievements based on the superior and inferior solution distance method.

[0015] As a further solution of the present invention: in the step S2, the process of determining the target keyword specifically includes:

[0016] Encode non-numeric initial keywords;

[0017] Standardize the initial keywords of the numeric type to eliminate the dimension.

[0018] As a further solution of the present invention: in the step S3, the process of determining the density of the comparison points specifically includes:

[0019] Calculate the comparison point density P = f / (πr 2 ), f represents the number of comparison points in the comparison point cluster, and r represents the cluster radius.

[0020] As a further solution of the present invention: in the step S3, the process of determining the comparison cluster further includes the following steps:

[0021] Determine the minimum circumscribed circle of the comparison cluster, determine the overlapping part of the minimum circumscribed circle, and when the ratio of the overlapping part to the minimum circumscribed circle a is greater than or equal to 0.5, take the comparison cluster corresponding to the minimum circumscribed circle a as an abnormal cluster, merge the single comparison point in the abnormal cluster into the nearest comparison cluster, and delete the abnormal cluster.

[0022] As a further solution of the present invention: in the step S3, when the target point does not belong to the comparison cluster, an error message is sent for prompting.

[0023] Beneficial effects of the present invention: In this scheme, by conducting a quality assessment on all scientific and technological achievements, high-quality achievements are screened out, the recommendation efficiency is improved, resource waste is avoided, and the high quality of the recommendation results is guaranteed, laying the foundation for subsequent matching; then, initial keywords are extracted from the actual needs of users, and pre-processed to be standardized as target keywords, so as to clarify the core characteristics of user needs, form quantifiable target points, and unify user needs into the same framework to facilitate comparison with scientific and technological achievements; comparison keywords are extracted from high-quality achievements, so as to map the characteristics of the achievements into the same coordinate system, form an intuitive comparison with user needs, construct a unified multi-dimensional feature space, and express user needs and scientific and technological achievements in the form of target points and comparison points, so as to provide a reference for the subsequent matching of scientific and technological achievements. Provide a quantitative comparison benchmark to provide data support for subsequent clustering and sorting operations; take the comparison point as the center, group the results into point clusters with different densities, exclude low-density point clusters, screen out irrelevant high-quality results, focus on results closely related to user needs, avoid recommending too many invalid results to users, and improve recommendation accuracy; calculate the Euclidean distance between the user demand point and each result point in the remaining high-density point clusters, determine the result point closest to the user demand, sort by relevance, use the quantitative distance as the recommendation basis, and enhance matching accuracy; arrange the remaining results in ascending order of distance and recommend them to users to ensure that users receive the high-quality results that best meet their needs first, improve satisfaction, thereby improving the efficiency of results conversion and optimizing resource utilization. The present invention improves the conversion efficiency and effect of scientific and technological achievements by accurately matching user needs with high-quality scientific and technological achievements. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The present invention will be further described below in conjunction with the accompanying drawings.

[0025] Figure 1 It is a flow chart of the intelligent evaluation and transformation management method of scientific and technological achievements of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] See also Figure 1 As shown, the present invention is a method for intelligent evaluation and transformation management of scientific and technological achievements, comprising the following steps:

[0028] S1: Obtain all scientific and technological achievements, evaluate the scientific and technological achievements based on preset evaluation steps to obtain evaluation scores, and when the evaluation scores are greater than or equal to preset values, mark the corresponding scientific and technological achievements as high-quality achievements;

[0029] S2: Determine the actual needs of the user, determine the keywords in the actual needs based on a preset keyword list, mark them as initial keywords, preprocess the initial keywords to obtain target keywords, establish an n-dimensional coordinate system, n represents the total number of the target keywords, generate target points (A1, A2, ..., An) in the n-dimensional coordinate system, An represents the nth target keyword;

[0030] Mark the target keyword in the high-quality results as a comparison keyword, and generate comparison points (B1, B2, ..., Bn) in the n-dimensional coordinate system based on the comparison keyword, where Bn represents the nth comparison keyword;

