Scientific and technological achievement management platform and method based on data intelligence

Abstract

The invention relates to a scientific and technological achievement management platform and method based on data intelligence. The method comprises the following steps: collecting scientific and technological achievement text data and achievement demand information at an achievement supplier uploading port and an achievement demander publishing port respectively; a data processing and semantic understanding algorithm based on artificial intelligence and deep learning is introduced into the achievement supply-demand matching server to perform semantic coding and one-way semantic matching of segment-by-segment granularity on the scientific and technological achievement text data and the achievement demand information; therefore, the matching degree between the scientific and technological achievement text data and the achievement demand information is determined, and a matching result is returned. Therefore, whether the scientific and technological achievements of the achievement supplier are returned to the achievement demander or not can be determined based on the matching degree between the segment granularity semantics of the scientific and technological achievement text and the achievement demand information semantics, so that the intelligent degree of scientific and technological achievement management is improved, and a more efficient and accurate solution is provided for scientific and technological achievement management and conversion.

Description

Technical Field

[0001] The present application relates to the technical field of transformation of scientific and technological achievements, and specifically, to a scientific and technological achievement management platform and method based on data intelligence. Background Art

[0002] Many third-party organizations have emerged in the market, which build bridges between supply and demand by building management platforms, and technical managers are responsible for the specific transformation work. However, in the specific docking process, since both parties involve multiple fields of achievements, the workload of manual screening and matching is large, time-consuming, and subject to significant subjective influences, it is difficult to achieve accurate matching between the two parties, which has brought certain difficulties to the transformation of scientific and technological achievements.

[0003] In view of the above technical problems, the invention with publication number CN114780673A discloses a scientific and technological achievement management method and a scientific and technological achievement management platform based on field matching, which can segment the scientific research achievement text data and mark its corresponding attribute information, and then match the attribute information after segmentation with the field keyword library to determine the target field keyword library. In this way, other segmentations are searched by using the attribute information of these matching segmentations, and it is determined whether these segmentations belong to the target field keywords, thereby achieving the matching of scientific and technological achievement text data and demanders.

[0004] However, although the management method adopted by the scientific and technological achievement management platform based on field matching has improved the intelligent level of scientific and technological achievement management to a certain extent, the management platform is highly dependent on keyword matching technology. By relying on keywords to match the text of scientific research results with the demand side, if there is a deviation in the keyword extraction or matching algorithm, it may lead to inaccurate matching results, thereby affecting the effective connection between scientific and technological achievements and demand sides. At the same time, the scheme relies on the use of existing field keyword libraries for matching, but these keyword libraries may not cover all emerging technologies or interdisciplinary terms, limiting the system's ability to handle scientific and technological achievements in new or marginal fields. In addition, using keywords to represent scientific and technological achievement text data for matching will cause a large amount of effective information loss in terms of information volume, resulting in a reduction in the matching accuracy between the demand side and the scientific and technological achievements.

[0005] Therefore, an optimized scientific and technological achievement management platform is desired. Summary of the invention

[0006] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] In the first aspect, the present application provides a scientific and technological achievement management platform based on data intelligence, the platform comprising: The achievement supplier upload port is used to upload the scientific and technological achievement text data and store the scientific and technological achievement text data in the scientific and technological achievement database; The result demander release port is used to upload the result demand information and store the result demand information in the demand database; A result supply-demand matching server is used to calculate the semantic matching degree between the scientific and technological result text data and the result demand information to determine whether to recommend a result supplier to the result demander; The achievement supply-demand matching server includes: A scientific and technological achievement segment granularity semantic coding module is used to perform segment granularity-based inter-segment context semantic association coding on the scientific and technological achievement text data to obtain a sequence of scientific and technological achievement segment granularity semantic coding feature vectors; A scientific and technological achievement segment granularity semantic saliency optimization module, used for inputting the sequence of the scientific and technological achievement segment granularity semantic coding feature vectors into the global context-based semantic saliency optimization module to obtain a sequence of optimized scientific and technological achievement segment granularity semantic coding feature vectors; An achievement requirement semantic coding module, used for semantically coding the achievement requirement information to obtain an achievement requirement semantic coding feature vector; A one-way interactive matching module for scientific and technological achievements and demand information is used to interactively match the sequence of the optimized scientific and technological achievements segment granularity semantic coding feature vectors and the achievement demand semantic coding feature vectors based on one-way granularity scanning to obtain one-way matching result information of scientific and technological achievements and demand information; The matching result generation module is used to generate a matching result based on the one-way matching result information of the scientific and technological achievement-demand information, and the matching result is used to indicate whether the matching degree between the scientific and technological achievement text data and the achievement demand information exceeds a preset threshold.

