Scientific researcher portrait construction method and device, electronic equipment and storage medium

Abstract

The invention provides a scientific researcher portrait construction method and device, electronic equipment and a storage medium, and is applied to the technical field of data processing, and the method comprises the steps: obtaining scientific research data of a target scientific researcher, and carrying out the preprocessing of the scientific research data, and obtaining the target scientific research data in a text format; extracting keywords of the target scientific research data and a relation network between the target scientific research personnel and other scientific research personnel; determining a scientific research score of a target scientific research person according to the target scientific research data; and constructing a portrait of the target scientific researcher based on the keyword, a relation network between the target scientific researcher and other scientific researchers and the scientific research score of the target scientific researcher. According to the method, the comprehensive ability and the potential value of the scientific researchers are helped to be deeply understood, and the detailed and accurate scientific researcher portraits are provided, so that the scientific research project management is optimized, and the scientific and technological innovation is promoted.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, electronic device and storage medium for constructing a portrait of a scientific researcher. Background Art

[0002] With the increase in scientific research activities and the expansion of the scientific research team, science and technology managers face new challenges in personnel evaluation and resource allocation. Traditional manual evaluation methods are not only inefficient, but also difficult to achieve objective and comprehensive evaluation. The evaluation of scientific researchers' professional capabilities, work efficiency and innovative achievements often requires quantitative data and objective evaluation criteria, which are often lacking in traditional methods. Summary of the invention

[0003] In view of this, the purpose of this application is to propose a method, device, electronic device and storage medium for constructing a portrait of a scientific researcher, so as to help gain a deeper understanding of the comprehensive capabilities and potential value of scientific researchers, and by providing detailed and accurate portraits of scientific researchers, it will help optimize the management of scientific research projects and promote scientific and technological innovation.

[0004] Based on the above purpose, this application provides a method for constructing a portrait of a scientific researcher, including:

[0005] Acquire the scientific research data of the target scientific researcher, and pre-process the scientific research data to obtain the target scientific research data in text format;

[0006] Extracting keywords of the target scientific research data and the relationship network between the target scientific researcher and other scientific researchers;

[0007] Determine a research score of a target researcher based on the target research data;

[0008] A profile of the target researcher is constructed based on the keywords, the relationship network between the target researcher and other researchers, and the research score of the target researcher.

[0009] Based on the same inventive concept, the present application also provides a device for constructing a portrait of a scientific researcher, including:

[0010] A preprocessing module is configured to obtain the scientific research data of the target scientific researcher and preprocess the scientific research data to obtain the target scientific research data in text format;

[0011] An extraction module, which is configured to extract keywords of the target scientific research data and a relationship network between the target scientific researcher and other scientific researchers;

[0012] A scoring module, configured to determine a scientific research score of a target scientific researcher based on the target scientific research data;

[0013] A portrait construction module is configured to construct a portrait of the target researcher based on the keywords, the relationship network between the target researcher and other researchers, and the research score of the target researcher.

[0014] Based on the same inventive concept, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method as described above when executing the computer program.

[0015] Based on the same inventive concept, the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the method as described above.

[0016] From the above, it can be seen that the present application provides a method, device, electronic device and storage medium for constructing a portrait of a scientific researcher, wherein the method includes: obtaining the scientific research data of the target scientific researcher and preprocessing the scientific research data to obtain the target scientific research data in text format; extracting the keywords of the target scientific research data and the relationship network between the target scientific researcher and other scientific researchers; determining the scientific research score of the target scientific researcher based on the target scientific research data; constructing a portrait of the target scientific researcher based on the keywords, the relationship network between the target scientific researcher and other scientific researchers, and the scientific research score of the target scientific researcher; by expanding and screening the keywords with synonyms, the accuracy and relevance of the keywords are ensured, thereby improving the quality and practicality of the portrait; by comprehensively considering the keywords, relationship networks and scientific research scores of the scientific researchers to construct the portrait, it can comprehensively reflect the professional ability, research direction and social network of the scientific researchers and other dimensions, which helps to gain an in-depth understanding of the comprehensive ability and potential value of the scientific researchers, and managers can more effectively conduct talent assessment, team building and resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic diagram of the process of constructing a portrait of a scientific researcher according to an embodiment of the present application;

[0019] Figure 2 This is a flow chart of a method for constructing a portrait of a scientific researcher according to another embodiment of the present application;