[0031] S3: setting a clustering radius, taking the comparison point as the cluster center, clustering the comparison points to obtain comparison point clusters, determining the comparison point density of the comparison point clusters, sorting the comparison point clusters in descending order according to the comparison point density, and removing the comparison point clusters in the sorting in sequence from the last comparison point cluster, until after removing a comparison point cluster, there are comparison points that do not belong to the comparison point cluster, and marking the comparison point clusters that have not been removed at this time as comparison clusters;

[0032] Determine the comparison cluster C where the target point is located, calculate the Euclidean distance D between the comparison point and the target point in the comparison cluster C, sort the comparison points in the comparison cluster C in ascending order according to the size of the Euclidean distance D to obtain a recommended order, and recommend the high-quality results to the user in the order of the recommended order.

[0033] It should be noted that by conducting a quality assessment on all scientific and technological achievements, high-quality achievements are screened out, the recommendation efficiency is improved, resource waste is avoided, and the high quality of the recommendation results is guaranteed, laying the foundation for subsequent matching; then, the initial keywords are extracted from the actual needs of users, and pre-processed to be standardized as target keywords, so as to clarify the core characteristics of user needs, form quantifiable target points, and unify user needs into the same framework for easy comparison with scientific and technological achievements; comparative keywords are extracted from high-quality achievements, so as to map the characteristics of the achievements into the same coordinate system, form an intuitive comparison with user needs, construct a unified multi-dimensional feature space, and express user needs and scientific and technological achievements in the form of target points and comparative points, providing quantified The comparison benchmark provides data support for subsequent clustering and sorting operations; with the comparison point as the center, the results are grouped into point clusters with different densities, and low-density point clusters are excluded to screen out irrelevant high-quality results, focus on results that are closely related to user needs, avoid recommending too many invalid results to users, and improve recommendation accuracy; calculate the Euclidean distance between the user demand point and each result point in the remaining high-density point clusters, determine the result point closest to the user demand, sort it by relevance, use the quantitative distance as the basis for recommendation, and enhance matching accuracy; arrange the remaining results in ascending order of distance and recommend them to users to ensure that users receive the high-quality results that best meet their needs first, improve satisfaction, thereby improving the efficiency of result conversion and optimizing resource utilization.

[0034] In another preferred embodiment of the present invention, in step S1, the process of determining the evaluation score specifically includes:

[0035] Determine the evaluation information of the scientific and technological achievements, the evaluation information includes the number of citations, the degree of technological leadership, the degree of user satisfaction, and the evaluation score of the scientific and technological achievements based on the superior and inferior solution distance method.

[0036] It is worth noting that the quality of scientific and technological achievements is affected by multiple factors (such as the number of citations, technological leadership, etc.). The good and bad solution distance method can take these multi-dimensional characteristics into consideration and give an overall evaluation score. The good and bad solution distance method constructs an ideal solution (best case) and a negative ideal solution (worst case) to quantify the distance between each achievement and the two. The closer the achievement is to the ideal solution, the higher the score, and the farther it is from the negative ideal solution, the lower the score. The good and bad solution distance method combined with multi-dimensional evaluation information can more scientifically and impartially evaluate the quality of scientific and technological achievements, select the best achievements, and take into account both evaluation efficiency and adaptability, providing a solid foundation for the precise transformation of scientific and technological achievements.

[0037] In another preferred embodiment of the present invention, in step S2, the process of determining the target keyword specifically includes:

[0038] Encode non-numeric initial keywords;

[0039] Standardize the initial keywords of the numeric type to eliminate the dimension.

[0040] In another preferred embodiment of the present invention, in step S3, the process of determining the comparison point density specifically includes:

[0041] The comparison point density P=f / (πr2) is calculated, where f represents the number of comparison points in the comparison point cluster, and r represents the cluster radius.

[0042] In another preferred embodiment of the present invention, in the step S3, the process of determining the comparison cluster further includes the following steps:

[0043] Determine the minimum circumscribed circle of the comparison cluster, determine the overlapping part of the minimum circumscribed circle, and when the ratio of the overlapping part to the minimum circumscribed circle a is greater than or equal to 0.5, take the comparison cluster corresponding to the minimum circumscribed circle a as an abnormal cluster, merge the single comparison point in the abnormal cluster into the nearest comparison cluster, and delete the abnormal cluster.

