A method, apparatus, and storage medium for recommending research collaboration institutions based on technology topic identification.

Abstract

This invention belongs to the field of data mining technology, specifically relating to a method, apparatus, and storage medium for recommending research collaborating institutions based on technology topic identification. The method includes: first, obtaining the scope of research and development activities of the target research institution; generating topic classification terms based on the scope of research and development activities; then, labeling the cutting-edge technologies corresponding to the literature data based on the literature dataset generated by retrieving the topic classification terms; second, extracting data information of the innovation entities engaged in the cutting-edge technologies to establish an innovation entity dataset; and finally, determining the collaborating institutions of the target research institution by calculating the recommendation scores of the innovation entities in the innovation entity dataset. The method provided in this application allows users to optimize the recommendation ranking according to their needs to select collaborating institutions.

Description

Technical Field

[0001] This invention belongs to the field of data mining technology, and more specifically, relates to a method, apparatus, and storage medium for recommending research collaboration institutions based on technology topic identification. Background Technology

[0002] With continuous social development and progress, open innovation has become a hot topic, and collaborative innovation has become the optimal choice for innovation entities to achieve resource complementarity, improve innovation efficiency, and reduce new product development costs. Enterprises, universities, research institutes, government agencies, and social organizations participate in collaborative innovation, gradually forming innovation cooperation networks with organizational forms such as industry-university-research cooperation, university-enterprise cooperation, industry alliance cooperation, and research institution cooperation. However, due to the scarcity and finiteness of resources, finding partner institutions with similar research fields and a willingness to cooperate is becoming increasingly difficult.

[0003] Current methods for recommending partners include those based on the similarity of future common neighbors. This method calculates the similarity between the node to be recommended and the node to be examined, and all nodes including the node to be recommended, the node to be examined, and future common neighbors, based on the connections between enterprises in the supply chain network. This yields a final cooperation score between the node to be recommended and the node to be examined, aiming to improve the accuracy of the recommendation results. However, supply chain networks are formed during product production and distribution, and network nodes include raw material suppliers, manufacturers, distributors, retailers, and consumers. Such networks focus more on upstream and downstream relationships between enterprises than on collaborative innovation. Therefore, they cannot be used to find innovative entities with strong R&D capabilities and high levels of expertise. Other methods include recommendation systems and methods based on patent data for recommending partner institutions. This method, based on collaborative filtering, incorporates inverse distance weights to optimize the recommendation ranking, effectively improving the accuracy of partner institution recommendations. Recommendation methods based on candidate sets of patent text similarity can better uncover the needs of target enterprises; however, patent data, as a single data source, has limitations and cannot simultaneously consider cutting-edge science and technology. Furthermore, this method does not consider the cooperation intentions and R&D activity of candidate institutions, requiring further screening of the selected institutions.

[0004] In view of this, the present invention is proposed. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a method for recommending scientific research cooperation institutions based on technical topic identification, so as to make it more convenient for target scientific research institutions to select cooperation institutions.

[0006] To address the aforementioned technical problems, the basic concept of the technical solution adopted by this invention is as follows: According to a first aspect of the embodiments of this invention, a method for recommending research cooperation institutions based on technology topic identification is provided. The method includes: obtaining the scope of research and development activities of a target research institution; generating topic classification terms based on the scope of research and development activities; labeling the cutting-edge technologies corresponding to the literature data based on the literature dataset generated by retrieving the topic classification terms; extracting data information of innovation entities engaged in the cutting-edge technologies and establishing an innovation entity dataset; and determining the cooperation institutions of the target research institution by calculating the recommendation scores of the innovation entities in the innovation entity dataset.

[0007] Optionally, the method for generating topic classification terms based on the scope of R&D activities includes: generating a technology decomposition table based on the obtained scope of R&D activities of the target research institution, wherein the technology decomposition table includes at least a first technology branch and a second technology branch; and determining the topic classification terms according to the branches of the technology decomposition table.

[0008] Optionally, the method for labeling cutting-edge technologies corresponding to the literature data includes: statistically analyzing the proportion of technical topic words in the literature dataset to obtain a first word frequency of the technical topic words, wherein the technical topic words include the topic classification words; determining high-frequency technical topic words by comparing the first frequency with the frequency threshold according to a preset frequency threshold; constructing a high-frequency technical topic word co-occurrence network based on the co-occurrence relationship of the high-frequency technical topic words, and summarizing the characteristics of high-frequency technical topic word clusters; identifying high-frequency technical topic words in the same word cluster as a cutting-edge technology topic to form the cutting-edge technology topic list; calculating the proportion of the cutting-edge technology topics in the cutting-edge technology topic list in the literature dataset according to the TF-IDF algorithm to obtain a second word frequency of the cutting-edge technology topic; and labeling the cutting-edge technologies corresponding to the literature data based on the second word frequency.

[0009] Optionally, the method for establishing the innovation subject dataset includes: extracting innovation subject information based on the labeling of the cutting-edge technology, wherein the innovation subject information includes at least: scope information of the innovation subject, field information of the innovation subject dataset, evaluation index information of the innovation subject, etc.