[0020] Figure 3 This is a flow chart of a method for constructing a portrait of a scientific researcher according to another embodiment of the present application;

[0021] Figure 4 A schematic diagram of a device for constructing a portrait of a scientific researcher in an embodiment of the present application;

[0022] Figure 5 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0024] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0025] Among the related technologies, the power industry is a highly standardized industry that relies on a large number of standard documents and technical specifications to guide key steps such as engineering design, construction and acceptance. These documents not only ensure the safe and reliable operation of the power system, but are also important tools for maintaining industry order and promoting technological progress. However, with the increasing scale and complexity of power projects, the existing standard document system has become increasingly large and complex. This has brought significant challenges to engineers in finding, understanding and applying relevant specifications, especially when it is necessary to respond to and solve on-site problems quickly. The overly cumbersome specification query process may affect the efficiency and quality of the project. At the same time, the role of scientific researchers in the power industry has become increasingly prominent. Through continuous technical research and innovation activities, they have provided strong technical support for the modernization and intelligent upgrading of the power system. The work results of scientific researchers are directly related to the technological progress and competitiveness of the industry. However, with the increase in scientific research activities and the expansion of the scientific research team, science and technology managers face new challenges in personnel evaluation and resource allocation. Traditional manual evaluation methods are not only inefficient, but also difficult to achieve objective and comprehensive evaluation. The evaluation of the professional ability, work efficiency and innovative achievements of scientific researchers often needs to rely on quantitative data and objective evaluation criteria, which are often lacking in traditional methods. In addition, the information of researchers usually involves a large amount of text materials, such as project reports, research papers and technical patents, etc. The management and analysis of these materials requires a lot of time and effort. Science and technology managers need to extract valuable data from these complex information to evaluate the contributions and potential of researchers. This process is very complex and labor-intensive.

[0026] Based on the above problems, the applicant found that: by obtaining the research data of the target scientific researcher and preprocessing the research data, the target scientific research data in text format is obtained; the keywords of the target scientific research data and the relationship network between the target scientific researcher and other scientific researchers are extracted; the scientific research score of the target scientific researcher is determined according to the target scientific research data; the portrait of the target scientific researcher is constructed based on the keywords, the relationship network between the target scientific researcher and other scientific researchers, and the scientific research score of the target scientific researcher; it is helpful to reduce the bias of subjective judgment, and the accuracy and relevance of the keywords are ensured by expanding and screening the keywords with synonyms, thereby improving the quality and practicality of the portrait; by comprehensively considering the scientific research data, keywords, interpersonal network and scientific research score of the scientific researcher to construct the portrait, it can fully reflect the professional ability, research direction and social network of the scientific researcher, which is helpful to deeply understand the comprehensive ability and potential value of the scientific researcher. By providing detailed and accurate portraits of scientific researchers, managers can more effectively conduct talent assessment, team building and resource allocation, which is helpful to optimize the management of scientific research projects and promote scientific and technological innovation.

[0027] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0028] In some embodiments, Figure 1 As shown, a method for constructing a portrait of a scientific researcher is performed by a data processor. The subsequent embodiments are all illustrated by taking the data processor as an example. The method includes:

[0029] S101, obtaining the scientific research data of the target scientific researcher, and preprocessing the scientific research data to obtain the target scientific research data in text format;

[0030] In the specific implementation, first obtain the relevant scientific research data of the target researchers, which usually includes but is not limited to the researchers' papers, patents, project participation records, academic reports, and any other publicly accessible scientific research results. After the data is acquired, the scientific research data is preprocessed to convert it into a format suitable for further analysis. Preprocessing mainly includes the following aspects: removing irrelevant information in the scientific research data, such as advertisements, irrelevant links, and non-scientific research related texts. In addition, it is necessary to identify and correct errors in the data, such as spelling errors, format errors, etc. The acquired scientific research data is uniformly converted into a standard text format, and PDF, HTML or other format files are converted into plain text files to facilitate subsequent text analysis and processing. Unstructured scientific research data can also be structured, useful information is extracted and stored in a certain format, such as storing the title, author, publication time, keywords and other information of the paper separately.

