Database construction method and system based on scientific and technological achievement management

Abstract

This application relates to the field of database construction technology, specifically to a database construction method and system based on the management of scientific and technological achievements. The method includes: analyzing the similarity between the semantic word vectors of keywords of each scientific and technological achievement and another scientific and technological achievement to obtain the domain consistency of the two achievements and determine whether they belong to the same domain; analyzing the access volume of all scientific and technological achievements in the same domain in each preset time period to obtain the relative access volume of each scientific and technological achievement in each preset time period; determining the subsequent access frequency of each scientific and technological achievement based on the degree of change in the relative access volume of each scientific and technological achievement in each preset time period, combined with the publication time of each scientific and technological achievement; sorting all scientific and technological achievements based on the subsequent access frequency; using a consistent hashing algorithm to allocate storage for the scientific and technological achievement data; and constructing a database index. This application aims to improve the storage efficiency and access performance of scientific and technological achievement data.

Description

Technical Field

[0001] This application relates to the field of database construction technology, specifically to database construction methods and systems based on the management of scientific and technological achievements. Background Technology

[0002] In recent years, universities, research institutes, and other scientific research institutions have increasingly emphasized the storage and management of research data in order to improve research capabilities and management efficiency. Considering the need for frequent access to various research articles, and in order to more efficiently utilize the read / write performance of storage devices and reduce access latency, the storage of research results needs to be rationally allocated, and databases need to be built for efficient indexing and dynamic allocation of storage resources.

[0003] Currently, tiered storage technology is commonly used, storing frequently accessed research results on high-performance storage devices to accelerate read and write speeds and reduce latency during subsequent accesses. Simultaneously, consistent hashing algorithms are used to allocate and map storage, dynamically adjusting storage strategies based on the access volume of research results to ensure efficient utilization and real-time optimization of storage resources.

[0004] The current practice in allocating storage resources for research findings is based on ranking them by total access volume. However, this method ignores high-access findings that have been published for a long time and whose access demand has significantly decreased, and it also fails to consider the imbalance in access volume between popular and less popular research areas. This results in some less demanded findings still occupying high-performance storage resources, thus failing to fully utilize the performance potential of the storage device. Summary of the Invention

[0005] In view of the above, it is necessary to provide a database construction method and system based on the management of scientific and technological achievements to solve the above problems.

[0006] The first aspect of this application provides a database construction method based on the management of scientific and technological achievements, the method comprising:

[0007] Acquire all scientific and technological achievements data and related data, including: publication time, total number of visits over a preset number of preset time periods, and keywords of the scientific and technological achievements;

[0008] The semantic word vectors of keywords for each scientific and technological achievement are obtained by using a language model. The similarity between the semantic word vectors of keywords of each scientific and technological achievement and another scientific and technological achievement is analyzed to obtain the domain consistency between each scientific and technological achievement and another scientific and technological achievement. Based on the numerical distribution of the domain consistency between two scientific and technological achievements, it is determined whether the two scientific and technological achievements are in the same domain.

[0009] The access volume of all scientific and technological achievements in the same field as each scientific and technological achievement is analyzed in each preset time period. The field consistency between each scientific and technological achievement and other scientific and technological achievements in the same field is combined to obtain the relative access volume of each scientific and technological achievement in each preset time period.

[0010] Based on the degree of change in the relative access volume of each scientific and technological achievement in each preset time period, and in combination with the release time of each scientific and technological achievement, the subsequent access frequency of each scientific and technological achievement is determined.

[0011] All scientific and technological achievements are sorted based on their subsequent access frequency, and a consistent hashing algorithm is used to allocate and store the scientific and technological achievement data to build a database index.

[0012] Preferably, the process of obtaining the consistency of the field between each scientific and technological achievement and another scientific and technological achievement specifically involves:

[0013] Compare the semantic word vectors of each keyword in the i-th scientific and technological achievement with those of the keywords in the j-th scientific and technological achievement, and determine the similar keywords and their corresponding similarity numbers in the j-th scientific and technological achievement for each keyword in the i-th scientific and technological achievement.

