A core technology identification method based on dual technology correlation

Abstract

The present invention discloses a core technology identification method based on dual technology relevance. In the method, first, relevant technical documents are collected and the text content in the documents is preprocessed; second, word embeddings corresponding to the terms contained in the technical documents are obtained through Word2Vec model training; then, the obtained word embeddings and the preprocessed technical documents are used as input, and topics representing different technologies are extracted through an ETM-based topic modeling process; then, the proximity and combination association degree between topics are measured using cosine similarity and association strength standardization methods; next, the proximity and combination association between topics are used as nodes and node links in the network to construct a dual network; finally, a multi-centrality analysis method based on multiple centrality indicators and factor analysis is used to identify dual core technologies, core combination technologies, core proximity technologies and edge technologies in the dual network.

Description

Technical Field

[0001] The present invention relates to a core technology identification method based on dual technology relevance. Background Art

[0002] Technological interconnectedness shapes the technological diversification patterns of innovators and influences the direction of technological innovation. Clarifying the interconnectedness of technologies helps clarify the relative importance of different technologies and the interconnectedness structure within technological fields. Exploring the interconnectedness of different technologies can help innovators comprehensively grasp technological trends and assist in implementing technological innovations.

[0003] Existing research has neglected the multiple types of technological interconnectedness, considering only a single type of relationship between technologies. However, the concept of technological interconnectedness is not singular but encompasses multiple types of interconnections. Different types of interconnections have varying strengths within the same set of technologies and exhibit complex patterns, revealing richer technological information than considering only a single type of interconnection. Considering multiple types of technological interconnections can help reveal the true structure of relationships between multiple technological fields within a technological system, enabling innovators to make informed decisions about technological innovation.

[0004] Current research methods rely on single-layer networks to study a single correlation between technologies. Limited by the modeling capabilities of single-layer networks, these methods can only study a single type of correlation and are unable to explore multiple types. When studying multiple correlations using these methods, they can only aggregate multiple correlation types into one, but this loses the information contained in the relationships between different types. Therefore, a method is needed that can simultaneously study and reveal multiple correlations between technologies.

[0005] Measuring the degree of association between technologies is the foundation for studying technological relevance, as it determines the structure of associations between technologies. Most existing methods for measuring the degree of technological association do not use text-based methods. Although some keyword-based methods attempt to leverage text data to achieve more accurate association measurements, keyword-based methods can only capture discrete relationships between keywords while ignoring semantic connections. Furthermore, such methods cannot handle the frequent occurrence of technical terms, synonyms, and polysemous words in patent texts. Therefore, a text-based method that takes into account text semantics is needed to achieve more accurate association measurements.

[0006] Furthermore, most existing core technology identification methods consider the relative importance of technologies from a single perspective, failing to comprehensively assess their importance. This can lead to one-sided identification of core technologies and overlook other potential core technologies. Therefore, a more comprehensive approach to identifying core technologies is urgently needed, capable of assessing the relative importance of technologies across multiple dimensions. Summary of the Invention

[0007] The purpose of the present invention is to provide a core technology identification method based on dual technology relevance to solve the technical problems raised by the background technology, comprising the following steps:

[0008] Extract technical keywords based on technical documents, construct a technical search formula, and obtain D original technical documents from the technical database based on the technical search formula;

[0009] performing sentence segmentation and a first text preprocessing on the text content in each of the D original technical documents to obtain preprocessed technical document sentences, and training a word embedding model based on the preprocessed technical document sentences to obtain word embeddings corresponding to the terms contained in the D original technical documents;

[0010] Performing a second text preprocessing on the D original technical documents to obtain technical documents recorded in a bag-of-words format;

[0011] Based on the word embedding and the technical documents in the bag-of-words format, topic modeling is performed using the ETM model to obtain three results, including a topic-term probability distribution matrix β, a document-topic probability distribution matrix θ, and a topic embedding matrix α;

[0012] Based on the topic embedding matrix α, the cosine similarity calculation formula is used to measure the proximity between two topic embeddings, and the proximity association matrix P that records the proximity association strength between the topics is obtained. Based on the document-topic probability distribution matrix θ, the combined association matrix C that records the combined association strength between the topics is calculated by the association strength normalization method. Based on the proximity association matrix P and the combined association matrix C, a dual network with two network levels is constructed. And for dual network Visualize; identify dual networks using multiple centrality analysis methods based on multiple centrality indicators and factor analysis Dual-core technology, core combination technology, core adjacent technology and edge technology in the industry;

[0013] Dual Network It can be represented by the hyperadjacency matrix A:

[0014]

[0015] in,

[0016]

[0017] The dual core technologies refer to topics that exhibit high centrality in both the proximity network layer and the combined network layer;

[0018] The core combination technology refers to a topic that has low centrality in the proximity network layer but high centrality in the combination network layer;

[0019] The edge technologies refer to topics that exhibit low centrality in both the proximity network layer and the combined network layer;

[0020] The core proximity technology refers to a topic that has high centrality in the proximity network layer but low centrality in the combination network layer.

[0021] Furthermore, the word embedding model is a Word2Vec model or a glove model.

[0022] Furthermore, the specific steps of sentence segmentation and the first text preprocessing include:

[0023] The Python toolkit NLTK is used to segment the text content of each original technical document into technical document sentences with sentences as units;

[0024] The python toolkit spaCy is used to perform the first text preprocessing on the technical document after sentence segmentation to obtain the preprocessed technical document sentences.

[0025] Furthermore, the first text preprocessing process: first, delete numbers, punctuation marks and words with a character length of less than 3 in the text; then, perform part-of-speech restoration on the remaining words and convert them into lowercase; finally, delete sentences whose sentence length is less than the "window size" parameter value set by the subsequent Word2Vec model to obtain preprocessed technical document sentences.

[0026] Furthermore, the second text preprocessing uses the python toolkit spaCy, and the processing process includes deleting numbers, punctuation marks, stop words, terms with a character length of less than 3, and non-noun terms in the original technical documents, restoring the remaining terms and converting them to lowercase, deleting terms with a document frequency of less than 3 in the technical document collection, and finally obtaining the preprocessed technical documents recorded in the form of a bag of words with a dictionary size of V.

[0027] Furthermore, based on the word embedding and the technical documents in the bag-of-words form, topic modeling is performed through the ETM model to obtain three results, including the topic-term probability distribution matrix β, the document-topic probability distribution matrix θ and the topic embedding matrix α.