[0031] S102, extracting keywords of the target scientific research data and the relationship network between the target scientific researcher and other scientific researchers;

[0032] In specific implementation, keyword extraction is to identify those words that can represent the theme and focus of the text by analyzing the content of the scientific research text. Usually, the target scientific research data is segmented and the stop words in the segmentation results are deleted to obtain the vocabulary set of the target scientific research data; the word frequency inverse document frequency of each word in the vocabulary set is determined. If the word frequency inverse document frequency of the word is greater than or equal to the preset word frequency inverse document frequency, the word is determined to be a keyword of the target scientific research data; extracting keywords from text data such as scientific research literature and project reports can help researchers quickly grasp the core theme and research trend of the text. Extracting the relationship network between the target researcher and other researchers usually involves entity recognition of the target scientific research data to obtain multiple entities and semantic relationships between multiple entities; determining all researchers among the multiple entities, and constructing a relationship network between the target researcher and other researchers among all researchers except the target researcher based on the semantic relationships between the multiple entities; it helps to build a detailed portrait of the researcher and can also provide scientific data support for scientific research management and decision-making.

[0033] S103, determining a scientific research score of a target scientific researcher according to the target scientific research data;

[0034] In specific implementation, it can be determined by evaluating the quality and importance of each scientific research result and the contribution of the target researcher in the scientific research results. For example, when scoring papers, factors such as the impact factor of the journal in which the paper is published and the number of citations of the paper can be considered; when scoring patents, the patent authorization, actual application and transformation can be evaluated; when scoring scientific research projects, the funding scale of the project, the depth and breadth of the project's research, and the social or academic impact of the project can be considered. Determining the contribution of the target researcher in the scientific research results includes analyzing the specific role and contribution of the researcher in each result, such as the first author of the paper, the corresponding author, or the host of the project, or the ranking of the target researcher in the results.

[0035] S104. Construct a portrait of the target researcher based on the keywords, the relationship network between the target researcher and other researchers, and the research score of the target researcher.

[0036] In specific implementation, by analyzing the keywords in the target researcher's literature and projects, their main research fields and interests can be identified. Keywords help to describe the target researcher's professional background and research expertise. The relationship network between the target researcher and other researchers can be used to analyze the researcher's cooperation mode, cooperation frequency and partners, which helps to understand the target researcher's position and influence in the research community. The research score integrates the quality and quantity of the target researcher's papers, patents, projects and other achievements, and is an important indicator to measure his or her scientific research achievements and influence. The above keyword information, relationship network analysis results and research scores are integrated to construct a comprehensive portrait of the target researcher, including but not limited to the researcher's basic information, research fields, major achievements, cooperation networks, social influence and other dimensions. Constructing the target researcher's portrait through this data and analysis-based method can not only provide a comprehensive, objective and dynamic evaluation of researchers, but also provide strong support for scientific research management and strategy formulation, which will help promote the transformation of scientific research institutions to a more data-driven and efficient management model.

[0037] In this embodiment, by constructing a portrait of a researcher based on keywords, a relationship network between the target researcher and other researchers, and the scientific research score of the target researcher, the scientific research management process becomes more transparent, and potential partners and cooperation opportunities can be identified to promote scientific research cooperation and knowledge exchange. It is helpful to build a stronger scientific research team and improve the influence of research results. Researchers can understand their position and influence in the field of scientific research through their own portraits, so as to better plan their career development path. It is also possible to manage and evaluate researchers more effectively, and to better cope with the challenges and opportunities in the field of scientific research, thereby promoting the progress of scientific research and technological development.

[0038] In some embodiments, Figure 2 As shown, the method of determining the scientific research score of the target scientific researcher based on the target scientific research data includes:

[0039] S201, obtaining a plurality of scientific research achievement data from the target scientific research data, and determining the number of participants in each scientific research achievement and the ranking of the target scientific researcher in the scientific research achievement according to the plurality of scientific research achievement data;

[0040] During the specific implementation, it is necessary to obtain multiple scientific research results data from the target scientific research data, which include but are not limited to: papers, patents, scientific research projects, etc.; for each scientific research result, it is necessary to determine the number of participants and the specific ranking of the target researchers, which can usually be obtained from the author list of the paper, the inventor list of the patent or the participant list of the project report. The ranking usually reflects the contribution of the target researchers to the result.