[0010] Optionally, the method for determining the collaborating institutions of the target research institution includes: obtaining pre-set evaluation index weights for the innovation entity; calculating a recommendation score for the innovation entity based on the index weights; sorting the recommendation scores in descending order to obtain a list of collaborating institutions, and determining the collaborating institutions of the target research institution.

[0011] Optionally, the method for determining the evaluation indicators of the innovation entity includes: calculating the theoretical research indicator Ti of the innovation entity's participation in the target frontier technology topic based on the number of academic papers produced by the innovation entity; calculating the applied research indicator Ai of the innovation entity's participation in the target frontier technology topic based on the number of patent applications of the innovation entity; calculating the R&D activity indicator Ri of the innovation entity's participation in the target frontier technology topic based on the growth rate of the innovation entity's scientific and technological literature output; calculating the cooperation activity indicator Ci of the innovation entity's participation in the target frontier technology topic based on the number of collaborating institutions of the innovation entity; and normalizing the theoretical research indicator, the applied research indicator, the R&D activity indicator, and the cooperation activity indicator to determine the normalized values ​​of the evaluation indicators.

[0012] Optionally, the method for calculating the recommendation score of the innovation entity includes: calculating the recommendation score of the innovation entity according to the following formula:

[0013]

[0014] in, These are the weights of indicators in theoretical research; These are the weights of applied research indicators; It is the weight of the R&D activity index; 1 is the weight of the collaboration activity index; Ti is the theoretical research index; Ai is the applied research index; Ri is the R&D activity index; Ci is the collaboration activity index; i is the target frontier technology theme.

[0015] According to a second aspect of the present invention, a research collaboration institution recommendation device based on technology topic identification is provided. The device includes: an acquisition device configured to acquire the research and development activity scope of a target research institution; a generation device configured to generate topic classification terms based on the research and development activity scope; a labeling device configured to label cutting-edge technologies corresponding to literature data based on a literature dataset generated by retrieving the topic classification terms; an establishment device configured to extract data information of innovation entities engaged in the cutting-edge technologies and establish an innovation entity dataset; and a determination device configured to determine the collaboration institutions of the target research institution by calculating the recommendation scores of the innovation entities in the innovation entity dataset.

[0016] Optionally, the generating apparatus is used to generate a method for generating topic classification terms based on the scope of the R&D activities, comprising: generating a technology decomposition table based on the obtained scope of the target research institution's R&D activities, wherein the technology decomposition table includes at least a first technology branch and a second technology branch; and determining the topic classification terms according to the branches of the technology decomposition table.

[0017] Optionally, the labeling device for labeling cutting-edge technologies corresponding to literature data includes: statistically analyzing the proportion of technical topic words in the literature dataset to obtain a first word frequency of the technical topic words, wherein the technical topic words include the topic classification words; determining high-frequency technical topic words by comparing the first frequency with the frequency threshold according to a preset frequency threshold; constructing a high-frequency technical topic word co-occurrence network based on the co-occurrence relationship of the high-frequency technical topic words, and summarizing the characteristics of high-frequency technical topic word clusters; identifying high-frequency technical topic words in the same word cluster as a cutting-edge technology topic to form the cutting-edge technology topic list; calculating the proportion of the cutting-edge technology topics in the cutting-edge technology topic list in the literature dataset according to the TF-IDF algorithm to obtain a second word frequency of the cutting-edge technology topic; and labeling the cutting-edge technologies corresponding to the literature data based on the second word frequency.

[0018] Optionally, the method for establishing an innovation subject dataset using the establishment device includes: extracting innovation subject information based on the labeling of the cutting-edge technology, wherein the innovation subject information includes at least: scope information of the innovation subject, field information of the innovation subject dataset, evaluation index information of the innovation subject, etc.

[0019] Optionally, the method for determining the collaborating institutions of the target research institution by the determining device includes: obtaining pre-set evaluation index weights for the innovation entity; calculating a recommendation score for the innovation entity based on the index weights; sorting the recommendation scores in descending order to obtain a list of collaborating institutions, and determining the collaborating institutions of the target research institution.

[0020] Optionally, the determining device is used for a method to determine the evaluation indicators of the innovation entity, including: calculating a theoretical research indicator Ti for the innovation entity's participation in the target frontier technology topic based on the number of academic papers produced by the innovation entity; calculating an applied research indicator Ai for the innovation entity's participation in the target frontier technology topic based on the number of patent applications of the innovation entity; calculating a research and development activity indicator Ri for the innovation entity's participation in the target frontier technology topic based on the growth rate of the innovation entity's scientific and technological literature output; calculating a cooperation activity indicator Ci for the innovation entity's participation in the target frontier technology topic based on the number of collaborating institutions of the innovation entity; and normalizing the theoretical research indicator, the applied research indicator, the research and development activity indicator, and the cooperation activity indicator to determine the normalized value of the evaluation indicator.

[0021] Optionally, the method by which the determining device calculates the recommendation score of the innovation subject includes: calculating the recommendation score of the innovation subject according to the following formula:

[0022]

[0023] in, These are the weights of indicators in theoretical research; These are the weights of applied research indicators; It is the weight of the R&D activity index; 1 is the weight of the collaboration activity index; Ti is the theoretical research index; Ai is the applied research index; Ri is the R&D activity index; Ci is the collaboration activity index; i is the target frontier technology theme.