[0028] The specific steps are as follows:

[0029] Using the word embeddings and the technical documents recorded in the bag-of-words format as input data for training the ETM model, the optimal setting value of the parameter K of the number of topics in the ETM model is determined through repeated experiments;

[0030] The technical documents recorded in the word embedding and bag-of-words format are used as model inputs, and a topic modeling process is performed based on the ETM model parameter value, the number of topics K, to obtain three output results in the form of matrices:

[0031] Topic-term probability distribution matrix β:

[0032]

[0033] Row vector β k· is the probability distribution of topic k over all terms, where k is the kth topic among K topics;

[0034] Document-topic probability distribution matrix θ:

[0035]

[0036] Row vector θ d· is the probability distribution of document d on all topics, where d is the d-th document in D topics;

[0037] Topic embedding matrix α:

[0038]

[0039] The column vector α·k is the topic embedding corresponding to topic k, where k is the kth topic among K topics.

[0040] Furthermore, the cosine similarity calculation formula is used to measure the proximity between two topic embeddings. The specific steps to obtain the proximity correlation matrix P that records the proximity correlation strength between the topics are as follows:

[0041] Use the cosine similarity calculation formula to calculate the element value in the proximity association matrix P;

[0042]

[0043] P is a symmetric square matrix, and the calculation formula of the element value is:

[0044]

[0045] Among them, α i is the topic embedding corresponding to topic i, α j is the topic embedding corresponding to topic j, |α i || is the L-2 norm of the topic embedding corresponding to topic i, ||α j || is the L-2 norm of the topic embedding corresponding to topic j, p ij and p ji is the proximity correlation degree between topic i and topic j;

[0046] The range of element values ​​in the proximity correlation matrix P is scaled from [-1, 1] to [0, 1] by standardization. The standardization calculation formula is:

[0047]

[0048] p′ ij is the normalized matrix element value;

[0049] The diagonal element values ​​of the proximity correlation matrix P are returned to 0, that is:

[0050] p′ ii =0

[0051] Finally, the processed proximity correlation matrix is ​​obtained.

[0052] Furthermore, the specific steps of calculating the combined association matrix C that records the combined association strengths between topics based on the document-topic probability distribution matrix θ by the association strength standardization method are as follows:

[0053] Set a threshold η and set the element value less than η in the document-topic probability distribution matrix θ to 0, thereby filtering rare events. The formula is expressed as:

[0054]

[0055] The combined association matrix C of the combined association strength between record topics is calculated using the association strength standardization method:

[0056]

[0057] C is a symmetrical square matrix, and the calculation formula of the element value is:

[0058]

[0059] θ idis the element value in the document-topic probability distribution matrix θ, that is, the probability that topic i appears in document d; θ jd is the element value in the document-topic probability distribution matrix θ, that is, the probability that topic j appears in a document d; ∑ d θ id θ jd is the probability that topic i and topic j appear together in the document collection, ∑ d θ id is the total probability of topic i appearing in the document collection; ∑ d θ jd is the total probability of topic j appearing in the document collection;

[0060] The diagonal element values ​​of the combined correlation matrix C are returned to zero, and the processed combined correlation matrix C is finally obtained. The return-to-zero processing formula is:

[0061] c ii =0.

[0062] Furthermore, the steps of using a multiple centrality analysis method based on multiple centrality indicators and factor analysis to identify dual core technologies, core combination technologies, core adjacent technologies, and edge technologies in the dual network M include:

[0063] Calculate the strength of each topic i in the proximity network layer among the K topics The calculation formula is: Calculate the strength of each topic i in the combined network layer among the K topics The calculation formula is: The dual network is calculated using the python toolkit NetworkX The feature vector centrality of each topic i in the proximity network layer and the combination network layer in the K topics and Current betweenness centrality and Current proximity to centrality and

[0064] Among them, the eigenvector centrality of each topic i in the p network layer corresponding to the proximity association matrix P is obtained by the eigenvector_centrality function in the Python toolkit NetworkX The eigenvector_centrality function in the Python toolkit NetworkX is used to obtain the eigenvector centrality of each topic i in the c network layer corresponding to the combined correlation matrix C. The current betweenness centrality of each topic i in the p network layer corresponding to the proximity association matrix P is obtained through the current_flow_betweenness_centrality function in the Python toolkit NetworkX The current betweenness centrality of each topic i in the c network layer corresponding to the combined correlation matrix C is obtained through the current_flow_betweenness_centrality function in the Python toolkit NetworkX The current closeness centrality of each topic i in the p network layer corresponding to the proximity association matrix P is obtained through the current_flow_closeness_centrality function in the Python toolkit NetworkX The current closeness centrality of each topic i in the combined network layer corresponding to the combined correlation matrix C is obtained through the current_flow_closeness_centrality function in the Python toolkit NetworkX

[0065] For each topic i among the K topics As input data, factor analysis was performed using the factor function of stata software to obtain the centrality variables that can explain the four layers in the proximity network. Commonality factor f p And each topic i among K topics has a factor f p The corresponding factor score f p (i) and the centrality variables that can explain the four centrality variables at the combined network level Commonality factor f c And each topic i among K topics has a factor f c The corresponding factor score f c (i), each subject i in the dual network The centrality in is represented as a vector

[0066] Set the factor score f for the partition topic i p (i) High and low thresholds γ p , set the factor score f of the partition topic i c (i) High and low thresholds γ c , which is used to judge the degree of centrality of the network position of subject i in the proximity network layer and the combination network layer respectively;

[0067] The factor score f p (i) As the x-axis, the factor score fc (i) As the y-axis, construct a two-dimensional coordinate system, and based on the vector Construct a two-dimensional space based on two thresholds γ p and γ c Divide the two-dimensional space into four spatial regions to identify the dual network Dual-core technology, core combination technology, core adjacent technology and edge technology.

[0068] Furthermore, the threshold γ p Set to the median or third quantile of the factor scores of K topics in the proximity network layer; the threshold γ c Set to the median or third quantile of the factor scores of the K topics in the combined network layer.

[0069] The beneficial effect of the present invention is that the method can embed two types of technical associations, namely proximity and combination, in a network system, while visualizing the association structure between technologies and analyzing various association patterns between technologies. First, relevant technical documents are collected and the text content in the documents is preprocessed; secondly, the word embeddings corresponding to the terms contained in the technical documents are obtained through Word2Vec model training; then, the obtained word embeddings and the preprocessed technical documents are used as input, and topics representing different technologies are extracted through ETM-based topic modeling; then, the cosine similarity and association strength standardization methods are used to measure the proximity and combination association between topics; next, the proximity and combination association between topics are used as nodes and node links in the network to construct a dual network. Finally, the multi-centrality analysis method based on multiple centrality indicators and factor analysis identified dual networks. Dual-core technology, core combination technology, core adjacent technology and edge technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0071] Figure 1 It is a topic consistency display diagram of the ETM model corresponding to different number of topics K;

[0072] Figure 2 This is a graph showing the topic embedding of topic 5 and the word embeddings of the 15 terms closest to its cosine.

[0073] Figure 3 It is a dual network display diagram embedded with dual technology correlation;

[0074] Figure 4 Identify dual networks A two-dimensional spatial display of dual core technology, core combination technology, core adjacent technology and edge technology.