[0041] S202. Determine the score of the scientific research achievement according to the number of participants in the scientific research achievement and the ranking of the target scientific researcher in the scientific research achievement;

[0042] In specific implementation, the number of participants in scientific research results reflects the scale of cooperation in the results. In scientific research projects, the size of the team can range from a few people to dozens of people, and each member may assume different tasks and responsibilities. The ranking of researchers in the results is usually a direct indicator of their contribution. In academic papers, the first author is usually considered to be the main contributor, while the corresponding author is responsible for supervising and guiding the entire research work. In patents and scientific research projects, rankings are often closely related to individual contributions. Therefore, when scoring, the higher the ranking, it usually means that the researcher's contribution is greater, and the corresponding score should also be higher.

[0043] S203. Perform a weighted summation on the scores of all scientific research results according to the preset scoring weights to obtain the scientific research score of the target researcher.

[0044] In specific implementation, the scores of various scientific research results will be weighted and summed according to the preset scoring weights (for example, 40% for papers, 30% for patents, and 30% for scientific research projects) to comprehensively evaluate the overall scientific research performance and contribution of researchers in order to make a fair and objective evaluation. By taking the weighted sum of the scores of all scientific research results, the resulting scientific research score not only provides researchers with a quantitative scientific research performance indicator, but also helps to promote the overall quality and efficiency of scientific research work.

[0045] In this embodiment, clear scoring criteria and weights are used to ensure that the contribution of each scientific research result is fairly evaluated, reducing subjectivity and bias. Scientific research institutions can evaluate the performance of researchers more scientifically and systematically, thereby promoting the quality and efficiency of scientific research work, and also helping to establish a more fair and dynamic scientific research environment.

[0046] In some embodiments, Figure 3 As shown, the score of the scientific research results is determined according to the number of participants in the scientific research results and the ranking of the target researchers in the scientific research results, including:

[0047] S301, determining the highest score and the lowest score for the scientific research results according to the type of the scientific research results and the preset type score relationship;

[0048] In specific implementation, the types of scientific research results usually include papers, patents, scientific research projects, academic reports, etc. Each type of scientific research result has different contributions to scientific research and technological development, so the preset type scoring relationship usually sets the corresponding scoring standards based on its importance and influence. For each type of scientific research result, the highest and lowest scores are preset according to its generally accepted academic or industry importance; the highest and lowest scores for scientific research results can be determined by querying the type of scientific research results and the preset type scoring relationship.

[0049] S302A, in response to determining that the ranking is before the first preset ranking, determining that the highest score is the score of the scientific research achievement;

[0050] In specific implementation, being before the first preset ranking (exemplarily, the first preset ranking can be the ranking corresponding to the top 30% of the participants of the scientific research results. For example, if there are 10 participants in total, the first preset ranking can be set to 2 or 3) usually indicates that the target researcher has made significant contributions to the scientific research results. If it is determined that the ranking is before the first preset ranking, then the highest score is determined as the score of the scientific research results.

[0051] S302B, in response to determining that the ranking is after the second preset ranking, determining the lowest score as the score of the scientific research achievement;

[0052] In specific implementation, being after the second preset ranking (exemplarily, the second preset ranking can be the ranking corresponding to the bottom 30% of the participants in the scientific research results. For example, if there are 10 participants in total, the second preset ranking can be set to 8 or 9) usually indicates that the target researcher has made a relatively small contribution to the scientific research results. If it is determined that the ranking is after the second preset ranking, then the lowest score is determined as the score of the scientific research results.

[0053] S302C. In response to determining that the ranking is between the first preset ranking and the second preset ranking, determining the score of the scientific research achievement according to the number of participants, ranking, highest score and lowest score of the scientific research achievement, wherein the score of the scientific research achievement is inversely proportional to the ranking.

[0054] In specific implementation, when it is determined that the ranking is between the first preset ranking and the second preset ranking, the formula Determine the score of the scientific research achievement, where F represents the score of the scientific research achievement, N represents the number of participants in the scientific research achievement, X represents the ranking of the target scientific researcher in the scientific research achievement, Amax represents the highest score, and Amin represents the lowest score. By setting the score of the scientific research achievement to be inversely proportional to the ranking, it is possible to evaluate the contributions of each scientific researcher more fairly, especially those whose rankings are between the first preset ranking and the second preset ranking. This not only considers the number of participants in the scientific research achievement and the individual's specific ranking, but also ensures the accuracy and rationality of the score through a reasonable mathematical model.