[0008] Optionally, the scientific and technological achievement segment granularity semantic encoding module is used to: after segmenting the scientific and technological achievement text data, obtain a sequence of the scientific and technological achievement segment granularity semantic encoding feature vectors through an inter-segment context semantic association encoder including a segment semantic embedding encoding layer.

[0009] Optionally, the scientific and technological achievement segment granularity semantic saliency optimization module includes: a data calculation unit, which is used to respectively calculate the mean and maximum values ​​of each scientific and technological achievement segment granularity semantic coding feature vector in the sequence of the scientific and technological achievement segment granularity semantic coding feature vector to obtain a scientific and technological achievement segment granularity semantic global representation vector composed of multiple vector means and a scientific and technological achievement segment granularity semantic salient representation vector composed of multiple vector maximum values; a first convolution coding unit, which is used to perform one-dimensional convolution coding on the scientific and technological achievement segment granularity semantic global representation vector and then pass it through The activation function is used to obtain a global semantic representation vector of the segment granularity of the activated expression of scientific and technological achievements; the second convolutional coding unit is used to perform matrix multiplication of the global semantic representation vector of the segment granularity of the activated expression of scientific and technological achievements with the first trainable linear transformation weight matrix after one-dimensional convolution coding to obtain a feature vector of the global semantic activation representation of the segment granularity of the scientific and technological achievements; the activation unit is used to perform one-dimensional convolution coding on the semantic salient representation vector of the segment granularity of the scientific and technological achievements and then perform matrix multiplication of the vector with the first trainable linear transformation weight matrix to obtain a feature vector of the global semantic activation representation of the segment granularity of the scientific and technological achievements. The activation function is used to obtain an activation expression of the scientific and technological achievement segment granularity semantic prominent representation vector; the third convolution coding unit is used to perform matrix multiplication with the second trainable linear transformation weight matrix after the activation expression of the scientific and technological achievement segment granularity semantic prominent representation vector is once again subjected to one-dimensional convolution coding to obtain a scientific and technological achievement segment granularity prominent semantic activation representation feature vector; the vector fusion unit is used to fuse the scientific and technological achievement segment granularity global semantic activation representation feature vector and the scientific and technological achievement segment granularity prominent semantic activation representation feature vector to obtain the scientific and technological achievement segment granularity global-prominent semantic association activation feature vector, and then perform nonlinear activation processing on the scientific and technological achievement segment granularity global-prominent semantic association activation feature vector to obtain the scientific and technological achievement segment granularity global-prominent semantic association weight feature vector; the weight multiplication unit is used to use the scientific and technological achievement segment granularity global-prominent semantic association weight feature vector as the weight, perform positional point multiplication on the sequence of the scientific and technological achievement segment granularity semantic coding feature vectors and add the sequence of the scientific and technological achievement segment granularity semantic coding feature vectors to obtain the sequence of the optimized scientific and technological achievement segment granularity semantic coding feature vectors.