[0075] It should be noted that the drawings are not necessarily drawn to scale, but are merely shown in a schematic manner that does not affect the reader's understanding. DETAILED DESCRIPTION

[0076] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0077] The present invention provides a core technology identification method based on dual technology relevance, comprising the following steps:

[0078] S1: Extract technical keywords based on technical documents and construct technical search formulas;

[0079] For example, the technical documents are multiple articles related to the field of 3D printing technology. Keywords describing this technology are extracted from these documents, and a technical search formula suitable for the technology database is constructed. For example, a specific search formula suitable for the incoPat patent database is as follows:

[0080] “TIAB=(3D printing) OR TIAB=(three-dimensional printing) OR TIAB=(3DP) OR TIAB=(additive manufacturing) OR TIAB=(rapid prototyping) OR TIAB=(three-dimensional manufacturing)”

[0081] S2: Obtain D original technical documents from the technical database based on the technical search formula;

[0082] For example, the technology database is a patent database (incoPat patent database or DerwentInnovations Index patent database). For example, based on the technology search formula related to 3D printing technology constructed in Example S1, 67,231 original technical documents are searched from the incoPat patent database. Preferably, the content of the original technical documents is the title text and abstract text of the patent specification on which the subsequent method analysis is based.

[0083] S3: performing sentence segmentation and a first text preprocessing on the text contents of the D original technical documents to obtain preprocessed technical document sentences;

[0084] Specifically, the specific steps of sentence segmentation and the first text preprocessing include:

[0085] S31: using the Python toolkit NLTK, the text content of each original technical document is segmented to obtain technical document sentences with sentences as units;

[0086] For example, the text contents of the 67,231 original technical documents obtained in Example S2 are segmented to obtain 590,634 technical document sentences.

[0087] S32: Use the Python toolkit spaCy to perform the first text preprocessing on the technical document sentences after sentence segmentation processing to obtain the preprocessed technical document sentences.

[0088] Specifically, the first text preprocessing process: first, delete numbers, punctuation marks, and words with a length of less than 3 characters in the text; then, perform part-of-speech restoration on the remaining words and convert them to lowercase; finally, delete sentences whose sentence length (the number of words contained in the sentence) is less than the "window size" parameter value set by the subsequent Word2Vec model, and obtain the preprocessed technical document sentences;

[0089] For example, the 590,634 technical document sentences obtained in Example S31 were subjected to text preprocessing to obtain 561,733 preprocessed technical document sentences.

[0090] S4: Based on the preprocessed technical document sentences obtained in S3, the Python toolkit Gensim is used to train the Word2Vec model to obtain word embeddings corresponding to D terms contained in the original technical document; the word embedding results will be used as one of the input data for subsequent ETM model training;

[0091] For example, when training a Word2Vec model, the following parameters were used: Skip-Gram architecture, 15 negative sampling values, 300 word embedding dimensions, 5 window sizes, 20 iterations, and a minimum word frequency of 1. All other parameters not mentioned used the default values ​​from Gensim's Word2Vec model API. Based on the 561,733 technical document sentences obtained in the S32 example, the Word2Vec model trained with these parameters yielded 300-dimensional word embeddings for 19,709 terms.

[0092] Preferably, in the present invention, the word embedding model is a Word2Vec model. Of course, in addition to the above models, it can also be other word embedding models such as Glove.

[0093] First, the Word2Vec model is simple and efficient, making it suitable for resource-constrained scenarios. Because it uses a shallow neural network to generate word embeddings, it is simpler and more efficient than complex models like BERT. Furthermore, Word2Vec performs well even in situations with limited computing resources, allowing researchers and practitioners to use it without extensive hardware support.

[0094] Secondly, the Word2Vec model is fast to train. The Word2vec model uses some acceleration methods, such as NegativeSampling and Hierarchical Softmax, which makes it faster during training.

[0095] Finally, the Word2Vec model supports incremental training, which means that the Word2Vec model can be updated with new data without training from scratch, which is a very useful feature for applications that need to continuously introduce new information.

[0096] S5: Perform a second text preprocessing on the D original technical documents described in S2 to obtain technical documents recorded in the form of bag-of-words. The technical documents recorded in the bag-of-words form will serve as one of the input data for subsequent ETM model training.

[0097] Specifically, the second text preprocessing uses the python toolkit spaCy, and the processing process includes deleting numbers, punctuation marks, stop words, terms with a character length of less than 3, and terms with non-noun parts of speech in the original technical documents. The stop words refer to terms that appear frequently in the language and contribute less to the actual semantics of the text, such as articles, prepositions, etc. Finally, the remaining terms are restored to their parts of speech and converted to lowercase, and terms with a document frequency of less than 3 in the technical document collection are deleted. Finally, the preprocessed technical documents are recorded in the form of a bag of words with a dictionary size of V. The dictionary refers to a collection of all unique (i.e., unique, non-repeating) terms extracted from the technical documents.

[0098] For example, the 67,231 original technical documents obtained in Example S2 are subjected to a second text preprocessing to obtain 67,135 technical documents recorded in the form of bag-of-words with a dictionary size of 9,042.

[0099] During the second text preprocessing step, retaining only noun-specific terms can improve the training efficiency of the topic model and enhance the semantic consistency and interpretability of the topic results. Technical components and terminology, such as methods and tools, often appear as nouns. Therefore, terms with other parts of speech become noise during topic model training, affecting both training efficiency and the accuracy of the results. These terms also fail to contribute to the interpretation of the topic results. Therefore, during the second text preprocessing step, terms other than noun-specific terms are removed to address these issues, positively enhancing the topic model training process.

[0100] S6: Based on the word embeddings obtained in S4 and the technical documents in the bag-of-words format obtained in S5, topic modeling is performed using the ETM model to obtain three results: the topic-term probability distribution matrix β, the document-topic probability distribution matrix θ, and the topic embedding matrix α.

[0101] First, the ETM used in the present invention has higher operational efficiency and computational efficiency. For example, traditional topic models such as LSA (Latent Semantic Allocation) and LDA (Latent Dirichlet allocation) have low computational efficiency and operational efficiency. Traditional topic models have parameter inference processes specific to different models, and the complexity of the parameter inference process increases with the complexity of the model itself. In addition, traditional topic models consume a lot of time when facing large document sets. The ETM model used in the steps of this method is a topic model based on a neural network, so the model parameters can be inferred through an automatic gradient backpropagation process, and parallel computing is allowed, thereby greatly improving the computational efficiency of the topic modeling process.

[0102] Secondly, the ETM model used has better model interpretability. The interpretability of traditional topic models is poor, and the training process only relies on a single input data of a document set represented in the form of a bag of words. Since the document set represented in the form of a bag of words can only record the discrete relationship between terms in the text content, it cannot capture the semantic relationship reflected by the context in which the terms are located, so it will cause the loss of semantic information. The training process of the ETM model used in the method steps of the present invention not only uses a document set represented in the form of a bag of words, but also utilizes word embeddings containing semantic information in the document set. Word embedding can encode the semantic and grammatical information of a term into its vector (i.e., embedding) representation. Word embedding, as the second input data of ETM, makes the ETM model more interpretable.