[0055] In this embodiment, by setting different score ranges for different types of scientific research achievements and combining the ranking of the target scientific researcher to determine the specific score of the individual, it is possible to more accurately reflect the actual contribution of each target scientific researcher to the project and ensure the fairness of the evaluation. Through a specific scoring model, the evaluation of scientific research achievements becomes more quantitative and standardized, providing an objective and measurable evaluation basis for scientific research management.

[0056] In some embodiments, extracting the keywords of the target scientific research data includes:

[0057] Perform word segmentation on the target scientific research data and delete the stop words in the word segmentation result to obtain a vocabulary set of the target scientific research data;

[0058] Specifically, word segmentation is the process of decomposing a continuous text string into meaningful words or vocabulary. Usually, sentences are segmented into words according to certain rules, such as forward maximum matching, reverse maximum matching, etc.; or statistical information in a large corpus, such as word frequency, co-occurrence frequency, etc., is used to predict and judge the word boundaries; or natural language processing techniques are applied, combined with knowledge of grammar, semantics, etc., for word segmentation. Stop words usually refer to words that frequently appear in the text but do not make a substantial contribution to conveying the main meaning, such as "of", "is", "in", etc. Deleting stop words can reduce the noise in the data set, improve the efficiency of subsequent processing, and the accuracy of keyword extraction. Usually, a predefined stop word list is used for filtering, and these lists can be customized according to the specific language and application scenario; or by analyzing the distribution of vocabulary in the corpus, high-frequency and low-information-content vocabulary are automatically identified. After word segmentation and deleting stop words, the obtained is a cleaned vocabulary set, which is more representative and informative, providing a basis for the next step of keyword extraction and term frequency-inverse document frequency (TF-IDF) calculation.

[0059] Determine the term frequency-inverse document frequency of each vocabulary in the vocabulary set. In response to determining that the term frequency-inverse document frequency of the vocabulary is greater than or equal to the preset term frequency-inverse document frequency, determine that the vocabulary is a keyword of the target scientific research data.

[0060] In specific implementation, the term frequency-inverse document frequency (TF-IDF) is a method used to evaluate the importance of a word to a document set or one of the documents in a corpus. It helps identify the keywords of the document by reducing the influence of common words and increasing the weight of important but uncommon words, so as to help extract the most representative and informative keywords from a large number of scientific research documents. Each word in the vocabulary set will have a corresponding term frequency inverse document frequency to evaluate the importance of the word in the document set. If it is determined that the term frequency inverse document frequency of the word is greater than or equal to the preset term frequency inverse document frequency, the word is determined to be a keyword of the target scientific research data. The preset term frequency inverse document frequency can be adjusted according to the specific application scenario and needs. In the analysis of scientific research documents, it may be necessary to select a higher preset term frequency inverse document frequency to ensure that the extracted keywords are highly professional and have information value.

[0061] In this embodiment, the word frequency inverse document frequency can effectively distinguish important words from common but unimportant words in the document, and the influence of common words is reduced by increasing the weight of rare words, thereby helping to identify truly critical words and improving the accuracy and relevance of keyword extraction. Accurate keyword extraction can greatly improve the efficiency and quality of information retrieval. In scientific research data analysis, the ability to quickly identify core concepts and keywords from a large amount of literature helps researchers quickly locate relevant research and materials, saving time and improving research efficiency.

[0062] In some embodiments, after extracting the keywords of the target scientific research data, the method further includes:

[0063] determining the number of the keywords;

[0064] During specific implementation, counting the total number of extracted keywords and adjusting the number of keywords according to actual conditions is the key to ensuring the quality of text analysis. It not only helps to improve the efficiency and effectiveness of text processing, but also is the basis for achieving accurate information services.

[0065] In response to determining that the number of the keywords is less than or equal to a first preset number, performing synonym expansion on the keywords;

[0066] In specific implementation, when the number of keywords is less than or equal to the first preset number (exemplarily, the first preset number can be set to 30% of the vocabulary set), it indicates that the number of keywords cannot fully represent the core content of the target scientific research data, and synonym expansion is performed to enhance the semantic coverage of keywords and improve the representativeness of keywords. Synonym expansion can help fill the semantic gaps that may exist in keywords, ensure that key information is not omitted, and thus improve the accuracy and depth of text analysis.

[0067] In response to determining that the number of the keywords is greater than or equal to a second preset number, the keywords are screened.