[0024] According to a third aspect of the embodiments of this application, a computer-readable storage medium is provided, on which computer program instructions are stored, which, when executed by a processor, are used to implement a method for recommending scientific research cooperation institutions based on technical topic identification provided by the first aspect of this disclosure or any embodiment of the first aspect.

[0025] According to a fourth aspect of the embodiments of this application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute, through the computer program, a method for recommending research cooperation institutions based on technical topic identification provided by the first aspect of this disclosure or any embodiment of the first aspect.

[0026] After adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art: First, the scope of R&D activities of the target research institution is obtained; based on the scope of R&D activities, topic classification terms are generated; then, based on the literature dataset generated by retrieving the topic classification terms, the cutting-edge technologies corresponding to the literature data are marked; second, data information of the innovation entities engaged in the cutting-edge technologies is extracted to establish an innovation entity dataset; finally, by calculating the recommendation score of the innovation entities in the innovation entity dataset, the cooperative institutions of the target research institution are determined. The method provided in this application, on the one hand, is based on the scope of R&D activities of the target research institution, which can ensure that the finally determined cooperative institutions are similar to the research fields of the target research institution; on the other hand, by generating a literature dataset, innovation entities can be extracted from multiple perspectives in a comprehensive manner, making the establishment of the innovation entity dataset more objective; furthermore, by quantifying the innovation entities and calculating the recommendation score, users can optimize the recommendation ranking according to their needs to select cooperative institutions.

[0027] The specific embodiments of the present invention will now be described in further detail with reference to the accompanying drawings. Attached Figure Description

[0028] The accompanying drawings, as part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments and descriptions of the invention are used to explain the invention, but do not constitute an undue limitation of the invention. Obviously, the drawings described below are merely some embodiments, and those skilled in the art can obtain other drawings based on these drawings without creative effort. In the drawings:

[0029] Figure 1 This is a flowchart of a method for recommending research cooperation institutions according to an embodiment of the present invention;

[0030] Figure 2 This is a flowchart of a method for recommending cooperative institutions of the X Institute according to an embodiment of the present invention;

[0031] Figure 3 This is a block diagram of a scientific research cooperation institution recommendation device according to an embodiment of the present invention;

[0032] Figure 4 This is a block diagram of an electronic device according to an embodiment of the present invention.

[0033] It should be noted that these accompanying drawings and textual descriptions are not intended to limit the scope of the invention in any way, but rather to illustrate the concept of the invention to those skilled in the art by referring to specific embodiments. Detailed Implementation

[0034] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0035] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0036] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0037] Example 1

[0038] Figure 1 This is a flowchart of a method for recommending research cooperation institutions according to an embodiment of the present invention. Figure 1 As shown, it includes steps S101-S105.

[0039] In step S101, the scope of research and development activities of the target research institution is obtained.

[0040] In this embodiment, the scope of research and development activities of the target research institution refers to the fields involved, including but not limited to the scope of industries engaged in, the industry classification, related disciplines, and organizational structure.

[0041] In step S102, topic classification terms are generated based on the scope of the R&D activities.

[0042] In this embodiment, the method for generating topic classification terms based on the scope of R&D activities includes: generating a technology decomposition table based on the obtained scope of R&D activities of the target research institution, wherein the technology decomposition table includes at least a first technology branch and a second technology branch; and determining the topic classification terms according to the branches of the technology decomposition table.

[0043] In this embodiment, the technology decomposition table is a division of topic classification terms. The technology decomposition table includes a hierarchical structure, that is, each first-level technology branch is decomposed into at least second-level technology branches. The topic classification terms correspond to each level of technology branch, and each technology branch contains at least one word.

[0044] Optionally, generating the technology decomposition table includes: using a word similarity calculation method to determine words related to the research and development activities of the target research institution, forming a topic classification word library; and classifying the words in the topic classification word library according to their text type and position to form a technology decomposition table. In this embodiment, commonly used word similarity calculation methods, such as methods based on world knowledge or a certain classification system and methods based on statistical context vector space models, can be used to generate the technology decomposition table.

[0045] In step S103, based on the literature dataset generated by retrieving the topic classification terms, the cutting-edge technologies corresponding to the literature data are labeled.

[0046] In this embodiment, the method for labeling the cutting-edge technologies corresponding to the literature data in the literature dataset includes: filtering scientific and technological literature in the literature dataset; labeling the literature data derived from the scientific and technological literature, wherein the types and sources of the scientific and technological literature data depend on the data resources accessed by the system, including but not limited to: science and technology policies, project texts, academic papers, conference papers, patent documents, research reports, independent web pages, electronic documents, etc.

[0047] The method for labeling cutting-edge technologies corresponding to literature data based on the literature dataset generated by retrieving the topic classification terms includes: calculating the proportion of technical topic terms in the literature dataset to obtain the first word frequency of the technical topic terms, wherein the technical topic terms include the topic classification terms; determining high-frequency technical topic terms by comparing the first frequency with the frequency threshold according to a preset frequency threshold; constructing a high-frequency technical topic term co-occurrence network based on the co-occurrence relationship of the high-frequency technical topic terms and summarizing the characteristics of high-frequency technical topic term clusters; identifying high-frequency technical topic terms of the same term cluster as a cutting-edge technology topic to form a list of target research institutions whose R&D activities include the cutting-edge technology topic; calculating the proportion of the cutting-edge technology topic in the list of cutting-edge technology topics in the literature dataset according to the TF-IDF algorithm to obtain the second word frequency of the cutting-edge technology topic; and labeling the cutting-edge technologies corresponding to the literature data based on the second word frequency.