[0010] Optionally, the vector fusion unit is used to: fuse the global semantic activation representation feature vector of the scientific and technological achievement segment granularity and the prominent semantic activation representation feature vector of the scientific and technological achievement segment granularity to obtain the global-prominent semantic association activation feature vector of the scientific and technological achievement segment granularity; respectively use the hyperbolic tangent function and The function activates the global-salient semantic association activation feature vector of the scientific and technological achievement segment granularity to obtain the global-salient feature hyperbolic tangent activation semantic representation vector of the scientific and technological achievement segment granularity and the global-salient feature S-type activation semantic representation vector of the scientific and technological achievement segment granularity; multiplies the global-salient feature hyperbolic tangent activation semantic representation vector of the scientific and technological achievement segment granularity and the global-salient feature S-type activation semantic representation vector of the scientific and technological achievement segment granularity by position point to obtain the global-salient semantic association weight feature vector of the scientific and technological achievement segment granularity.

[0011] Optionally, the scientific and technological achievement-demand information one-way interactive matching module is used to: input the sequence of the optimized scientific and technological achievement segment granularity semantic coding feature vector and the achievement demand semantic coding feature vector into the one-way attention granularity scanning interactive matching module to obtain the scientific and technological achievement-demand information one-way matching result representation vector as the scientific and technological achievement-demand information one-way matching result information.

[0012] Optionally, the scientific and technological achievement-demand information one-way interactive matching module includes: a semantic association unit, which is used to calculate the semantic association between each optimized scientific and technological achievement segment granularity semantic coding feature vector in the sequence of optimized scientific and technological achievement segment granularity semantic coding feature vectors and the achievement demand semantic coding feature vector to obtain a sequence of scientific and technological achievement-demand information one-way matching semantic measurement coefficients; a normalization processing unit, which is used to normalize the sequence of scientific and technological achievement-demand information one-way matching semantic measurement coefficients to obtain a sequence of scientific and technological achievement-demand information one-way matching semantic measurement weights; a vector weighting unit, which is used to use the sequence of scientific and technological achievement-demand information one-way matching semantic measurement weights as weights to calculate the weighted sum of the sequence of optimized scientific and technological achievement segment granularity semantic coding feature vectors to obtain the scientific and technological achievement-demand information one-way matching interactive reshaping feature vector; a differential feature vector calculation unit, which is used to calculate the differential feature vector between the scientific and technological achievement-demand information one-way matching interactive reshaping feature vector and the achievement demand semantic coding feature vector as the scientific and technological achievement-demand information one-way matching result representation vector.

[0013] Optionally, the semantic relevance unit is used to: input the optimized scientific and technological achievement segment granularity semantic coding feature vector and the achievement requirement semantic coding feature vector into the feature union module for cascade processing to obtain the scientific and technological achievement-requirement information semantic joint feature vector; calculate the matrix multiplication of the scientific and technological achievement-requirement information semantic joint feature vector and the parameter matrix, and then add the obtained feature vector to the bias vector by position to obtain the linear transformation scientific and technological achievement-requirement information semantic joint feature vector; use The function activates the linear transformation scientific and technological achievement-demand information semantic joint feature vector to obtain the scientific and technological achievement-demand information one-way matching semantic measurement coefficient.

[0014] Optionally, the matching result generation module is used to: input the scientific and technological achievement-demand information one-way matching result representation vector into a classifier-based matching result generator to obtain a matching result, and the matching result is used to indicate whether the matching degree between the scientific and technological achievement text data and the achievement demand information exceeds a preset threshold.