[0014] Based on the serial number of each keyword in the i-th scientific and technological achievement and the corresponding similarity serial number, and combined with the semantic similarity between the i-th keyword and its similar keywords in the j-th scientific and technological achievement, the domain consistency factor of the i-th scientific and technological achievement in the j-th scientific and technological achievement is determined.

[0015] The maximum value of the domain consistency factor of the i-th scientific and technological achievement in the j-th scientific and technological achievement and the domain consistency factor of the j-th scientific and technological achievement in the i-th scientific and technological achievement is taken as the domain consistency between the i-th scientific and technological achievement and the j-th scientific and technological achievement.

[0016] Preferably, determining the similar keywords and corresponding similarity numbers of each keyword in the i-th scientific and technological achievement in the j-th scientific and technological achievement specifically involves:

[0017] For the semantic word vector of each keyword of the i-th scientific and technological achievement, find the semantic word vector with the highest cosine similarity among all the semantic word vectors of all the keywords of the j-th scientific and technological achievement, and denot it as the similar keyword of each keyword of the i-th scientific and technological achievement in the j-th scientific and technological achievement. Obtain the index of the similar keyword in the keywords of the j-th scientific and technological achievement, and denot it as the similarity index.

[0018] Preferably, determining the domain consistency factor of the i-th scientific and technological achievement in the j-th scientific and technological achievement includes:

[0019] Calculate the negative correlation mapping result after positively fusing the index of each keyword in the i-th scientific and technological achievement with the similarity index corresponding to the j-th scientific and technological achievement, and use it as the weight;

[0020] The domain consistency factor of the i-th scientific and technological achievement in the j-th scientific and technological achievement is obtained by weighted summing the cosine similarity between all keywords of the i-th scientific and technological achievement and the semantic word vectors corresponding to similar keywords of the j-th scientific and technological achievement.

[0021] Preferably, the weight is specifically the reciprocal of the product of the index of each keyword in the i-th scientific and technological achievement and the similarity index corresponding to the j-th scientific and technological achievement.

[0022] Preferably, the process of determining whether two scientific and technological achievements belong to the same field specifically includes:

[0023] If the domain consistency between two scientific and technological achievements is greater than a preset threshold, the two scientific and technological achievements are determined to be in the same domain; otherwise, the two scientific and technological achievements are determined not to be in the same domain.

[0024] Preferably, the formula for obtaining the relative access volume of each scientific and technological achievement in each preset time period is as follows: In the formula: f` i,a f represents the relative access volume of the i-th scientific and technological achievement within the a-th preset time period. i,a L` represents the total number of visits to the i-th scientific and technological achievement within the a-th preset time period; i,j The normalized value representing the domain consistency between the i-th and j-th scientific and technological achievements; n i f represents the total number of scientific and technological achievements in the same field as the i-th scientific and technological achievement; j,a This represents the total number of visits to the j-th scientific and technological achievement within the a-th preset time period.

[0025] Preferably, determining the subsequent access frequency of each scientific and technological achievement specifically involves:

[0026] Calculate the number of years between the release date of each scientific and technological achievement and the current time;

[0027] Based on the fluctuation characteristics of the relative access volume of each scientific and technological achievement in adjacent preset time periods, the tag sequence of each scientific and technological achievement is determined.

[0028] The cumulative sum of the products of the element values ​​and their corresponding indexes in the tag sequence of each scientific and technological achievement is obtained and divided by the corresponding interval number in years to obtain the subsequent access frequency of each scientific and technological achievement.

[0029] Preferably, determining the marker sequence for each scientific and technological achievement specifically involves:

[0030] Perform a first-order difference on the sequence consisting of all relative visits to each scientific and technological achievement to obtain a first-order difference sequence. Replace the negative elements in the first-order difference sequence with 0 to obtain a labeled sequence.