[0048] In this embodiment, the technical subject terms include, but are not limited to: subject classification terms, words marked in the titles, keywords, and abstracts of scientific and technological documents.

[0049] Specifically, after completing the statistics of technical topic terms in the literature dataset, the occurrence frequency of each technical topic term is determined, i.e., the first term frequency; according to the preset frequency threshold, when the first term frequency of the technical topic term is greater than the frequency threshold, the technical topic term is determined to be a high-frequency technical topic term.

[0050] A co-occurrence network is constructed based on high-frequency technical keywords and their co-occurrence relationships. The co-occurrence relationships determine the relationship between the high-frequency technical keyword and other technical keywords in the document dataset. The co-occurrence network is then analyzed using a network community partitioning algorithm to summarize the characteristics of high-frequency word clusters within it. This network community partitioning algorithm can explain the correlations between information resources. In this embodiment, the summary of high-frequency word cluster characteristics can be achieved using any method of the network community partitioning algorithm.

[0051] High-frequency technical terms within the same term cluster are grouped as a single technical topic. A list of cutting-edge technical topics is determined, using communities as boundaries. The proportion of each cutting-edge technical topic in the corresponding scientific literature is calculated using the TF-IDF algorithm, and this proportion is taken as the term frequency of that cutting-edge technology. The cutting-edge technologies corresponding to the literature data are identified based on their term frequencies and then tagged. When multiple cutting-edge technologies correspond to a single piece of literature data, the cutting-edge technology tagging of that literature data includes all corresponding cutting-edge technical topics; that is, one piece of literature data corresponds to zero, one, or more cutting-edge technical topics.

[0052] TF-IDF (term frequency–inverse document frequency) is a commonly used weighting technique in information retrieval and text mining. TF-IDF is a statistical method used to evaluate the importance of a word to a document within a document set or corpus. A word's importance increases proportionally to its frequency of occurrence in a document, but decreases inversely proportionally to its frequency of occurrence in the corpus. Term frequency (TF) represents the frequency of a term (keyword) in the text. This number is usually normalized (generally by dividing the term frequency by the total number of words in the document) to prevent bias towards longer documents. Inverse document frequency (IDF) refers to the IDF of a specific word, which can be obtained by dividing the total number of documents by the number of documents containing that word, and then taking the logarithm of the quotient. The fewer documents containing term t, the higher the IDF, indicating that the term has good class distinguishing ability.

[0053] In step S104, data information of the innovation entities engaged in the cutting-edge technology is extracted to establish an innovation entity dataset.

[0054] In this embodiment, the method for establishing an innovation subject dataset includes: extracting innovation subject information based on the labeling of the cutting-edge technology, wherein the innovation subject information includes at least: scope information of the innovation subject, field information of the innovation subject dataset, evaluation index information of the innovation subject, etc.

[0055] In this embodiment, the extracted innovation entity information includes the scope information of the innovation entity, the field information of the innovation entity dataset, and the evaluation index information of the innovation entity. The scope information of the innovation entity includes at least the author and institution information of the scientific and technological literature. The field information of the innovation entity dataset includes at least the innovation entity name, innovation entity ID, innovation entity address, country of origin, city of origin, scholar ID, scholar email, document ID, number of collaborating entities, document type marker, publication date, and cutting-edge technology marker. The evaluation index information of the innovation entity includes at least the number of academic papers produced by the innovation entity, the number of patent applications, the growth rate of scientific and technological literature output, and the number of collaborating institutions. Based on the innovation entity information, an innovation entity dataset is established.

[0056] In step S105, the cooperative institutions of the target research institution are determined by calculating the recommendation scores of the innovation subjects in the innovation subject dataset.

[0057] In this embodiment, the method for determining the collaborating institutions of the target research institution includes: obtaining pre-set evaluation index weights for the innovation entity; calculating a recommendation score for the innovation entity based on the index weights; sorting the recommendation scores in descending order to obtain a list of collaborating institutions, and determining the collaborating institutions of the target research institution.

[0058] The method for determining the evaluation indicators of the innovation entity includes: calculating the theoretical research indicator Ti of the innovation entity's participation in the target frontier technology topic based on the number of academic papers produced by the innovation entity; calculating the applied research indicator Ai of the innovation entity's participation in the target frontier technology topic based on the number of patent applications of the innovation entity; calculating the R&D activity indicator Ri of the innovation entity's participation in the target frontier technology topic based on the growth rate of the innovation entity's scientific and technological literature output; calculating the cooperation activity indicator Ci of the innovation entity's participation in the target frontier technology topic based on the number of collaborating institutions of the innovation entity; and normalizing the theoretical research indicator, the applied research indicator, the R&D activity indicator, and the cooperation activity indicator to determine the normalized values ​​of the evaluation indicators.