[0015] In the second aspect, the present application provides a method for managing scientific and technological achievements based on data intelligence, the method comprising: Upload scientific and technological achievements text data, and store the scientific and technological achievements text data in the scientific and technological achievements database; Upload the achievement demand information and store the achievement demand information in the demand database; Calculating the semantic matching degree between the scientific and technological achievement text data and the achievement demand information to determine whether to recommend an achievement supplier to the achievement demander; The process of calculating the semantic matching degree between the scientific and technological achievement text data and the achievement demand information to determine whether to recommend an achievement supplier to the achievement demander includes: Performing segment-granularity-based inter-segment context semantic association coding on the scientific and technological achievement text data to obtain a sequence of scientific and technological achievement segment-granularity semantic coding feature vectors; Inputting the sequence of the scientific and technological achievement segment granularity semantic coding feature vectors into a global context-based semantic significance optimization module to obtain a sequence of optimized scientific and technological achievement segment granularity semantic coding feature vectors; Semantically encoding the achievement requirement information to obtain an achievement requirement semantic encoding feature vector; Perform interactive matching based on unidirectional granularity scanning on the sequence of the optimized scientific and technological achievement segment granularity semantic coding feature vectors and the achievement requirement semantic coding feature vectors to obtain scientific and technological achievement-requirement information unidirectional matching result information; A matching result is generated based on the scientific and technological achievement-demand information one-way matching result information, and the matching result is used to indicate whether the matching degree between the scientific and technological achievement text data and the achievement demand information exceeds a preset threshold.

[0016] Optionally, the scientific and technological achievement text data is encoded based on segment granularity inter-segment contextual semantic association coding to obtain a sequence of scientific and technological achievement segment granularity semantic coding feature vectors, including: after segmenting the scientific and technological achievement text data, passing it through an inter-segment contextual semantic association encoder including a segment semantic embedding coding layer to obtain a sequence of scientific and technological achievement segment granularity semantic coding feature vectors.

[0017] The above technical solution is adopted to collect the text data of scientific and technological achievements and the information on achievement demand at the upload port of the achievement supplier and the release port of the achievement demander, respectively, and introduce the data processing and semantic understanding algorithm based on artificial intelligence and deep learning in the achievement supply-demand matching server to semantically encode the text data of scientific and technological achievements and the achievement demand information and perform one-way semantic matching at a segment-by-segment granularity, so as to determine the matching degree between the text data of scientific and technological achievements and the achievement demand information, and then return the matching result. In this way, it is possible to determine whether to return the scientific and technological achievements of the achievement supplier to the achievement demander based on the matching degree between the segment-granularity semantics of the scientific and technological achievement text and the semantics of the achievement demand information, thereby improving the intelligent level of scientific and technological achievement management and bringing more efficient and accurate solutions to the management and transformation of scientific and technological achievements.

[0018] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings: Figure 1 It is a block diagram of a scientific and technological achievement management platform based on data intelligence according to an exemplary embodiment.

[0020] Figure 2 It is a flow chart of a method for managing scientific and technological achievements based on data intelligence according to an exemplary embodiment.

[0021] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment.

[0022] Figure 4 It is an application scenario diagram of a scientific and technological achievement management platform based on data intelligence according to an exemplary embodiment. DETAILED DESCRIPTION

[0023] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0024] It should be understood that the various steps described in the method implementation of the present application can be performed in different orders and / or performed in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0025] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0026] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0027] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0028] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0029] The specific implementation of the present application is described in detail below with reference to the accompanying drawings.

[0030] Figure 1 FIG. 1 is a block diagram of a scientific and technological achievement management platform based on data intelligence according to an exemplary embodiment. Figure 1 As shown, the scientific and technological achievement management platform 100 includes: The achievement supplier upload port 101 is used to upload the scientific and technological achievement text data and store the scientific and technological achievement text data in the scientific and technological achievement database; The achievement demander releases port 102, which is used to upload achievement demand information and store the achievement demand information in a demand database; The achievement supply-demand matching server 103 is used to calculate the semantic matching degree between the scientific and technological achievement text data and the achievement demand information to determine whether to recommend an achievement supplier to the achievement demander; The achievement supply-demand matching server 103 includes: The scientific and technological achievement segment granularity semantic coding module 1031 is used to perform segment granularity-based inter-segment context semantic association coding on the scientific and technological achievement text data to obtain a sequence of scientific and technological achievement segment granularity semantic coding feature vectors; The scientific and technological achievement segment granularity semantic saliency optimization module 1032 is used to input the sequence of the scientific and technological achievement segment granularity semantic coding feature vectors into the global context-based semantic saliency optimization module to obtain a sequence of optimized scientific and technological achievement segment granularity semantic coding feature vectors; The achievement requirement semantic coding module 1033 is used to semantically encode the achievement requirement information to obtain an achievement requirement semantic coding feature vector; A one-way interactive matching module 1034 for scientific and technological achievements and demand information is used to interactively match the sequence of the optimized scientific and technological achievements segment granularity semantic coding feature vectors and the achievement demand semantic coding feature vectors based on one-way granularity scanning to obtain one-way matching result information of scientific and technological achievements and demand information; The matching result generation module 1035 is used to generate a matching result based on the scientific and technological achievement-demand information one-way matching result information, and the matching result is used to indicate whether the matching degree between the scientific and technological achievement text data and the achievement demand information exceeds a preset threshold.