[0031] Secondly, embodiments of this application also provide a database construction system based on the management of scientific and technological achievements, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0032] This application has at least the following beneficial effects:

[0033] This application first acquires all scientific and technological achievements data and related data. By obtaining the basic information of all scientific and technological achievements, a data foundation is laid for subsequent analysis and modeling. A language model is used to obtain the semantic word vectors of the keywords for each scientific and technological achievement. Obtaining the semantic word vectors of the keywords through a language model captures the semantic features of the keywords, rather than just the surface text, which helps in identifying the similarity between different scientific and technological achievements. Analyzing the similarity between the semantic word vectors of the keywords of each scientific and technological achievement and another scientific and technological achievement yields the domain consistency between each scientific and technological achievement and another. This helps in determining which scientific and technological achievements are similar in academic or technical fields, thereby identifying achievements belonging to the same field. This facilitates more effective classification and grouping during storage and retrieval. Determining domain consistency helps to aggregate achievements in related fields and optimize the data organization structure. Analyzing the access volume of all scientific and technological achievements in the same field within each preset time period helps to understand the recent access trends of achievements in a field, thereby better predicting future access demand. Access volume analysis can identify which fields and scientific and technological achievements are potential high-access targets. Combining the field consistency between each scientific and technological achievement and other achievements, the relative access volume of each achievement within each preset time period is obtained. This helps to determine the relative importance of each achievement in its field, aiding in the allocation of storage resources and optimization of database access strategies to more efficiently meet the access needs of different scientific and technological achievements. Based on the degree of change in the relative access volume of each scientific and technological achievement within each preset time period, combined with the release time of each achievement, the subsequent access frequency of each achievement is determined. This helps to identify which achievements should be prioritized for storage in high-performance storage, assisting in optimizing storage and resource allocation strategies. Finally, ranking all scientific and technological achievements based on their subsequent access frequency, and prioritizing the storage and management of achievements with higher access frequencies, ensures that the most frequently accessed achievements are allocated appropriate storage resources, thereby improving the overall system efficiency. In this way, optimizing storage and access strategies improves overall data management efficiency, ensuring that scientific and technological achievement data can be stored and retrieved efficiently and accurately. Attached Figure Description

[0034] Figure 1A flowchart illustrating the steps of a database construction method based on scientific and technological achievements management, provided as an embodiment of this application;

[0035] Figure 2 A schematic diagram of a consistent hash ring provided in one embodiment of this application;

[0036] Figure 3 A schematic diagram of an adjusted consistent hash ring provided for one embodiment of this application. Detailed Implementation

[0037] In the description of the embodiments in this application, the words "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary," "or," and "for example" is intended to present the relevant concepts in a specific manner.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in this application's specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0039] It should also be noted that the terms "first" and "second" in this application and its accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The methods disclosed in the embodiments of this application or the methods shown in the flowcharts include one or more steps for implementing the method. Without departing from the scope of protection of this application, the execution order of multiple steps can be interchanged, and some steps can also be deleted.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0041] The following, in conjunction with the accompanying drawings, details the specific scheme of the database construction method and system based on scientific and technological achievements management provided in this application.

[0042] Please see Figure 1 The diagram illustrates a flowchart of a database construction method based on scientific and technological achievements management according to an embodiment of this application. The method includes the following steps:

[0043] The first step is to acquire all scientific and technological achievements data and related data, including: the name of the scientific and technological achievement, the publication time, the total number of visits over a preset number of preset time periods, and the keywords of the scientific and technological achievement.

[0044] First, all scientific and technological achievements and related data are stored in different storage devices. These storage devices include high-performance storage devices with high cost per unit of storage space but fast read and write speeds, and general storage areas with low cost per unit of storage space but low read and write speeds.

[0045] Using hierarchical storage technology, several scientific and technological achievements are first arranged from highest to lowest according to their current access volume. The scientific and technological achievements with high access volume are stored in high-performance storage first. After the high-performance storage is full, the remaining scientific and technological achievements that have not yet been stored are stored in general storage.

[0046] A consistent hashing algorithm is used for storage allocation of scientific and technological achievement data and for constructing a database index. First, each piece of scientific and technological achievement data is mapped onto a hash ring to form scientific and technological achievement nodes. Based on the storage conditions of each piece of data, this application considers adding several virtual nodes with different storage devices at appropriate locations on the consistent hashing ring to complete the storage allocation and database construction. A schematic diagram of the consistent hashing ring construction is shown below. Figure 2 As shown.