[0059] In this embodiment, based on the number of academic papers produced by the innovation entity, the theoretical research index (Ti) of the innovation entity in the specified cutting-edge technology topic can be obtained by calculating the proportion of academic papers related to the specified cutting-edge technology topic produced by the innovation entity; based on the number of patent applications of the innovation entity, the applied research index (Ai) of the innovation entity in the specified cutting-edge technology topic can be obtained by calculating the proportion of patent applications related to the specified cutting-edge technology topic submitted by the innovation entity; based on the growth rate of scientific and technological literature output of the innovation entity, the R&D activity index (Ri) of the innovation entity in the specified cutting-edge technology topic can be obtained by calculating the average annual growth rate of scientific and technological literature related to the specified cutting-edge technology topic produced by the innovation entity; based on the number of collaborating institutions of the innovation entity, the collaboration activity index (Ci) of the innovation entity in the specified cutting-edge technology topic can be obtained by statistically analyzing the number of collaborations between the innovation entity and other entities in the specified cutting-edge technology topic.

[0060] The methods for normalizing the evaluation indicators include:

[0061] Normalization is performed according to the following formula:

[0062]

[0063] Where, x max x represents the maximum value of the evaluation indicator data. mix is the minimum value of the evaluation indicator data, and is the normalized value of the evaluation indicator data.

[0064] In this embodiment, the method for calculating the recommendation score of the innovation subject includes:

[0065] The recommendation score for the innovation entity is calculated using the following formula:

[0066]

[0067] in, These are the weights of indicators in theoretical research; These are the weights of applied research indicators; It is the weight of the R&D activity index; 1 is the weight of the collaboration activity index; Ti is the theoretical research index; Ai is the applied research index; Ri is the R&D activity index; Ci is the collaboration activity index; i is the target frontier technology theme.

[0068] This application, on the one hand, bases its decision on the scope of research and development activities of the target research institution, ensuring that the final selected collaborating institution has a similar research field to the target research institution; on the other hand, by generating a literature dataset, it can extract the innovation subject from multiple perspectives in a comprehensive manner, making the establishment of the innovation subject dataset more objective; furthermore, by quantifying the innovation theme and calculating recommendation scores, it can enable users to optimize the recommendation ranking according to their needs and select collaborating institutions.

[0069] Figure 2 This is a flowchart of a method for recommending collaborating institutions of the X Institute according to an embodiment of the present invention, such as... Figure 2 As shown, this example illustrates a recommended partner institution for Institute X. Institute X primarily engages in research in the field of human settlements, meaning its research and development activities fall within this area.

[0070] In this embodiment, step 201 is first executed to determine the technology decomposition of the research and development activities of Institute X, resulting in a technology decomposition table. This technology decomposition table includes two levels of technology branches. The first technology branch includes: natural systems, human systems, residential systems, social systems, and supporting systems. The second technology branch includes: dividing the natural system into atmospheric environment and air pollution; dividing the human system into subjective annoyance evaluation, comfort assessment, and ecology; dividing the residential system into urban sewage and domestic waste; dividing the social system into noise, sound insulation, and sound absorption; and dividing the supporting system into indoor air and ventilation.

[0071] Then, step 202 is executed to determine relevant subject classification terms based on the discipline system of human settlements. Step 203 involves searching and downloading relevant scientific and technological documents from literature retrieval databases based on the subject classification terms. These databases include academic journal databases, patent databases, and national policy databases. Step 204 involves marking the sources of the documents in the literature dataset. Step 205 involves establishing a literature dataset. In this embodiment, the literature dataset includes 16,058 academic papers, 1,302 patents, and 15 national policies. Based on manual interpretation of the literature dataset, step 206 is executed to mark the cutting-edge technologies in the literature data.

[0072] In this embodiment, the labeling of cutting-edge technologies in literature data includes three methods: the first is manual interpretation; the second is extracting keywords as technical subject terms and calculating word frequency; and the third is extracting IPC sub-category technical subject terms and calculating word frequency.

[0073] For example, in one embodiment, cutting-edge technologies are labeled by interpreting the cutting-edge technologies in the national policy data. In this embodiment, the national policy data includes 15 cutting-edge technologies.

[0074] In another embodiment, keywords are used as technical topic terms. The frequency of each technical topic term is calculated and sorted in descending order based on frequency. A frequency threshold is set, and high-frequency technical topic terms are determined by comparing the frequency with the threshold. For example, if the frequency threshold is set to 30, 234 words are included in the high-frequency technical topic term range. A high-frequency technical topic term co-occurrence network is constructed based on the co-occurrence relationships of these terms, and community structures are defined. For example, this co-occurrence network is divided into 7 community structures, including 7 high-frequency word clusters, which represent the cutting-edge technologies in academic paper data based on the frequency of high-frequency technical topic terms, totaling 7 items.