[0031] In view of the above technical problems, in the technical solution of the present application, a scientific and technological achievement management platform based on data intelligence is proposed, which can collect scientific and technological achievement text data and achievement demand information through the upload port of the achievement supplier and the release port of the achievement demander, and introduce data processing and semantic understanding algorithms based on artificial intelligence and deep learning in the achievement supply-demand matching server to semantically encode the scientific and technological achievement text data and the achievement demand information and perform one-way semantic matching at a segment-by-segment granularity, so as to determine the matching degree between the scientific and technological achievement text data and the achievement demand information, and thus return the matching result. In this way, it is possible to determine whether to return the scientific and technological achievements of the achievement supplier to the achievement demander based on the matching degree between the segment-granularity semantics of the scientific and technological achievement text and the semantics of the achievement demand information, thereby improving the intelligence level of scientific and technological achievement management, and avoiding the information loss and low matching accuracy caused by the keyword matching method by matching the full text of the scientific research achievement text segment by segment, and at the same time, it can effectively solve the problem that the existing field keyword library may not cover all emerging technologies or interdisciplinary terms and limit the ability to transform scientific and technological achievements, bringing more efficient and accurate solutions to scientific and technological achievement management and transformation.

[0032] Specifically, in the technical solution of the present application, first, the scientific and technological achievement text data is uploaded at the upload port of the achievement supplier, and the scientific and technological achievement text data is stored in the scientific and technological achievement database; the achievement demand information is uploaded at the release port of the achievement demander, and the achievement demand information is stored in the demand database. Next, considering that the scientific and technological achievement text data usually contains rich scientific and technological achievement semantic information, and this information may be distributed in different parts or paragraphs of the text. Therefore, in order to be able to decompose the text data into smaller units that are easier to analyze and understand, so as to more comprehensively capture the full-text semantic content of the scientific and technological achievement text data and avoid information omissions and confusion, in the technical solution of the present application, the scientific and technological achievement text data is segmented and then processed through an inter-segment context semantic association encoder containing a segment semantic embedding coding layer to obtain a sequence of scientific and technological achievement segment granularity semantic coding feature vectors. It should be understood that different paragraphs in the scientific and technological achievement text data often have intrinsic connections. Through the processing of the inter-segment contextual semantic association encoder containing the segment semantic embedding coding layer, the segment semantic embedding coding layer can be used to embed and map each paragraph in the scientific and technological achievement text data into the same semantic high-dimensional space, and the embedded coding semantic information of each paragraph can be captured. Then, the inter-segment contextual semantic association encoder is used to help model and learn the contextual semantic association between different paragraphs in the text, so as to better understand the overall semantic structure of the text. By considering the association between paragraphs, the accuracy and coherence of semantic representation can be improved, which helps to accurately capture the semantic information in the entire scientific and technological achievement text data.

[0033] In one embodiment of the present application, the scientific and technological achievement segment granularity semantic encoding module 1031 is used to: after segmenting the scientific and technological achievement text data, obtain a sequence of the scientific and technological achievement segment granularity semantic encoding feature vectors through an inter-segment context semantic association encoder including a segment semantic embedding encoding layer.