[0047] The obtained dataset of scientific and technological achievements is initially allocated for storage and a database is constructed. The scientific and technological achievements are stored on a hash ring, and each node stores related data for that achievement. The number of nodes storing the scientific and technological achievements is denoted as n. The related data for each scientific and technological achievement includes: the name of the achievement, its publication date, a set of daily visits over the past week, and a set of keywords related to the achievement. It should be noted that the total daily visits over the past week are a preset number of preset time periods, which can be determined by the user based on their storage space. This embodiment uses data from each day within a week.

[0048] The second step is to use a language model to obtain the semantic word vectors of the keywords of each scientific and technological achievement, analyze the similarity between the semantic word vectors of the keywords of each scientific and technological achievement and another scientific and technological achievement, and obtain the domain consistency between each scientific and technological achievement and another scientific and technological achievement; based on the numerical distribution of the domain consistency between two scientific and technological achievements, determine whether the two scientific and technological achievements are in the same domain.

[0049] While total access volume can reflect the frequency of access to scientific and technological achievements to some extent, scientific and technological achievements evolve with time. Some scientific and technological achievements that were published a long time ago may have made groundbreaking discoveries and had a large number of accesses in the past, but at present they are already public knowledge and no longer need to be accessed or cited. Their recent access volume may not have increased significantly, so it is unreasonable to put them into high-performance storage. Therefore, the method of allocating storage and building databases solely based on total access volume is somewhat one-sided.

[0050] Scientific and technological achievements are highly time-sensitive; the faster the recent growth rate of access volume, the higher the recent access frequency. Therefore, it is necessary to further adjust the storage allocation based on factors such as the recent growth rate of access volume for scientific and technological achievements.

[0051] Scientific and technological achievements cover a wide range of fields, and the level of research interest varies across different areas. Popular fields typically experience higher visitor traffic due to active research activities, and even smaller research results receive considerable attention. Conversely, less popular fields tend to have fewer research achievements, and even if breakthroughs occur, the increase in visitor traffic may be limited due to the relatively small number of researchers in those fields. Therefore, while there is a certain positive correlation between the visitor volume and the quality of research results, the strength of this correlation is influenced by the popularity of the field. Thus, when adjusting storage resource allocation based on visitor volume, it is crucial to first eliminate the interference of field popularity on visitor volume changes.

[0052] Scientific and technological achievements in the same field often have similar or even identical keywords. The earlier a keyword appears in the list, the higher its relevance to the content of the scientific and technological achievement. Firstly, for a given keyword, semantic word vectors can be obtained using the BERT model. The cosine similarity between two semantic word vectors represents the semantic similarity between the two keywords.

[0053] For the i-th scientific and technological achievement, obtain its keyword set. Among them, g i,s s represents the s-th keyword of the i-th scientific and technological achievement. i Let represent the total number of keywords in the i-th scientific and technological achievement; and denote the set of semantic word vectors of the keywords in the i-th scientific and technological achievement as . in, Let represent the semantic word vector of the s-th keyword of the i-th scientific and technological achievement; let denote the set of semantic word vectors of the keywords of the j-th scientific and technological achievement (j≠i) as . in, Let s represent the semantic word vector of the s-th keyword of the j-th scientific and technological achievement. j This represents the total number of keywords in the j-th scientific and technological achievement, and also the total number of semantic word vectors for the keywords in the j-th scientific and technological achievement.

[0054] For the keyword semantic word vector set of the i-th scientific and technological achievement The elements in the array, with the a-th (1≤a≤s) as an example. i Taking the j-th element as an example, the semantic word vector set of the keywords of the j-th scientific and technological achievement is respectively... Find the element with the highest similarity to the cosine, and obtain the keyword semantic word vector set of that element for the j-th scientific and technological achievement. The subscript in the middle is denoted as b. a (1≤ba ≤s j The cosine similarity is c. a Based on this, the domain consistency factor of the i-th scientific and technological achievement in the j-th scientific and technological achievement is calculated and denoted as L. i,j L i,j The calculation formula is: In the formula: a represents the i-th scientific and technological achievement and the a-th keyword, b a For the j-th scientific and technological achievement, the b-th one a There are 10 keywords, and among the keywords of the j-th scientific and technological achievement, the keyword with the highest semantic similarity to the a-th keyword of the i-th scientific and technological achievement has a semantic similarity of c. a .