[0075] In another embodiment, patent IPC subcategories are used as technical subject terms. The frequency of each technical subject term is calculated and they are arranged in descending order based on frequency. A frequency threshold is set, and high-frequency technical subject terms are determined by comparing the frequency with the threshold. For example, if the high-frequency threshold is set to 20, then 156 IPC subcategories are included in the high-frequency technical subject term range. A high-frequency technical subject term co-occurrence network is constructed based on the co-occurrence relationships of these high-frequency technical subject terms, and community structures are defined. For example, this co-occurrence network is divided into 8 community structures, including 8 high-frequency word clusters. These high-frequency word clusters represent the cutting-edge technologies of the patent data, totaling 8 items.

[0076] The labeled cutting-edge technologies are deduplicated to obtain the final labeled cutting-edge technologies. In this embodiment, 23 cutting-edge technologies are finally labeled from the human settlements literature data, including: outdoor sound reinforcement systems, traffic noise pollution control technology, noise monitoring and evaluation, pipeline vibration reduction and noise reduction technology, flue gas nitrogen oxide purification technology, dioxin-like air pollutant control, intelligent spray dust suppression technology, VOCs, ozone and other organic waste gas treatment, low-concentration malodorous waste gas treatment, indoor air quality improvement, synergistic control technology of air pollutants and greenhouse gases, rural domestic sewage treatment, harmless treatment and resource utilization technology of toilet waste, rural domestic waste treatment technology, beautiful countryside, urban thermal environment and thermal comfort research, urban ecology, the impact of climate change on human settlements, the impact of vegetation diversity on human settlements, intelligent management of human settlements, intelligent buildings, intelligent monitoring of human settlements, and smart urban environment and monitoring.

[0077] After the final frontier technologies are labeled, step 207 is executed to establish a frontier technology innovation subject dataset. Taking the labeling of traffic noise pollution control technology in the literature dataset as an example, in this embodiment, the literature dataset includes 338 academic literature records and 124 patents. The innovation subject data of the academic literature data and patent papers are extracted. The innovation subject data includes: extracting the author and institution information of journal articles and the patentee information of patents. After cleaning and processing the innovation subject data, the final innovation subject data information is retained. Based on the innovation subject data information, an innovation subject dataset for traffic noise pollution control technology is established.

[0078] After obtaining the innovation entity dataset, step 208 is executed to calculate the evaluation indicators of the innovation entities. In this embodiment, based on the innovation entity dataset for traffic noise pollution control technology, the evaluation indicators of the innovation entities are calculated according to the following formula:

[0079]

[0080]

[0081]

[0082] Collaboration Activity Index (Ci) = Number of papers co-published with other institutions + Number of patent applications co-filed with other institutions

[0083] In this embodiment, calculations show that the theoretical research index, applied research index, scientific research activity index, and collaborative activity index scores of the WAVES research group at Ghent University, Belgium are 0.86, 0.84, 0.60, and 0.49, respectively; while the theoretical research index, applied research index, scientific research activity index, and collaborative activity index scores of the State Key Laboratory of Traction Power at Southwest Jiaotong University, China are 0.68, 0.44, 0.57, and 0.71, respectively.

[0084] According to step 209, the weights of each evaluation indicator are set. In this embodiment, the weights of theoretical research indicators are set. Weight of applied research indicators Research activity index weight Cooperation Activity Index Weight Step 210 calculates the recommended score of the innovation entity, and step 211 rearranges the order of the innovation entities according to the recommended score, that is, the top five innovation entities are included in the list of technical cooperation institutions for traffic noise pollution control.

[0085] In this embodiment, the list of collaborating institutions is ordered as follows: WAVES Research Group, Ghent University, Belgium (recommendation score 0.70), State Key Laboratory of Traction Power, Southwest Jiaotong University, China (recommendation score 0.60), School of Intelligent Engineering, Sun Yat-sen University, China (recommendation score 0.56), Department of Building Services Engineering, Hong Kong Polytechnic University, China (recommendation score 0.55), and Faculty of Hygiene, Plovdiv Medical University, Bulgaria (recommendation score 0.47). Therefore, based on this order, Institute X can select collaborating institutions.

[0086] Example 2

[0087] Figure 3 This is a block diagram of a research cooperation institution recommendation device according to an embodiment of the present invention, such as... Figure 3 As shown, the device 300 includes an acquisition device 301, a generation device 302, a marking device 303, a creation device 304, and a determination device 305.

[0088] Acquisition device 301 is configured to acquire the scope of research and development activities of the target research institution;

[0089] The generation device 302 is configured to generate topic classification terms based on the scope of the research and development activities;

[0090] The labeling device 303 is configured to label cutting-edge technologies corresponding to the literature data based on the literature dataset generated by the retrieval of the topic classification terms.

[0091] The device 304 is configured to extract data information from innovation entities engaged in the cutting-edge technology and establish an innovation entity dataset.

[0092] The determining device 305 is configured to determine the collaborating institutions of the target research institution by calculating the recommendation scores of the innovation subjects in the innovation subject dataset.

[0093] Optionally, the generation device 302 is used to generate a method for generating topic classification terms based on the scope of the R&D activities, including: generating a technology decomposition table based on the obtained scope of the R&D activities of the target research institution, wherein the technology decomposition table includes at least a first technology branch and a second technology branch; and determining the topic classification terms according to the branches of the technology decomposition table.