[0068] In specific implementation, when the number of keywords is greater than or equal to the second preset number (exemplarily, the second preset number can be set to 60% of the vocabulary set), it indicates that there are too many keywords, which may cause information redundancy and reduce the efficiency and accuracy of text analysis. The purpose of screening the keywords is to eliminate those words that are not important enough or have low correlation with the target scientific research data, and retain the most representative and information-valuable keywords.

[0069] In this embodiment, by expanding synonyms, the semantic coverage of keywords can be supplemented and enriched to ensure that key information is not missed, thereby enhancing the accuracy and depth of text analysis; screening of excessive keywords and eliminating less important words helps retain the most representative and information-valuable keywords. This not only improves the efficiency of text processing, but also ensures the reliability and effectiveness of the analysis results, avoiding information redundancy and processing burden caused by too many keywords, and also avoiding missing important information due to insufficient keywords.

[0070] In some embodiments, the screening of the keywords includes:

[0071] Determine the text vectors of the keywords, and determine the cosine similarity of any two keywords based on the text vectors of the two keywords;

[0072] In specific implementation, the text vectors of keywords are usually determined using pre-trained word embedding models such as Word2Vec, GloVe, or FastText to convert each keyword into a vector of fixed dimension. These vectors capture the semantic features of the vocabulary, so that semantically similar words are also close in distance in the vector space. Cosine similarity measures the similarity of two vectors in direction, and its value ranges from -1 to 1. A cosine value of 1 means that the directions of the two vectors are exactly the same, 0 means that the two are orthogonal, and -1 means that the two directions are completely opposite. By calculating the cosine similarity of the text vectors of any two keywords, it can be determined whether the two keywords are too close in semantics.

[0073] In response to determining that the cosine similarity is greater than or equal to a preset cosine similarity, the keyword with the smallest term frequency inverse document frequency among the two keywords is deleted.

[0074] In a specific implementation, if the cosine similarity of two keywords is greater than or equal to a preset cosine similarity (for example, the preset cosine similarity can be set to 0.6), it indicates that the two keywords are very similar in semantics and may cause keyword redundancy. In this case, the keyword with the smallest word frequency inverse document frequency among the two keywords is deleted to effectively optimize the keyword set, reduce redundancy, and improve the quality and efficiency of text analysis.

[0075] In this embodiment, deleting keywords that are too similar in semantics can significantly reduce the redundancy in the keyword set, which not only improves the quality of the keywords, but also enables each retained keyword to independently represent a unique concept or theme, thereby enhancing the information value of the keywords. The streamlined keywords can improve the overall quality and efficiency of scientific research text analysis.

[0076] In some embodiments, extracting the relationship network between the target researcher and other researchers includes:

[0077] Perform entity recognition on the target scientific research data to obtain multiple entities and semantic relationships between multiple entities;

[0078] In specific implementation, entity recognition is a task in natural language processing (NLP), which aims to automatically identify entities with specific meanings from text, such as names of people, organizations, places, etc. In scientific research data analysis, entities usually refer to researchers, research institutions, research projects, research fields, publications, etc. Entities are usually identified using predefined rules; or models are trained using labeled training data to automatically identify entities in text; and pre-trained models such as BERT and RoBERTa are used for entity recognition, which can learn rich language features using a large amount of unlabeled data. The recognition of semantic relationships between entities aims to determine the specific connections between two or more entities, such as collaboration, citations, affiliations, etc. In scientific research data, it helps to reveal the collaboration network of researchers, the intersection of research fields, and the path of knowledge dissemination.

[0079] All scientific researchers are determined from the multiple entities, and a relationship network between the target scientific researcher and other scientific researchers among all scientific researchers except the target scientific researcher is constructed according to the semantic relationships between the multiple entities.

[0080] In specific implementation, all scientific researchers are determined from the multiple entities obtained, and a relationship network between the target scientific researcher and other scientific researchers among all scientific researchers except the target scientific researcher is constructed based on the semantic relationship between the multiple entities, wherein nodes represent scientific researchers, edges represent the relationship between them, and the type and strength of the relationship (such as the number of collaborations) can be used to define the weight of the edge.