[0055] It should be understood that c a The higher the value, the higher the similarity between the two keywords; a and b a The smaller the value, the earlier the two keywords appear in the text, and the higher their relevance to the scientific and technological achievements. The value of c is used as the similarity between the two. a The weights of the values ​​are summed to obtain the domain consistency between the i-th and j-th scientific and technological achievements. Their value ranges are then mapped to [0,1] and normalized to obtain L`. i,j =norm{L i,j}, norm{} denotes the normalization function; in particular, let L` i,i =1.

[0056] The maximum value of the normalized value of the domain consistency factor of the i-th scientific and technological achievement in the j-th scientific and technological achievement and the normalized value of the domain consistency factor of the j-th scientific and technological achievement in the i-th scientific and technological achievement is taken as the domain consistency between the i-th scientific and technological achievement and the j-th scientific and technological achievement.

[0057] Furthermore, it determines whether two scientific and technological achievements belong to the same field: if the field consistency between the two scientific and technological achievements is greater than a preset threshold, the two scientific and technological achievements are determined to belong to the same field; otherwise, the two scientific and technological achievements are determined not to belong to the same field. In this embodiment, the preset threshold value is 0.7. Implementers can determine the value of the threshold according to the actual situation, and this application does not impose any restrictions on it.

[0058] The third step is to analyze the access volume of all scientific and technological achievements in the same field as each scientific and technological achievement in each preset time period, and combine the field consistency between each scientific and technological achievement and other scientific and technological achievements in the same field to obtain the relative access volume of each scientific and technological achievement in each preset time period.

[0059] To eliminate the influence of domain popularity on the access volume of scientific and technological achievements, the access volume of the i-th scientific and technological achievement is reduced by the access volume of all scientific and technological achievements in the same domain as the i-th scientific and technological achievement, thus obtaining the relative access volume of the i-th scientific and technological achievement. The total access volume set F of the i-th scientific and technological achievement is then used to determine the relative access volume. i Day t of visits f i,t For example, its relative number of visits is denoted as f` i,t The calculation formula is as follows: In the formula: f i,t L` represents the total number of visits to the i-th scientific and technological achievement on day t within the past week; i,j The normalized value representing the domain consistency between the i-th and j-th scientific and technological achievements; n i f represents the total number of scientific and technological achievements in the same field as the i-th scientific and technological achievement; j,t This represents the total number of visits to the j-th scientific and technological achievement on day t within the past week.

[0060] In summary, the ratio of the total number of visits to the i-th scientific and technological achievement on day t within the past week to the total number of visits to all scientific and technological achievements in the same field represents its relative number of visits after removing the influence of field popularity. i,t The relative visit volume of the scientific and technological achievement within the past week was calculated using the same method.

[0061] The fourth step: Based on the degree of change in the relative access volume of each scientific and technological achievement in each preset time period, and in combination with the release time of each scientific and technological achievement, determine the subsequent access frequency of each scientific and technological achievement.

[0062] Technological achievements are constantly evolving and highly time-sensitive. Total access volume lacks real-time data; to predict the future frequency of access to technological achievements, further calculations are needed, incorporating more recent and real-time change data.

[0063] The earlier a scientific or technological achievement is published, the more likely it is to already be known to the public and no longer require access or viewing. Obtain the publication date of each scientific or technological achievement and calculate the number of years between the publication date and the current date. Note that any period less than one year should be rounded up to the nearest year.