[0103] Furthermore, the ETM model used is robust to stop words and rare words. Traditional topic models reduce the interpretability of their results when encountering stop words and rare words. This is because stop words and rare words appear within the content of topic results, making them unhelpful for interpreting them. However, the ETM model used in this method generates separate topics for meaningless and frequently occurring stop words and rare words, distinguishing meaningful terms from these, thereby improving the interpretability of the model results.

[0104] Finally, thanks to the input word embedding data, the ETM model used has unique outputs that other topic models do not have.

[0105] Topic embedding. Traditional topic models only have two outputs: the topic-term probability distribution matrix β and the document-topic probability distribution matrix θ. ETM, on the other hand, has a unique output: the topic embedding matrix α. Topic embeddings express the semantic content and rich contextual semantic information of a topic through vectors (i.e., embeddings), providing a foundation for more accurate measurement of the degree of association between topics.

[0106] The process of obtaining three result matrices through topic modeling using the ETM model includes the following steps:

[0107] S61: The word embeddings obtained in S4 and the technical documents recorded in the bag-of-words format obtained in S5 are used as input data for training the ETM model. The optimal setting value of the parameter K for the number of topics in the ETM model is determined through repeated experiments.

[0108] For example, in the ETM model, all parameters except the number of topics K remain unchanged. The experiment is repeated with different numbers of topics K. The topic coherence (TC) index of each experimental model result is calculated. The higher the topic coherence value, the stronger the interpretability of the topic model. The formula for calculating topic coherence (TC) is as follows:

[0109]

[0110] Function f(·,·) is the normalized pointwise mutual information, and its calculation formula is:

[0111]

[0112] Among them, P(w i ,w j ) is the term w i With the term w j The probability of co-occurrence in the same document, P(w i) is the term w i The marginal probability of occurrence, P(w j ) is the term w j The marginal probability of occurrence is selected. The number of topics K corresponding to the maximum value of the topic consistency index is determined as the parameter value for the final ETM model training.

[0113] For example, the training parameters are set as follows: learning rate is 0.001, training cycle is 150, batch size is 1000, and other parameters except the number of topics K use the default values ​​of the ETM model. The number of topics K is repeated in the range of [5,100] with a step size of 5 to obtain the topic consistency results corresponding to each experimental model, such as Figure 1 As shown:

[0114] When the number of topics is 50, the topic consistency reaches its maximum value and has better interpretability. Therefore, the number of topics K in the ETM training parameters is determined to be 50.

[0115] S62: Take the word embeddings obtained in S4 and the technical documents recorded in the form of bag-of-words obtained in S5 as model inputs, perform topic modeling based on the ETM model parameter values ​​determined in S61, and obtain three output results in the form of matrices:

[0116] Topic-term probability distribution matrix β:

[0117]

[0118] Row vector β k· is the probability distribution of topic k (i.e., the kth topic among K topics) over all terms;

[0119] Document-topic probability distribution matrix θ:

[0120]

[0121] Row vector θ d· is the probability distribution of document d (i.e., the d-th document in D topics) over all topics;

[0122] Topic embedding matrix α:

[0123]

[0124] The column vector α·k is the topic embedding corresponding to topic k (i.e., the kth topic among K topics).

[0125] For example, we can use the 300-dimensional word embeddings corresponding to the 19,709 terms obtained in Example S4 and the 67,135 technical documents recorded in the bag-of-words format with a dictionary size of 9,042 obtained in Example S5 to perform topic modeling using the model parameter values ​​determined in Example S61, and finally obtain:

[0126] Topic-term probability distribution matrix β:

[0127]

[0128] Document-topic probability distribution matrix θ:

[0129]

[0130] Topic embedding matrix α:

[0131]

[0132] The above results are presented with only three significant figures. The "topics" can be presented in two different forms using the resulting matrix β and matrix α. When presented using matrix β, each topic can be represented by the term with the largest probability distribution value for the topic on the terms, as shown in the following table:

[0133]

[0134]

[0135] The table shows some of the results, namely the 15 terms with the largest probability distribution values ​​for different topics on different terms. When displayed by α, the topic embedding corresponding to the topic in the embedding space can be visualized after dimensionality reduction, as well as the word embedding of the term closest to the topic embedding in cosine space, such as Figure 2 shown.

[0136] It should be noted that the “topics” represent different technologies, and the technical content represented by these technologies is represented by the term with the largest probability value distributed on the topic, or by the term corresponding to the word embedding in the embedding space that is closest to the cosine space distance of the topic embedding.

[0137] For example, the results for Topic 5 in the figure show the topic embedding corresponding to Topic 5 in the embedding space, as well as the word embeddings of the 15 terms closest to Topic 5 in cosine space. Based on the meanings of the terms adjacent to Topic 5, we can infer that this topic represents technologies related to temperature control and heating processes in 3D printing.

[0138] S7: Use the cosine similarity calculation formula to measure the proximity between the two topic embeddings, and obtain the proximity correlation matrix P that records the degree of proximity correlation between the topics;

[0139] The method of the present invention is based on the unique output of ETM - the topic embedding matrix α, which achieves a more accurate measurement of the degree of topic proximity. Existing methods for measuring the degree of topic proximity are all based on the topic-term probability distribution matrix β output by the traditional topic model. However, during the generation process, the traditional topic model only relies on the document set represented by the bag of words that can only capture the discrete relationship between terms, which makes the topic-term probability distribution matrix β output by the model unable to capture the semantic content represented by the topic. Therefore, the degree of topic association calculated by this type of method is not accurate enough. The topic embedding matrix α output by the ETM model, based on the input word embedding data, realizes the expression of the semantic content contained in the topic in the form of a vector (i.e., embedding). Topic embedding can fully reflect the rich semantic information contained in the topic content, and further, a more accurate measurement of the degree of topic association at the semantic level can be obtained by a calculation method applicable to the degree of vector (i.e., embedding) relationship.

[0140] Measuring the proximity between two topic embeddings using the cosine similarity calculation formula involves the following steps:

[0141] S71: Calculate the element value in the proximity association matrix P based on the cosine similarity;

[0142]

[0143] P is a symmetric square matrix, and the calculation formula of the element value is:

[0144]

[0145] Among them, α i is the topic embedding corresponding to topic i, α j is the topic embedding corresponding to topic j, ||α i || is the L-2 norm of the topic embedding corresponding to topic i, ||α j || is the L-2 norm of the topic embedding corresponding to topic j, p ij and p ji is the proximity correlation degree between topic i and topic j.