[0081] In this embodiment, the relationship network between the target researcher and other researchers except the target researcher among all researchers can clearly show the cooperative relationship between researchers, which helps to identify key figures and core teams in the scientific research field, as well as the cooperation mode between them. The relationship network provides decision support for scientific research managers, helping them to identify the structure and dynamics of scientific research teams, evaluate the cooperation potential and risks of scientific research projects, and formulate scientific research policies and strategies.

[0082] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0083] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0084] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a device for constructing a portrait of a scientific researcher.

[0085] refer to Figure 4 , the scientific researcher portrait building device comprises:

[0086] A preprocessing module 701 is configured to obtain the scientific research data of the target scientific researcher and preprocess the scientific research data to obtain the target scientific research data in text format;

[0087] An extraction module 702, which is configured to extract keywords of the target scientific research data and a relationship network between the target scientific researcher and other scientific researchers;

[0088] A scoring module 703 is configured to determine a research score of a target researcher based on the target research data;

[0089] The portrait construction module 704 is configured to construct a portrait of the target researcher based on the keywords, the relationship network between the target researcher and other researchers, and the research score of the target researcher.

[0090] Furthermore, the scoring module 703 is specifically used for:

[0091] Obtaining multiple scientific research achievement data from the target scientific research data, and determining the number of participants in each scientific research achievement and the ranking of the target scientific researcher in the scientific research achievement based on the multiple scientific research achievement data;

[0092] Determine the score of the scientific research results based on the number of participants in the scientific research results and the ranking of the target researchers in the said scientific research results;

[0093] The scores of all scientific research results are weighted and summed according to the preset scoring weights to obtain the scientific research score of the target researcher.

[0094] Furthermore, the scoring module 703 is also specifically used for:

[0095] Determine the highest and lowest scores for scientific research achievements based on the type of scientific research achievements and the preset type score relationship;

[0096] In response to determining that the ranking is before the first preset ranking, determining the highest score as the score of the scientific research achievement;

[0097] In response to determining that the ranking is after the second preset ranking, determining the lowest score as the score of the scientific research achievement;

[0098] In response to determining that the ranking is between the first preset ranking and the second preset ranking, the score of the scientific research achievement is determined according to the number of participants, ranking, highest score and lowest score of the scientific research achievement, wherein the score of the scientific research achievement is inversely proportional to the ranking.

[0099] Furthermore, the extraction module 702 is specifically used for:

[0100] Performing word segmentation on the target scientific research data and deleting stop words in the word segmentation results to obtain a vocabulary set of the target scientific research data;

[0101] The term frequency inverse document frequency of each word in the vocabulary set is determined, and in response to determining that the term frequency inverse document frequency of the word is greater than or equal to a preset term frequency inverse document frequency, the word is determined to be a keyword of the target scientific research data.

[0102] Furthermore, the extraction module 702 is further specifically used for:

[0103] determining the number of the keywords;

[0104] In response to determining that the number of the keywords is less than or equal to a first preset number, performing synonym expansion on the keywords;

[0105] In response to determining that the number of the keywords is greater than or equal to a second preset number, the keywords are screened.

[0106] Furthermore, the extraction module 702 is further specifically used for:

[0107] Determine the text vectors of the keywords, and determine the cosine similarity of any two keywords based on the text vectors of the two keywords;

[0108] In response to determining that the cosine similarity is greater than or equal to a preset cosine similarity, the keyword with the smallest term frequency inverse document frequency among the two keywords is deleted.

[0109] Furthermore, the extraction module 702 is further specifically used for:

[0110] Perform entity recognition on the target scientific research data to obtain multiple entities and semantic relationships between multiple entities;

[0111] All scientific researchers are determined from the multiple entities, and a relationship network between the target scientific researcher and other scientific researchers among all scientific researchers except the target scientific researcher is constructed according to the semantic relationships between the multiple entities.

[0112] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0113] The device of the above-mentioned embodiment is used to implement the corresponding method for constructing a portrait of a scientific researcher in any of the aforementioned embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0114] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for constructing a portrait of a scientific researcher described in any of the above embodiments is implemented.

[0115] Figure 5 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0116] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0117] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0118] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0119] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0120] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0121] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0122] The electronic device of the above-mentioned embodiment is used to implement the corresponding scientific researcher portrait construction method in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0123] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method for constructing a portrait of a scientific researcher as described in any of the above embodiments.

[0124] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0125] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the method for constructing a portrait of a scientific researcher as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0126] Based on the same concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer executes the method described in any of the above embodiments, which has the beneficial effects of the corresponding method embodiments and will not be repeated here.