[0064] The more significant the recent increase in the relative access volume of a scientific or technological achievement, the higher the recent access volume of that achievement, and the more likely it is to be accessed frequently in the future. Let F' be the set of relative access volumes of the i-th scientific or technological achievement within the past week. i For example, a first-order difference is performed on the sequence consisting of the relative access frequency set elements of the i-th scientific and technological achievement, resulting in a first-order difference sequence. Negative elements in the first-order difference sequence are replaced with 0 to obtain a labeled sequence. Furthermore, the subsequent access frequency of the i-th scientific and technological achievement is denoted as P. i P iThe calculation formula is: In the formula:ye i fc` represents the number of years since the publication of the i-th scientific and technological achievement. A larger value indicates a longer period of time since the achievement's publication, suggesting lower timeliness, lower probability of access, and lower subsequent access frequency. i,s Let s be the s-th element in the tag sequence of the i-th scientific and technological achievement. The larger the value of s, the more times the scientific and technological achievement has been accessed recently, the higher the probability of it being accessed in the future, and the higher the access frequency. At the same time, the larger the value of s, the closer the increase is to the current time, and the higher the reference value of the increase.

[0065] Finally, the frequency P of subsequent access to the i-th scientific and technological achievement is obtained. i The larger this value, the more frequently the technological achievement is expected to be accessed in the future, and the more it should be stored in a high-performance memory.

[0066] Calculate the frequency of subsequent access to all scientific and technological achievements, which will be used for subsequent restorage, allocation, and management of scientific and technological achievement data.

[0067] The fifth step is to sort all scientific and technological achievements based on their subsequent access frequency, use a consistent hashing algorithm to allocate storage for the scientific and technological achievement data, and build a database index.

[0068] All scientific and technological achievements are reordered using their P-values ​​instead of their total access frequency. The higher the subsequent access frequency value, the more it needs to be stored in high-performance memory with high read and write speeds to fully utilize its read and write performance. After the storage allocation, for scientific and technological achievements that are stored in high-performance memory according to total access frequency but need to be stored in general memory after reordering by frequency, they need to be transferred from high-performance memory to general memory. Virtual nodes are added and deleted in the initial hash table to correspond to the storage allocation situation, resulting in an adjusted consistent hash table. A new database index is then built to manage the scientific and technological achievement data.

[0069] The adjusted consistent hash ring diagram is shown below. Figure 3 As shown.

[0070] Based on the same inventive concept as the above methods, this application also provides a database construction system based on scientific and technological achievements management, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described database construction methods based on scientific and technological achievements management.

[0071] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description; sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0072] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from its essential characteristics. Therefore, the embodiments described above should be considered exemplary and non-limiting in all respects; modifications to the technical solutions described in the foregoing embodiments, or equivalent substitutions of some technical features, without causing the essence of the corresponding technical solutions to deviate from the scope of the technical solutions in the embodiments of this application, should all be included within the protection scope of this application.

Claims

1. A database construction method based on management of scientific and technological achievements, characterized in that, The method includes the following steps: Acquire all scientific and technological achievements data and related data, including: publication time, total number of visits over a preset number of preset time periods, and keywords of the scientific and technological achievements; The semantic word vectors of keywords for each scientific and technological achievement are obtained by using a language model. The similarity between the semantic word vectors of keywords of each scientific and technological achievement and another scientific and technological achievement is analyzed to obtain the domain consistency between each scientific and technological achievement and another scientific and technological achievement. Based on the numerical distribution of the domain consistency between two scientific and technological achievements, it is determined whether the two scientific and technological achievements are in the same domain. The access volume of all scientific and technological achievements in the same field as each scientific and technological achievement is analyzed in each preset time period. The field consistency between each scientific and technological achievement and other scientific and technological achievements in the same field is combined to obtain the relative access volume of each scientific and technological achievement in each preset time period. Based on the degree of change in the relative access volume of each scientific and technological achievement in each preset time period, and in combination with the release time of each scientific and technological achievement, the subsequent access frequency of each scientific and technological achievement is determined. All scientific and technological achievements are sorted based on the frequency of subsequent access, and a consistent hashing algorithm is used to allocate and store the scientific and technological achievement data to build a database index. The consistency between each scientific and technological achievement and another scientific and technological achievement in their respective fields is specifically as follows: Compare the semantic word vectors of each keyword in the i-th scientific and technological achievement with those of the keywords in the j-th scientific and technological achievement, and determine the similar keywords and their corresponding similarity numbers in the j-th scientific and technological achievement for each keyword in the i-th scientific and technological achievement. Based on the serial number of each keyword in the i-th scientific and technological achievement and the corresponding similarity serial number, and combined with the semantic similarity between the i-th keyword and its similar keywords in the j-th scientific and technological achievement, the domain consistency factor of the i-th scientific and technological achievement in the j-th scientific and technological achievement is determined. The maximum value of the domain consistency factor of the i-th scientific and technological achievement in the j-th scientific and technological achievement and the domain consistency factor of the j-th scientific and technological achievement in the i-th scientific and technological achievement is taken as the domain consistency between the i-th scientific and technological achievement and the j-th scientific and technological achievement.