[0146] For example: Based on the results of the topic embedding matrix α obtained in Example S62, the proximity correlation matrix P is calculated using the cosine similarity calculation formula (proximity correlation is the first type of correlation in dual correlation);

[0147]

[0148] S72: scaling the value range of the element values ​​in the proximity association matrix P from [-1, 1] to [0, 1] by normalization processing. The normalization processing calculation formula is:

[0149]

[0150] p′ ij is the element value of the standardized proximity correlation matrix P;

[0151] In the present invention, the normalization process is to ensure that the weights of the network edges subsequently constructed based on the proximity association matrix P are non-negative. Then, in order to ensure that there are no node self-connections in the network subsequently constructed based on the proximity association matrix P, the diagonal element values ​​of the proximity association matrix P are normalized to 0, that is:

[0152] p′ ii =0

[0153] Finally, the processed proximity correlation matrix P is obtained.

[0154] For example, after normalizing the proximity correlation matrix P obtained in Example S71 and returning the diagonal elements to zero, the final proximity correlation matrix P is obtained:

[0155]

[0156] S8: Based on the document-topic probability distribution matrix θ, a combined association matrix C recording the degree of combined association between topics is calculated by an association strength standardization method (combined association is the second type of association in dual association).

[0157] In the method of the present invention, a more accurate measurement of the degree of topic combination is achieved based on the association strength standardization method. The combination refers to the relationship in which two different topics are used together, that is, the relationship of co-occurrence. Therefore, when measuring the degree of topic combination, it is necessary to use the co-occurrence measurement method. The existing topic co-occurrence measurement methods are all based on the document-topic probability distribution matrix θ. By setting a threshold value for the probability of topic occurrence or setting a threshold value for the number of topics contained in each document, θ is converted into a binary matrix and then a topic co-occurrence matrix is ​​constructed, thereby achieving the measurement of the topic co-occurrence degree. This type of method will cause a large amount of topic probability information to be lost during the process of setting the threshold for binary matrix conversion. In addition, directly calculating the topic co-occurrence degree based on the binary matrix will be subject to the size effect brought by the topic probability itself. The size effect will cause the topics that frequently appear in the document set to counterfactually have a high frequency of co-occurrence with other topics. If the size effect is not eliminated, the final topic co-occurrence result will not be able to reflect the true combination (i.e., co-occurrence) correlation degree between the topics. The association strength standardization method used in the steps of this method is a measurement method for measuring the deviation between the observed co-occurrence frequency and the expected co-occurrence frequency under the independence assumption. Therefore, the associationstrength normalization method can eliminate the scale effect existing in co-occurrence data.

[0158] The combined association matrix C of the combined association degree between record topics calculated by the association strength standardization method includes the following steps:

[0159] S81: Set a threshold η and set the element values ​​less than η in the document-topic probability distribution matrix θ to 0, thereby filtering rare events. The formula is expressed as:

[0160]

[0161] Reasons and necessity for filtering rare events:

[0162] Since the association strength normalization method may have calculation bias when encountering rare events, in order to avoid the influence of rare events and obtain more accurate results, it is necessary to set a threshold for filtering rare events. Rare events are events with a very low probability of occurrence.

[0163] An example of a calculation bias when using the Association Strength Standardization method for rare events: If event A occurs 1 times, and event B also occurs 1 times, and both event A and event B occur only once, then they are both occurring simultaneously. This is expressed as: A = B = AB = 1. Then, using the Association Strength Standardization method, the probability of event A and event B occurring together is:

[0164]

[0165] Obviously, the probability value of event A and event B occurring together is calculated according to the association strength standardization method is the counterfactual, larger value.

[0166] For example, we set the threshold η to 0.01 and filter out rare events in the document-topic probability distribution matrix θ obtained in Example S62 based on η. The filtered matrix θ is:

[0167]

[0168] S82: Calculate the combined association matrix C of the combined association degree between record topics using the association strength standardization method:

[0169]

[0170] C is a symmetrical square matrix, and the calculation formula of the element value is:

[0171]

[0172] θ id is the element value in the document-topic probability distribution matrix θ, that is, the probability that topic i appears in a document d; θ jd is the element value in the document-topic probability distribution matrix θ, that is, the probability that topic j appears in a document d; ∑ d θ id θ jd is the probability that topic i and topic j appear together in the document collection, ∑ d θ id is the total probability of topic i appearing in the document collection; ∑ d θ jd is the total probability of topic j appearing in the document collection; then, in order to ensure that there is no node self-connection in the network subsequently constructed based on the combined correlation matrix C, the diagonal element values ​​of the combined correlation matrix C are returned to 0, that is:

[0173] cii =0

[0174] Finally, the processed proximity correlation matrix C is obtained.

[0175] For example, based on the document-topic probability distribution matrix θ obtained in Example S81, we use the association strength normalization method to calculate and return the diagonal element values ​​to zero to obtain the combined association matrix C:

[0176]

[0177] S9: Based on the proximity correlation matrix P and the combined correlation matrix C, a dual network with two network levels is constructed And for dual network Visualize; identify dual networks using multiple centrality analysis methods based on multiple centrality indicators and factor analysis Dual core technology, core combination technology, core adjacent technology and edge technology (in dual network In , each topic represents a technical subfield);

[0178] Dual Network By the hyperadjacency matrix express:

[0179]

[0180] Where I is the identity matrix, that is:

[0181]

[0182] In the super-adjacency matrix The unit matrix I in the non-diagonal position has no practical meaning and is only used to record and identify the one-to-one correspondence between the same nodes in two network layers.

[0183] The present invention constructs a dual network The proposed method steps can simultaneously embed multiple technology associations into a network-based model that encompasses different technologies and the associations between them, thereby studying the complex associations between technologies. Existing network-based technology association analysis methods all use single-layer network models and are therefore only suitable for exploring technology associations with only one type of association. However, the associations between different technologies are complex and include multiple types of associations. When faced with multiple associations, single-layer network models can only aggregate different association types into one association for study, thereby losing the association information contained between different association types. Dual networks can overcome this problem. Dual networks contain different network layers. The nodes in different network layers are the same, but the connection relationships between nodes are different. Nodes represent different topics, and the connection relationships between nodes represent the association relationships between topics. Therefore, the use of dual networks can be used to represent two associations between the same set of technologies, providing a foundation for analyzing complex association patterns between technologies and identifying core technologies.

[0184] The multiple centrality analysis method steps based on multiple centrality indicators and factor analysis adopted by the present invention can help innovation entities measure the relative importance of different technical sub-fields in the target technical field and identify core technologies. In the process of technological innovation, the recombination of knowledge elements in existing technical fields, or the reconfiguration of the combination of knowledge elements in technical fields that have already been combined together, is an important way to give birth to new technical fields and new technical solutions. Therefore, exploring the correlation and correlation patterns between technologies, and judging the relative importance of different technologies play an important role in the discovery of technological opportunities. This method step can judge the relative importance of technologies and core technologies in a group of technologies with dual correlation types through a multiple centrality analysis method based on multiple centrality indicators and factor analysis, thereby discovering potential important technological opportunities.