[0127] It is understandable that before using the technical solutions of each embodiment of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0128] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0129] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0130] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0131] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0132] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0133] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0134] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the protection scope of the present application.

Claims

1. A method for constructing a portrait of a scientific researcher, characterized in that: include: Acquire the scientific research data of the target scientific researcher, and pre-process the scientific research data to obtain the target scientific research data in text format; Extracting keywords of the target scientific research data and the relationship network between the target scientific researcher and other scientific researchers; Determine a research score of a target researcher based on the target research data; A profile of the target researcher is constructed based on the keywords, the relationship network between the target researcher and other researchers, and the research score of the target researcher.

2. The method for constructing a portrait of a scientific researcher according to claim 1, characterized in that: Determining the scientific research score of the target scientific researcher according to the target scientific research data includes: Obtaining multiple scientific research achievement data from the target scientific research data, and determining the number of participants in each scientific research achievement and the ranking of the target scientific researcher in the scientific research achievement based on the multiple scientific research achievement data; Determine the score of the scientific research results based on the number of participants in the scientific research results and the ranking of the target researchers in the said scientific research results; The scores of all scientific research results are weighted and summed according to the preset scoring weights to obtain the scientific research score of the target researcher.

3. The method for constructing a portrait of a scientific researcher according to claim 2, characterized in that: The score of the scientific research results is determined based on the number of participants in the scientific research results and the ranking of the target researchers in the scientific research results, including: Determine the highest and lowest scores for scientific research achievements based on the type of scientific research achievements and the preset type score relationship; In response to determining that the ranking is before the first preset ranking, determining the highest score as the score of the scientific research achievement; In response to determining that the ranking is after the second preset ranking, determining the lowest score as the score of the scientific research achievement; In response to determining that the ranking is between the first preset ranking and the second preset ranking, the score of the scientific research achievement is determined according to the number of participants, ranking, highest score and lowest score of the scientific research achievement, wherein the score of the scientific research achievement is inversely proportional to the ranking.

4. The method for constructing a portrait of a scientific researcher according to claim 1, characterized in that: The step of extracting keywords of the target scientific research data includes: Performing word segmentation on the target scientific research data and deleting stop words in the word segmentation results to obtain a vocabulary set of the target scientific research data; The term frequency inverse document frequency of each word in the vocabulary set is determined, and in response to determining that the term frequency inverse document frequency of the word is greater than or equal to a preset term frequency inverse document frequency, the word is determined to be a keyword of the target scientific research data.

5. The method for constructing a portrait of a scientific researcher according to claim 4, characterized in that: After extracting the keywords of the target scientific research data, it also includes: determining the number of the keywords; In response to determining that the number of the keywords is less than or equal to a first preset number, performing synonym expansion on the keywords; In response to determining that the number of the keywords is greater than or equal to a second preset number, the keywords are screened.

6. The method for constructing a portrait of a scientific researcher according to claim 5, characterized in that: The screening of the keywords includes: Determine the text vectors of the keywords, and determine the cosine similarity of any two keywords based on the text vectors of the two keywords; In response to determining that the cosine similarity is greater than or equal to a preset cosine similarity, the keyword with the smallest term frequency inverse document frequency among the two keywords is deleted.

7. The method for constructing a portrait of a scientific researcher according to claim 1, characterized in that: The extracting of the relationship network between the target researcher and other researchers comprises: Perform entity recognition on the target scientific research data to obtain multiple entities and semantic relationships between multiple entities; All scientific researchers are determined from the multiple entities, and a relationship network between the target scientific researcher and other scientific researchers among all scientific researchers except the target scientific researcher is constructed according to the semantic relationships between the multiple entities.

8. A device for constructing a portrait of a scientific researcher, characterized in that: include: A preprocessing module is configured to obtain the scientific research data of the target scientific researcher and preprocess the scientific research data to obtain the target scientific research data in text format; An extraction module, which is configured to extract keywords of the target scientific research data and a relationship network between the target scientific researcher and other scientific researchers; A scoring module, configured to determine a scientific research score of a target scientific researcher based on the target scientific research data; A portrait construction module is configured to construct a portrait of the target researcher based on the keywords, the relationship network between the target researcher and other researchers, and the research score of the target researcher.

9. An electronic device 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 program, the method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images