[0034] Then, it is considered that the semantic context encoding features of each segment in the scientific and technological achievement text data have different contribution degrees in the process of actually matching with the demand semantics to generate the matching results. That is to say, each of the scientific and technological achievement segment granularity semantic encoding feature vectors in the sequence of the scientific and technological achievement segment granularity semantic encoding feature vectors has different importance for the subsequent semantic matching task between the scientific and technological achievement text data and the achievement demand information. Based on this, in order to be able to identify and emphasize the key paragraph context semantic information in the scientific and technological achievement text data, so as to highlight those parts that are most important for understanding the core value and application scenarios of scientific and technological achievements, in the technical solution of the present application, the sequence of the scientific and technological achievement segment granularity semantic encoding feature vectors is further input into the semantic significance optimization module based on the global context to obtain the sequence of optimized scientific and technological achievement segment granularity semantic encoding feature vectors. Through the processing of the global context-based semantic saliency optimization module, the correlation relationship and importance semantics between the context semantics of each paragraph in the scientific and technological achievement text data can be learned and captured, thereby giving these key segment-granularity semantic features a higher weight to help identify and emphasize the key semantic information and features in the text, highlighting and saliency optimization of these key scientific and technological achievements important semantics, which helps to enhance the semantic expression ability of the scientific and technological achievement text and provide better quality semantic representation for subsequent matching and analysis tasks.

[0035] In one embodiment of the present application, the scientific and technological achievement segment granularity semantic saliency optimization module 1032 includes: a data calculation unit, which is used to respectively calculate the mean and maximum values ​​of each scientific and technological achievement segment granularity semantic coding feature vector in the sequence of the scientific and technological achievement segment granularity semantic coding feature vector to obtain a scientific and technological achievement segment granularity semantic global representation vector composed of multiple vector means and a scientific and technological achievement segment granularity semantic salient representation vector composed of multiple vector maximum values; a first convolution coding unit, which is used to perform one-dimensional convolution coding on the scientific and technological achievement segment granularity semantic global representation vector and then pass it through The activation function is used to obtain a global semantic representation vector of the segment granularity of the activated expression of scientific and technological achievements; the second convolutional coding unit is used to perform matrix multiplication of the global semantic representation vector of the segment granularity of the activated expression of scientific and technological achievements with the first trainable linear transformation weight matrix after one-dimensional convolution coding to obtain a feature vector of the global semantic activation representation of the segment granularity of the scientific and technological achievements; the activation unit is used to perform one-dimensional convolution coding on the semantic salient representation vector of the segment granularity of the scientific and technological achievements and then perform matrix multiplication of the vector with the first trainable linear transformation weight matrix to obtain a feature vector of the global semantic activation representation of the segment granularity of the scientific and technological achievements. The activation function is used to obtain an activation expression of the scientific and technological achievement segment granularity semantic prominent representation vector; the third convolution coding unit is used to perform matrix multiplication with the second trainable linear transformation weight matrix after the activation expression of the scientific and technological achievement segment granularity semantic prominent representation vector is once again subjected to one-dimensional convolution coding to obtain a scientific and technological achievement segment granularity prominent semantic activation representation feature vector; the vector fusion unit is used to fuse the scientific and technological achievement segment granularity global semantic activation representation feature vector and the scientific and technological achievement segment granularity prominent semantic activation representation feature vector to obtain the scientific and technological achievement segment granularity global-prominent semantic association activation feature vector, and then perform nonlinear activation processing on the scientific and technological achievement segment granularity global-prominent semantic association activation feature vector to obtain the scientific and technological achievement segment granularity global-prominent semantic association weight feature vector; the weight multiplication unit is used to use the scientific and technological achievement segment granularity global-prominent semantic association weight feature vector as the weight, perform positional point multiplication on the sequence of the scientific and technological achievement segment granularity semantic coding feature vectors and add the sequence of the scientific and technological achievement segment granularity semantic coding feature vectors to obtain the sequence of the optimized scientific and technological achievement segment granularity semantic coding feature vectors.