[0185] The multi-centrality analysis method employed in this invention, based on multiple centrality indices and factor analysis, is applicable across heterogeneous hierarchies and can simultaneously consider multiple centrality indices. As a structural characteristic, centrality can reveal the importance and influence of individual nodes within a multi-network. Existing multi-centrality analysis methods, such as multiplex rank and versatility, measure the importance of nodes by measuring their centrality within a multi-network. However, these methods are largely based on the assumption that all layers of a multi-network represent similar relationship types and have similar structures. This makes them unsuitable for multi-networks where relationship types vary significantly across layers. Furthermore, existing multi-centrality analysis methods can only consider a single centrality indicator within each layer and fail to account for the different aspects of centrality reflected by different centrality indicators. The multi-centrality analysis method employed in this invention, based on multiple centrality indices and factor analysis, overcomes these two issues with existing methods. It is not only applicable to multi-networks with heterogeneous hierarchies but can also simultaneously consider the degree of positional centrality represented by multiple centralities within each layer, resulting in a more versatile and accurate multi-centrality analysis method.

[0186] Specifically, the dual network It consists of two network layers, with the same nodes within them, representing the K topics obtained by S6. The links between nodes within the two network layers record the degrees of association corresponding to different associations between the same set of nodes, namely, the proximity association degree and the combined association degree between the K topics measured by S7 and S8, respectively. In addition to the links within the two network layers, there are also links between the two network layers. The link relationship between the two network layers records the one-to-one correspondence between the nodes representing the same technology (i.e., the topics representing the technology) in the two network layers.

[0187] For example, a dual network is constructed based on the proximity correlation matrix P obtained in the S72 example and the combined correlation matrix C obtained in the S82 example. By the hyperadjacency matrix Expressed as:

[0188]

[0189] Then, for the dual network Specifically, the dual network constructed based on the Python toolkit pymnet is Visualize the constructed dual network like Figure 3 shown.

[0190] Identify dual networks using a multi-centrality analysis method based on multiple centrality indices and factor analysis The core technology steps:

[0191] S91: Calculate the strength of each topic i in the proximity network layer among the K topics The calculation formula is: Calculate the strength of each topic i in the combined network layer among the K topics The calculation formula is: Using the Python toolkit NetworkX to calculate the dual network built by S9 The feature vector centrality of each topic i in the proximity network layer and the combination network layer in the K topics and Current betweenness centrality Hehe Current proximity to centrality and

[0192] The current betweenness centrality and current proximity centrality used in this step can achieve more accurate measurement of betweenness centrality and proximity centrality in networks with technical correlation properties. In networks with technical correlation properties, the edges between each network node represent the propagation path of technical information between nodes. The simplest and most widely used calculations of proximity centrality and betweenness centrality are based on the shortest path, but for networks with technical correlation properties, technical information does not only flow and propagate along the shortest path. For example, in the dual network constructed by this method, In this example, the topics represented by the nodes consist of technical information. This technical information does not have a known ideal propagation path and therefore spreads in a random walk. In this type of network, proximity and betweenness centrality measures based on the shortest path can produce erroneous results. To address this issue, this method uses current proximity centrality and current betweenness centrality, which are applicable to networks with similar information diffusion processes, to obtain more accurate proximity and betweenness centrality measurements. These two current centrality measures still share the same intuition as traditional proximity and betweenness centrality measures, but more fully consider the process by which information flows and propagates through the network, just like the current in a power grid.

[0193] Among them, the intensity Represents the sum of the association degrees between any topic i and other topics j in the K topics in the p network layer (i.e., the proximity network layer); pij is the association degree between topic i and topic j in the p network layer (i.e., the proximity network layer); higher strength This means that topic i is more closely related to other topics in the p network layer (i.e., the proximity network layer);

[0194] Among them, the intensity Represents the sum of the link weights between any topic i and other topics j in the K topics in the c network layer (i.e., the combined network layer); cij is the degree of association between topic i and topic j in the c network layer (i.e., the combined network layer); higher strength This means that topic i is more closely related to other topics in the c network layer (i.e., the combined network layer);

[0195] Among them, the eigenvector centrality of each topic i in the p network layer (i.e., the proximity network layer) corresponding to the proximity association matrix P is obtained by the eigenvector_centrality function in the Python toolkit NetworkX. Eigenvector centrality The larger the value, the greater the influence of topic i in the p network layer (i.e., the proximity network layer);

[0196] Among them, the eigenvector centrality of each topic i in the c network layer (i.e., the combined network layer) corresponding to the combined correlation matrix C is obtained by the eigenvector_centrality function in the Python toolkit NetworkX Eigenvector centrality The larger the value, the greater the influence of topic i in the c network layer (i.e., the combined network layer);

[0197] Among them, the current betweenness centrality of each topic i in the p network layer (i.e., the proximity network layer) corresponding to the proximity association matrix P is obtained by the current_flow_betweenness_centrality function in the Python toolkit NetworkX Current betweenness centrality The larger it is, the more important the topic i is to the p network layer (i.e., the proximity network layer);

[0198] Among them, the current betweenness centrality of each topic i in the c network layer (i.e., the combined network layer) corresponding to the combined correlation matrix C is obtained by the current_flow_betweenness_centrality function in the Python toolkit NetworkX Current betweenness centrality The larger the value of (i), the more important the topic i is for the c network layer (i.e., the combined network layer);

[0199] Among them, the current closeness centrality of each topic i in the p network layer (i.e., the proximity network layer) corresponding to the proximity association matrix P is obtained by the current_flow_closeness_centrality function in the Python toolkit NetworkX. Current proximity to centrality The larger the value, the closer the relationship between topic i and other topics is at the p network layer (i.e., the proximity network layer);

[0200] Among them, the current closeness centrality of each topic i in the c network layer (i.e., the combined network layer) corresponding to the combined correlation matrix C is obtained by the current_flow_closeness_centrality function in the Python toolkit NetworkX Current proximity to centrality The larger the value, the closer the relationship between topic i and other topics is at the c-network layer (i.e., the combined network layer);

[0201] From this, the 8 centralities of each topic i among the K topics are calculated:

[0202] For example: the dual network constructed in the S9 example We calculated eight centrality variables for each of the 50 topics i, and some of the results are as follows:

[0203]

[0204] S92: For each topic i among the K topics obtained in S91 As input data, we use the factor function of stata software to perform factor analysis (factor analysis is a data dimensionality reduction method that retains important information in the data set. Through factor analysis, multiple variables can be simplified into several unrelated factors that can explain the original variables). Finally, we get the centrality variables that can explain the four p network layers (proximity network layers) Commonality factor f p And the corresponding factor score f of each topic i in the K topics on the factor fp p (i), factor score f p The value of (i) can comprehensively reflect the centrality of the position of topic i in the p network layer (proximity network layer) represented by the four centrality variables, and can explain the centrality of the four centrality variables in the c network layer (combination network layer). Commonality factor f c And each topic i among K topics has a factor fc The corresponding factor score f c (i), factor score f c The value of (i) can comprehensively reflect the centrality of the position of the subject i represented by the four centrality variables in the c network layer (combined network layer); each subject i in the dual network The centrality in can be expressed as a vector Represents subject i in the dual network The overall centrality of the network position.