[0094] Optionally, the labeling device 303 is used to label cutting-edge technologies corresponding to literature data in a method comprising: statistically analyzing the proportion of technical topic words in the literature dataset to obtain a first word frequency of the technical topic words, wherein the technical topic words include the topic classification words; determining high-frequency technical topic words by comparing the first frequency with the frequency threshold according to a preset frequency threshold; constructing a high-frequency technical topic word co-occurrence network based on the co-occurrence relationship of the high-frequency technical topic words, and summarizing the characteristics of high-frequency technical topic word clusters; identifying high-frequency technical topic words in the same word cluster as a cutting-edge technology topic to form the cutting-edge technology topic list; calculating the proportion of the cutting-edge technology topics in the cutting-edge technology topic list in the literature dataset according to the TF-IDF algorithm to obtain a second word frequency of the cutting-edge technology topic; and labeling the cutting-edge technologies corresponding to the literature data based on the second word frequency.

[0095] Optionally, the method for establishing an innovation subject dataset by the establishment device 304 includes: extracting innovation subject information based on the labeling of the cutting-edge technology, wherein the innovation subject information includes at least: scope information of the innovation subject, field information of the innovation subject dataset, evaluation index information of the innovation subject, etc.

[0096] Optionally, the determining device 305 is used to determine the cooperating institutions of the target research institution in a method comprising: obtaining pre-preset evaluation index weights of the innovation entity; calculating a recommendation score for the innovation entity based on the index weights; sorting the recommendation scores in descending order to obtain a list of cooperating institutions, and determining the cooperating institutions of the target research institution.

[0097] Optionally, the determining device 305 is used for a method to determine the evaluation indicators of the innovation entity, including: calculating the theoretical research indicator Ti of the innovation entity's participation in the target frontier technology topic based on the number of academic papers produced by the innovation entity; calculating the applied research indicator Ai of the innovation entity's participation in the target frontier technology topic based on the number of patent applications of the innovation entity; calculating the R&D activity indicator Ri of the innovation entity's participation in the target frontier technology topic based on the growth rate of the innovation entity's scientific and technological literature output; calculating the cooperation activity indicator Ci of the innovation entity's participation in the target frontier technology topic based on the number of cooperative institutions of the innovation entity; and normalizing the theoretical research indicator, the applied research indicator, the R&D activity indicator, and the cooperation activity indicator to determine the normalized value of the evaluation indicator.

[0098] Optionally, the method by which the determining device 305 calculates the recommendation score of the innovation subject includes: calculating the recommendation score of the innovation subject according to the following formula:

[0099]

[0100] in, These are the weights of indicators in theoretical research; These are the weights of applied research indicators; It is the weight of the R&D activity index; 1 is the weight of the collaboration activity index; Ti is the theoretical research index; Ai is the applied research index; Ri is the R&D activity index; Ci is the collaboration activity index; i is the target frontier technology theme.

[0101] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0102] Example 3

[0103] Figure 4 This is a block diagram of an electronic device according to an embodiment of the present invention. Please refer to the attached diagram. Figure 4 The diagram illustrates the structure of the device, which includes a memory and a processor. The memory stores computer instructions that can run on the processor, and the processor executes the computer instructions to implement the methods described in any embodiment of this disclosure.

[0104] The present invention also provides a computer-readable storage medium having stored thereon computer program instructions, which, when executed by a processor, implement the steps of a method for recommending research collaboration institutions based on technical topic identification provided by the present invention.

[0105] Those skilled in the art will understand that one or more embodiments of this specification can be provided as a method, system, or computer program product. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0106] This specification also provides a computer-readable storage medium on which a computer program can be stored. When executed by a processor, the program implements the steps of the method for recommending research collaboration institutions based on technical topic identification as described in any embodiment of this specification, and / or implements the steps of the method for recommending research collaboration institutions based on technical topic identification as described in any embodiment of this specification. Wherein, "and / or" indicates at least one of two options; for example, "A and / or B" includes three options: A, B, and "A and B".

[0107] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the data processing device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0108] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0109] The embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing apparatus or for controlling the operation of a data processing apparatus. Alternatively or additionally, the program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0110] The processing and logic flow described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by dedicated logic circuitry—such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits), and the device can also be implemented as dedicated logic circuitry.

[0111] Suitable computers for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0112] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0113] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0114] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0115] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0116] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-described technical content to create equivalent embodiments without departing from the scope of the present invention. The implementation schemes in the above embodiments can also be further combined or replaced. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for recommending research collaboration institutions based on technology topic identification, characterized in that, include: To obtain the scope of research and development activities of the target research institution; Based on the scope of the aforementioned R&D activities, generate thematic classification terms; Based on the literature dataset generated by searching the aforementioned topic classification terms, the cutting-edge technologies corresponding to the literature data are labeled; Extract data information from the innovation entities engaged in the aforementioned cutting-edge technologies and establish an innovation entity dataset; By calculating the recommendation scores of the innovation entities in the innovation entity dataset, the cooperative institutions of the target research institution are determined; The method for generating topic classification terms based on the scope of the R&D activities includes: Based on the scope of R&D activities of the target research institution, a technology decomposition table is generated, wherein the technology decomposition table includes at least a first technology branch and a second technology branch. Based on the branches of the technology breakdown table, determine the topic classification terms; The method for labeling cutting-edge technologies corresponding to the literature data includes: The proportion of technical topic terms in the literature dataset is statistically analyzed to obtain the first word frequency of the technical topic terms, wherein the technical topic terms include the topic classification terms; Based on a preset frequency threshold, high-frequency technical keywords are determined by comparing the first word frequency with the frequency threshold. Based on the co-occurrence relationships of the high-frequency technical keywords, a co-occurrence network of high-frequency technical keywords is constructed, and the characteristics of high-frequency technical keyword clusters are summarized. High-frequency technical keywords within the same word cluster are identified as a cutting-edge technical topic, forming a list of cutting-edge technical topics; The proportion of the cutting-edge technology topics in the list of cutting-edge technology topics in the literature dataset is calculated using the TF-IDF algorithm to obtain the second word frequency of the cutting-edge technology topics. Based on the second word frequency, the cutting-edge technologies corresponding to the literature data are marked.