[0036] Further, in one embodiment of the present application, the vector fusion unit is used to: fuse the global semantic activation representation feature vector of the scientific and technological achievement segment granularity and the prominent semantic activation representation feature vector of the scientific and technological achievement segment granularity to obtain the global-prominent semantic association activation feature vector of the scientific and technological achievement segment granularity; respectively use the hyperbolic tangent function and The function activates the global-salient semantic association activation feature vector of the scientific and technological achievement segment granularity to obtain the global-salient feature hyperbolic tangent activation semantic representation vector of the scientific and technological achievement segment granularity and the global-salient feature S-type activation semantic representation vector of the scientific and technological achievement segment granularity; multiplies the global-salient feature hyperbolic tangent activation semantic representation vector of the scientific and technological achievement segment granularity and the global-salient feature S-type activation semantic representation vector of the scientific and technological achievement segment granularity by position point to obtain the global-salient semantic association weight feature vector of the scientific and technological achievement segment granularity.

[0037] Specifically, the sequence of the scientific and technological achievement segment granularity semantic coding feature vectors is input into the global context-based semantic significance optimization module for processing using the following semantic significance optimization formula to obtain the sequence of the optimized scientific and technological achievement segment granularity semantic coding feature vectors; The semantic significance optimization formula is: ; ; ; ; ;in, is a sequence of semantic encoding feature vectors of the scientific and technological achievements segment granularity, represents the global mean operation in the calculation vector, Represents the maximum value operation in the vector. is the semantic mean representation vector of the granularity of scientific and technological achievements, is the maximum semantic representation vector of the scientific and technological achievements segment granularity, represents one-dimensional convolutional coding, express Activation function, represents the first trainable linear transformation weight matrix, represents the second trainable linear transformation weight matrix, and They are the feature vector representing the global semantic activation at the granularity of scientific and technological achievements and the feature vector representing the prominent semantic activation at the granularity of scientific and technological achievements. for function, for function, It means point multiplication by position. A sequence of semantic encoding feature vectors for optimizing the granularity of scientific and technological achievements.

[0038] Then, the achievement demand information is semantically encoded to extract the semantic coding features in the achievement demand information. These semantic coding features include the scientific and technological achievements and demand purposes required by the achievement demander, thereby obtaining the achievement demand semantic coding feature vector.

[0039] Furthermore, since the sequence of the optimized scientific and technological achievement segment granularity semantic coding feature vectors and the achievement demand semantic coding feature vectors respectively contain the key segment granularity context semantic salient features in the scientific and technological achievement text data and the semantic coding features of the scientific and technological achievement requirements, in order to be able to match the semantic information of the two, so as to judge the matching degree between the scientific and technological achievements and the requirements, and thus provide a basis for subsequent decision-making, in the technical solution of the present application, the sequence of the optimized scientific and technological achievement segment granularity semantic coding feature vectors and the achievement demand semantic coding feature vectors are further input into the unidirectional attention granularity scanning interactive matching module to obtain the scientific and technological achievement-requirement information unidirectional matching result representation vector. Through the processing of the unidirectional attention granularity scanning interactive matching module, the unidirectional semantic interaction and granularity scanning matching between the scientific and technological achievement segment granularity context semantic association features and the demand semantic coding features can be realized, thereby helping the system to better learn and capture the semantic association features and matching degree between the achievements and the requirements, providing more powerful support for subsequent recommendation and matching tasks, and helping to achieve more accurate scientific and technological achievement transformation.

[0040] In one embodiment of the present application, the scientific and technological achievement-demand information one-way interactive matching module is used to: input the sequence of the optimized scientific and technological achievement segment granularity semantic coding feature vector and the achievement demand semantic coding feature vector into the one-way attention granularity scanning interactive matching module to obtain the scientific and technological achievement-demand information one-way matching result representation vector as the scientific and technological achievement-demand information one-way matching result information.