[0205] For example, using the factor function of stata software, setting the parameter of the control factor analysis method to the principal component (pf), we can perform factor analysis on the eight centrality variables calculated in the S91 example, and finally obtain the factor score f for each topic i in the 50 topics. p (i) and f c (i), the results are as follows:

[0206]

[0207]

[0208] By vector Expressed as:

[0209]

[0210] S93: Setting the factor score f for the partitioned topic i p (i) High and low thresholds γ p , set the factor score f of the partition topic i c (i) High and low thresholds γ c , which is used to judge the centrality of the network position of topic i in the proximity network layer and the combination network layer respectively; specifically, the threshold γ in the proximity network layer p It can be set as the factor score f of K topics p (i) The median, third quantile, etc.; the threshold γ in the combined network layer c It can be set as the factor score f of K topics c (i) The median, third quantile, etc.

[0211] For example: set the threshold γ p Set to 50 topic factor scores f p (i), the threshold γc is set to the median of 50 topic factor scores f c The median of (i). Right now:

[0212] γ p =0.045,γc =0.168

[0213] S94: factor score f p (i) As the x-axis, the factor score f c (i) As the y-axis, construct a two-dimensional coordinate system and based on the vector obtained by S92 Construct a two-dimensional space, based on the two thresholds γ set by S93 p and γ c Divide the two-dimensional space into four spatial regions to identify the dual network Dual core technology, core combination technology, core adjacent technology and edge technology (in dual network In , each topic represents a technical subfield);

[0214] Dual-core technologies are topics that demonstrate high centrality in both the proximity and combination layers. The technologies represented by these topics rely on knowledge and foundations that are generally related to the technologies represented by other topics. This reduces the cost of technology combination and demonstrates greater potential for combination.

[0215] Core combinatorial technologies refer to topics with low centrality in the proximity network layer but high centrality in the combinatorial network layer. These technologies may have high knowledge barriers, increasing learning and cognitive costs. Therefore, technologies represented by other topics tend to directly combine these technologies with themselves to generate new solutions to technical problems. Furthermore, these technologies may also be formed by combining a wide range of other technical elements.

[0216] Edge technologies are topics that exhibit low centrality in both the proximity and combination layers. These topics may be emerging technologies, still in the early stages of development, focusing on innovative new theories and techniques not explored by other topics. Furthermore, these topics may represent outdated technologies and therefore require further in-depth evaluation to determine their continued value.

[0217] Core proximity technologies refer to topics with high centrality in the proximity network layer but low centrality in the combination network layer. Not all technical knowledge can be combined to solve new technical problems. For example, in biotechnology, not all protein pairs can be combined to form compounds that effectively attack diseases. Therefore, in such cases, technical knowledge from other topics must be integrated and refined before it can be applied to solve specific technical problems. Because the knowledge structure of the new technology formed through integration and refinement is partially derived from other technologies, it will have a certain degree of proximity to other related technologies.

[0218] For example: Based on the S92 example, we get the vector of 50 topic factor scores And the threshold γ set in the S93 example p and γ c , a two-dimensional space with four spatial regions is constructed, thereby distinguishing four types of technologies. The results are shown in Figure 4 . The first quadrant (factor score f p (i) High and factor score f c (i) high) is dual core technology; the second quadrant (factor score f p (i) Low and factor score f c (i) high) is the core combination technology; the third quadrant (factor score f p (i) Low and factor score f c (i) low) is marginal technology; the fourth quadrant (factor score f p (i) High and factor score f c (i) Low) is the core proximity technology. Each sample point in the two-dimensional space is the vector corresponding to a topic In the figure, different topics are identified by the label style i.

[0219] Regarding the embodiments of the present invention, it should also be noted that, in the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0220] The above description is only a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. The scope of protection of the present invention shall be subject to the scope of protection of the claims. Although the present invention has been disclosed as above with preferred embodiments, it is not intended to limit the present invention. Any technician familiar with this profession can make some changes or modifications to equivalent embodiments of equivalent changes using the technical content disclosed above without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of the technical solution of the present invention.

Claims

1. A core technology identification method based on dual technology relevance, characterized by: The following steps are involved: Extract technical keywords based on technical documents, construct a technical search formula, and obtain D original technical documents from the technical database based on the technical search formula; performing sentence segmentation and a first text preprocessing on the text content in each of the D original technical documents to obtain preprocessed technical document sentences, and training a word embedding model based on the preprocessed technical document sentences to obtain word embeddings corresponding to the terms contained in the D original technical documents; Performing a second text preprocessing on the D original technical documents to obtain technical documents recorded in a bag-of-words format; Based on the word embedding and the technical documents recorded in the bag-of-words form, topic modeling is performed using the ETM model to obtain three results, including a topic-term probability distribution matrix β, a document-topic probability distribution matrix θ, and a topic embedding matrix α; Based on the topic embedding matrix α, the cosine similarity calculation formula is used to measure the proximity between two topic embeddings, and the proximity association matrix P that records the proximity association strength between the topics is obtained. Based on the document-topic probability distribution matrix θ, the combined association matrix C that records the combined association strength between the topics is calculated using the association strength normalization method. Based on the proximity association matrix P and the combined association matrix C, a dual network with two network levels is constructed. And for dual network Visualize; identify dual networks using multiple centrality analysis methods based on multiple centrality indicators and factor analysis Dual-core technology, core combination technology, core adjacent technology and edge technology in the industry; Dual Network By the hyperadjacency matrix express: in, The dual core technologies refer to topics that exhibit high centrality in both the proximity network layer and the combined network layer; The core combination technology refers to a topic that has low centrality in the proximity network layer but high centrality in the combination network layer; The edge technologies refer to topics that exhibit low centrality in both the proximity network layer and the combined network layer; The core proximity technology refers to a topic that has high centrality in the proximity network layer but low centrality in the combination network layer.

2. The core technology identification method based on dual technology relevance according to claim 1, characterized in that: The word embedding model is a Word2Vec model or a glove model.

3. The core technology identification method based on dual technology relevance according to claim 1, characterized in that: The specific steps of sentence segmentation and the first text preprocessing include: The Python toolkit NLTK is used to segment the text content of each original technical document into technical document sentences with sentences as units; The python toolkit spaCy is used to perform the first text preprocessing on the technical document after sentence segmentation to obtain the preprocessed technical document sentences.