2. The method for recommending research collaboration institutions based on technology topic identification according to claim 1, characterized in that, The method for establishing the innovation subject dataset includes: Based on the labeling of the cutting-edge technologies, innovation subject information is extracted, wherein the innovation subject information includes at least: scope information of the innovation subject, field information of the innovation subject dataset, and evaluation index information of the innovation subject; Based on the aforementioned innovation entity information, an innovation entity dataset is established.

3. The method for recommending research cooperation institutions based on technology topic identification according to claim 1 or 2, characterized in that, The method for determining the collaborating institutions of the target research institution includes: Obtain the pre-set evaluation index weights of the innovation entity; Based on the weights of the aforementioned indicators, a recommendation score for the innovation entity is calculated. The recommended scores are sorted in descending order to obtain a list of collaborating institutions, and the collaborating institutions of the target research institution are determined.

4. The method for recommending research cooperation institutions based on technology topic identification according to claim 3, characterized in that, The methods for determining the evaluation indicators for innovation entities include: Based on the number of academic papers produced by the innovation entity, calculate the theoretical research index Ti of the innovation entity's participation in the target frontier technology topic; Based on the number of patent applications filed by the innovation entity, calculate the applied research index Ai of the innovation entity's participation in the target frontier technology theme; Based on the growth rate of scientific and technological literature output by the innovation entities, calculate the R&D activity index Ri of the innovation entities participating in the target frontier technology topics; Based on the number of collaborating institutions of the innovation entity, calculate the cooperation activity index Ci of the innovation entity in the target frontier technology theme; The theoretical research indicators, applied research indicators, R&D activity indicators, and cooperation activity indicators are normalized to determine the normalized values ​​of the evaluation indicators.

5. The method for recommending research cooperation institutions based on technology topic identification according to claim 4, characterized in that, The method for calculating the recommendation score of the innovation subject includes: The recommendation score for the innovation entity is calculated using the following formula: in, These are the weights of indicators in theoretical research; These are the weights of applied research indicators; It is the weight of the R&D activity index; 1 is the weight of the collaboration activity index; Ti is the theoretical research index; Ai is the applied research index; Ri is the R&D activity index; Ci is the collaboration activity index; i is the target frontier technology theme.

6. A research collaboration institution recommendation device based on technology topic identification, characterized in that, include: The acquisition device is configured to acquire the scope of research and development activities of the target research institution; The generation device is configured to generate topic classification terms based on the scope of the research and development activities; A labeling device is configured to label cutting-edge technologies corresponding to document data based on a document dataset generated by retrieving the subject classification terms. An apparatus is configured to extract data information from innovation entities engaged in the aforementioned cutting-edge technologies and establish an innovation entity dataset. The determining device is configured to determine the collaborating institutions of the target research institution by calculating the recommendation scores of the innovation subjects in the innovation subject dataset; The method for generating topic classification terms based on the scope of the research and development activities, as described by the generating device, includes: Based on the scope of R&D activities of the target research institution, a technology decomposition table is generated, wherein the technology decomposition table includes at least a first technology branch and a second technology branch. Based on the branches of the technology breakdown table, determine the topic classification terms; The method for using the labeling device to label cutting-edge technologies corresponding to literature data includes: The proportion of technical topic terms in the literature dataset is statistically analyzed to obtain the first word frequency of the technical topic terms, wherein the technical topic terms include the topic classification terms; Based on a preset frequency threshold, high-frequency technical keywords are determined by comparing the first word frequency with the frequency threshold. Based on the co-occurrence relationships of the high-frequency technical keywords, a co-occurrence network of high-frequency technical keywords is constructed, and the characteristics of high-frequency technical keyword clusters are summarized. High-frequency technical keywords within the same word cluster are identified as a cutting-edge technical topic, forming a list of cutting-edge technical topics; The proportion of the cutting-edge technology topics in the list of cutting-edge technology topics in the literature dataset is calculated using the TF-IDF algorithm to obtain the second word frequency of the cutting-edge technology topics. Based on the second word frequency, the cutting-edge technologies corresponding to the literature data are marked.

7. An electronic device, characterized in that, The device includes a memory and a processor, characterized in that the memory stores a computer program, and the processor is configured to execute the method of any one of claims 1 to 5 through the computer program.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method of any one of claims 1 to 5.

Images