[0044] It should be noted that in the clustering process, clusters with abnormal point distribution may be generated (for example, the points in the cluster are sparse and not concentrated, or the cluster overlaps significantly with other clusters). The minimum circumscribed circle is a geometric analysis tool that can intuitively reflect the spatial distribution of points in the cluster. By detecting the overlapping parts of the minimum circumscribed circle, abnormal clusters with fuzzy boundaries and non-independent boundaries with other clusters can be identified; abnormal clusters may lead to inaccurate recommendation results, so these abnormal clusters need to be eliminated or their points need to be reclassified.

[0045] In another preferred embodiment of the present invention, in the step S3, when the target point does not belong to the comparison cluster, an error message is sent for prompting.

[0046] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. The intelligent evaluation and transformation management method of scientific and technological achievements is characterized by: The following steps are involved: S1: Obtain all scientific and technological achievements, evaluate the scientific and technological achievements based on preset evaluation steps to obtain evaluation scores, and when the evaluation scores are greater than or equal to preset values, mark the corresponding scientific and technological achievements as high-quality achievements; S2: Determine the actual needs of the user, determine the keywords in the actual needs based on a preset keyword list, mark them as initial keywords, preprocess the initial keywords to obtain target keywords, establish an n-dimensional coordinate system, n represents the total number of the target keywords, generate target points (A1, A2, ..., An) in the n-dimensional coordinate system, An represents the nth target keyword; Mark the target keyword in the high-quality results as a comparison keyword, and generate comparison points (B1, B2, ..., Bn) in the n-dimensional coordinate system based on the comparison keyword, where Bn represents the nth comparison keyword; S3: setting a clustering radius, taking the comparison point as the cluster center, clustering the comparison points to obtain comparison point clusters, determining the comparison point density of the comparison point clusters, sorting the comparison point clusters in descending order according to the comparison point density, and removing the comparison point clusters in the sorting in sequence from the last comparison point cluster, until after removing a comparison point cluster, there are comparison points that do not belong to the comparison point cluster, and marking the comparison point clusters that have not been removed at this time as comparison clusters; Determine the comparison cluster C where the target point is located, calculate the Euclidean distance D between the comparison point and the target point in the comparison cluster C, sort the comparison points in the comparison cluster C in ascending order according to the size of the Euclidean distance D to obtain a recommended order, and recommend the high-quality results to the user in the order of the recommended order.

2. The method for intelligent evaluation and transformation management of scientific and technological achievements according to claim 1 is characterized in that: In step S1, the process of determining the evaluation score specifically includes: Determine the evaluation information of the scientific and technological achievements, the evaluation information includes the number of citations, the degree of technological leadership, the degree of user satisfaction, and the evaluation score of the scientific and technological achievements based on the superior and inferior solution distance method.

3. The method for intelligent evaluation and transformation management of scientific and technological achievements according to claim 1 is characterized in that: In step S2, the process of determining the target keyword specifically includes: Encode non-numeric initial keywords; Standardize the initial keywords of numeric type to eliminate the dimension.

4. The method for intelligent evaluation and transformation management of scientific and technological achievements according to claim 1 is characterized in that: In step S3, the process of determining the comparison point density specifically includes: Calculate the comparison point density P = f / (πr 2 ), f represents the number of comparison points in the comparison point cluster, and r represents the cluster radius.

5. The method for intelligent evaluation and transformation management of scientific and technological achievements according to claim 1 is characterized in that: In the step S3, the process of determining the comparison cluster further includes the following steps: Determine the minimum circumscribed circle of the comparison cluster, determine the overlapping part of the minimum circumscribed circle, and when the ratio of the overlapping part to the minimum circumscribed circle a is greater than or equal to 0.5, take the comparison cluster corresponding to the minimum circumscribed circle a as an abnormal cluster, merge the single comparison point in the abnormal cluster into the nearest comparison cluster, and delete the abnormal cluster.

6. The method for intelligent evaluation and transformation management of scientific and technological achievements according to claim 1 is characterized in that: In the step S3, when the target point does not belong to the comparison cluster, an error message is sent for prompting.

Images