4. The core technology identification method based on dual technology relevance according to claim 3 is characterized by: The first text preprocessing process is as follows: first, numbers, punctuation marks, and words with a length of less than 3 characters in the text are deleted; then, the remaining words are restored to their parts of speech and converted to lowercase; finally, sentences with a length less than the "window size" parameter value set by the subsequent Word2Vec model are deleted to obtain preprocessed technical document sentences.

5. The core technology identification method based on dual technology relevance according to claim 1 is characterized in that: The second text preprocessing uses the Python toolkit spaCy. The processing process includes deleting numbers, punctuation marks, stop words, terms with a character length of less than 3, and non-noun terms in the original technical documents, restoring the remaining terms and converting them to lowercase, deleting terms with a document frequency of less than 3 in the technical document collection, and finally obtaining the preprocessed technical documents recorded in the form of a bag of words with a dictionary size of V.

6. The core technology identification method based on dual technology relevance according to claim 1, characterized in that: Based on the word embedding and the technical documents recorded in the bag-of-words format, a topic modeling process is performed using the ETM model to obtain three results, including a topic-term probability distribution matrix β, a document-topic probability distribution matrix θ, and a topic embedding matrix α. The specific steps are as follows: Using the word embeddings and the technical documents recorded in the bag-of-words format as input data for training the ETM model, the optimal setting value of the parameter K of the number of topics in the ETM model is determined through repeated experiments; The technical documents recorded in the word embedding and bag-of-words format are used as model inputs, and topic modeling is performed based on the ETM model parameter value topic number K, resulting in three matrix output results: Topic-term probability distribution matrix β: Row vector β k· is the probability distribution of topic k over all terms, where k is the kth topic among K topics; Document-topic probability distribution matrix θ: Row vector θ d· is the probability distribution of document d on all topics, where d is the d-th document in D topics; Topic embedding matrix α: Column vector α ·k is the topic embedding corresponding to topic k, where k is the kth topic among K topics.

7. The core technology identification method based on dual technology relevance according to claim 1, characterized in that: The specific steps for using the cosine similarity calculation formula to measure the proximity between two topic embeddings and obtain the proximity correlation matrix P that records the proximity correlation strength between the topics are as follows: Use the cosine similarity calculation formula to obtain the element value in the proximity association matrix P; P is a symmetric square matrix, and the calculation formula of the element value is: Among them, α i is the topic embedding corresponding to topic i, α j is the topic embedding corresponding to topic j, ||α i || is the L-2 norm of the topic embedding corresponding to topic i, ||α j || is the L-2 norm of the topic embedding corresponding to topic j, p ij and p ji is the proximity correlation degree between topic i and topic j; The range of element values ​​in the proximity correlation matrix P is scaled from [-1, 1] to [0, 1] by standardization. The standardization calculation formula is: p' ij is the normalized matrix element value; The diagonal element values ​​of the proximity correlation matrix P are returned to 0, that is: p' ii ＝0 Finally, the processed proximity correlation matrix P is obtained.

8. The core technology identification method based on dual technology relevance according to claim 1 is characterized in that The specific steps for calculating the combined association matrix C that records the combined association strength between topics based on the document-topic probability distribution matrix θ using the association strength standardization method are as follows: Set a threshold η and set the element value less than η in the document-topic probability distribution matrix θ to 0, thereby filtering rare events. The formula is expressed as: The combined association matrix C of the combined association strength between record topics is calculated using the association strength standardization method: C is a symmetrical square matrix, and the calculation formula of the element value is: θ id is the element value in the document-topic probability distribution matrix θ, that is, the probability that topic i appears in document d; θ jd is the element value in the document-topic probability distribution matrix θ, that is, the probability that topic j appears in a document d; ∑ d θ id θ jd is the probability that topic i and topic j appear together in the document collection, ∑ d θ id is the total probability of topic i appearing in the document collection; ∑ d θ jd is the total probability of topic j appearing in the document collection; The diagonal element values ​​of the combined correlation matrix C are returned to zero, and the processed combined correlation matrix C is finally obtained. The return-to-zero processing formula is: c ii ＝0。 9. The core technology identification method based on dual technology relevance according to claim 1, characterized in that: Dual networks were identified using a multi-centrality analysis method based on multiple centrality indices and factor analysis. The steps of dual core technology, core combination technology, core adjacent technology and edge technology in the process include: Calculate the strength of each topic i in the proximity network layer among the K topics The calculation formula is: Calculate the strength of each topic i in the combined network layer among the K topics The calculation formula is: The dual network is calculated using the python toolkit NetworkX The feature vector centrality of each topic i in the proximity network layer and the combination network layer in the K topics and Current betweenness centrality and Current proximity to centrality and p ij is the element value in the proximity correlation matrix P, c ij is the element value in the combined incidence matrix C; Among them, the eigenvector centrality of each topic i in the p network layer corresponding to the proximity association matrix P is obtained by the eigenvector_centrality function in the Python toolkit NetworkX The eigenvector_centrality function in the Python toolkit NetworkX is used to obtain the eigenvector centrality of each topic i in the c network layer corresponding to the combined correlation matrix C. The current betweenness centrality of each topic i in the p network layer corresponding to the proximity association matrix P is obtained through the current_flow_betweenness_centrality function in the Python toolkit NetworkX The current betweenness centrality of each topic i in the c network layer corresponding to the combined correlation matrix C is obtained through the current_flow_betweenness_centrality function in the Python toolkit NetworkX The current closeness centrality of each topic i in the p network layer corresponding to the proximity association matrix P is obtained through the current_flow_closeness_centrality function in the Python toolkit NetworkX The current closeness centrality of each topic i in the c network layer corresponding to the combined correlation matrix C is obtained through the current_flow_closeness_centrality function in the Python toolkit NetworkX For each topic i among the K topics As input data, factor analysis was performed using the factor function of stata software to obtain the centrality variables that can explain the four layers in the proximity network. Commonality factor f p And each topic i among K topics has a factor f p The corresponding score f p (i) and the centrality variables that can explain the four centrality variables at the combined network level Commonality factor f c And each topic i among K topics has a factor f c The corresponding factor score f c (i), each subject i in the dual network The centrality in is represented as a vector Set the factor score f for dividing topic i p (i) High and low thresholds γ p , set the factor score f of the partition topic i c (i) High and low thresholds γ c , which is used to judge the degree of centrality of the network position of subject i in the proximity network layer and the combination network layer respectively; The factor score f p (i) As the x-axis, the factor score f c (i) As the y-axis, construct a two-dimensional coordinate system, and based on the vector Construct a two-dimensional space based on two thresholds γ p and γ c Divide the two-dimensional space into four spatial regions to identify the dual network Dual-core technology, core combination technology, core adjacent technology and edge technology.

10. The core technology identification method based on dual technology relevance according to claim 9, characterized in that: The threshold γ p Set to the median or third quantile of the factor scores of K topics in the proximity network layer; the threshold γ c Set to the median or third quantile of the factor scores of the K topics in the combined network layer.

Images