2. The database construction method based on scientific and technological achievement management as described in claim 1, characterized in that, The process of determining the similar keywords and corresponding similarity numbers of each keyword in the i-th scientific and technological achievement in the j-th scientific and technological achievement is as follows: For the semantic word vector of each keyword of the i-th scientific and technological achievement, find the semantic word vector with the highest cosine similarity among all the semantic word vectors of all the keywords of the j-th scientific and technological achievement, and denot it as the similar keyword of each keyword of the i-th scientific and technological achievement in the j-th scientific and technological achievement. Obtain the index of the similar keyword in the keywords of the j-th scientific and technological achievement, and denot it as the similarity index.

3. The database construction method based on scientific and technological achievement management as described in claim 1, characterized in that, The determination of the domain consistency factor of the i-th scientific and technological achievement in the j-th scientific and technological achievement includes: Calculate the negative correlation mapping result after positively fusing the index of each keyword in the i-th scientific and technological achievement with the similarity index corresponding to the j-th scientific and technological achievement, and use it as the weight; The domain consistency factor of the i-th scientific and technological achievement in the j-th scientific and technological achievement is obtained by weighted summing the cosine similarity between all keywords of the i-th scientific and technological achievement and the semantic word vectors corresponding to similar keywords of the j-th scientific and technological achievement.

4. The database construction method based on scientific and technological achievement management as described in claim 3, characterized in that, The weight is specifically the reciprocal of the product of the index of each keyword in the i-th scientific and technological achievement and the similarity index corresponding to the j-th scientific and technological achievement.

5. The database construction method based on scientific and technological achievement management as described in claim 1, characterized in that, The process for determining whether two scientific and technological achievements belong to the same field is as follows: If the domain consistency between two scientific and technological achievements is greater than a preset threshold, the two scientific and technological achievements are determined to be in the same domain; otherwise, the two scientific and technological achievements are determined not to be in the same domain.

6. The database construction method based on scientific and technological achievement management as described in claim 1, characterized in that, The relative access volume of each scientific and technological achievement in each preset time period is obtained by the following formula: In the formula: This represents the relative number of visits to the i-th scientific and technological achievement within the a-th preset time period. For the first The total number of visits to a scientific and technological achievement within the a-th preset time period. The normalized value representing the domain consistency between the i-th and j-th scientific and technological achievements; This represents the total number of scientific and technological achievements in the same field as the i-th scientific and technological achievement; Indicates the first The total number of visits to a scientific and technological achievement within the a-th preset time period.

7. The database construction method based on scientific and technological achievement management as described in claim 1, characterized in that, The determination of the subsequent access frequency of each scientific and technological achievement is specifically as follows: Calculate the number of years between the release date of each scientific and technological achievement and the current time; Based on the fluctuation characteristics of the relative access volume of each scientific and technological achievement in adjacent preset time periods, the tag sequence of each scientific and technological achievement is determined. The cumulative sum of the products of the element values ​​and their corresponding indexes in the tag sequence of each scientific and technological achievement is obtained and divided by the corresponding interval number in years to obtain the subsequent access frequency of each scientific and technological achievement.

8. The database construction method based on scientific and technological achievement management as described in claim 7, characterized in that, The determination of the tag sequence for each scientific and technological achievement is specifically as follows: Perform a first-order difference on the sequence consisting of all relative visits to each scientific and technological achievement to obtain a first-order difference sequence. Replace the negative elements in the first-order difference sequence with 0 to obtain a labeled sequence.

9. A database construction system based on the management of scientific and technological achievements, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-8.

Images