[0041] Further, in one embodiment of the present application, the scientific and technological achievement-demand information one-way interactive matching module 1034 includes: a semantic association unit, which is used to calculate the semantic association between each optimized scientific and technological achievement segment granularity semantic coding feature vector in the sequence of optimized scientific and technological achievement segment granularity semantic coding feature vectors and the achievement demand semantic coding feature vector to obtain a sequence of scientific and technological achievement-demand information one-way matching semantic measurement coefficients; a normalization processing unit, which is used to normalize the sequence of scientific and technological achievement-demand information one-way matching semantic measurement coefficients to obtain a sequence of scientific and technological achievement-demand information one-way matching semantic measurement weights; a vector weighting unit, which is used to use the sequence of scientific and technological achievement-demand information one-way matching semantic measurement weights as weights to calculate the weighted sum of the sequence of optimized scientific and technological achievement segment granularity semantic coding feature vectors to obtain the scientific and technological achievement-demand information one-way matching interactive reshaping feature vector; a differential feature vector calculation unit, which is used to calculate the differential feature vector between the scientific and technological achievement-demand information one-way matching interactive reshaping feature vector and the achievement demand semantic coding feature vector as the scientific and technological achievement-demand information one-way matching result representation vector.

[0042] Furthermore, in one embodiment of the present application, the semantic relevance unit is used to: input the optimized scientific and technological achievement segment granularity semantic coding feature vector and the achievement requirement semantic coding feature vector into the feature union module for cascade processing to obtain the scientific and technological achievement-requirement information semantic joint feature vector; calculate the matrix multiplication of the scientific and technological achievement-requirement information semantic joint feature vector and the parameter matrix, and then add the obtained feature vector to the bias vector by position to obtain the linear transformation scientific and technological achievement-requirement information semantic joint feature vector; use The function activates the linear transformation scientific and technological achievement-demand information semantic joint feature vector to obtain the scientific and technological achievement-demand information one-way matching semantic measurement coefficient.

[0043] Specifically, the semantic association between each optimized scientific and technological achievement segment granularity semantic coding feature vector in the sequence of optimized scientific and technological achievement segment granularity semantic coding feature vectors and the achievement requirement semantic coding feature vector is calculated using the following semantic association measurement formula to obtain a sequence of semantic measurement coefficients of one-way matching of the scientific and technological achievement-requirement information; The semantic relevance measurement formula is: ;in, and are the semantic coding feature vector of the achievement requirement and the semantic coding feature vector of each optimized scientific and technological achievement segment granularity, represents a vector concatenation operation, is the parameter matrix, is the bias vector, is the sigmoid function, It is each one-way matching semantic measurement coefficient of scientific and technological achievements and demand information in the sequence of one-way matching semantic measurement coefficients of scientific and technological achievements and demand information.

[0044] Then, the one-way matching result representation vector of the scientific and technological achievement-demand information is input into the matching result generator based on the classifier to obtain the matching result, and the matching result is used to indicate whether the matching degree between the scientific and technological achievement text data and the achievement demand information exceeds the preset threshold. In this way, the one-way matching information between the segment granularity context semantic features of the scientific and technological achievement text and the semantic coding features of the demand information can be used for classification processing to determine the matching degree between the scientific and technological achievement text data and the achievement demand information, and return the matching result of whether the matching degree between the scientific and technological achievement text data and the achievement demand information exceeds the preset threshold. In this way, it is possible to determine whether to return the scientific and technological achievements of the achievement supplier to the achievement demander based on the matching degree between the segment granularity semantics of the scientific and technological achievement text and the achievement demand information semantics, thereby improving the intelligent level of scientific and technological achievement management, and avoiding the information loss and low matching accuracy caused by the keyword matching method by the way of segment-by-segment semantic matching of the full text of the scientific research achievement text, and at the same time, it can effectively solve the problem that the existing field keyword library may not cover all emerging technologies or interdisciplinary terms and limit the ability to transform scientific and technological achievements, bringing more efficient and accurate solutions to scientific and technological achievement management and transformation.

[0045] In a preferred embodiment, inputting the scientific and technological achievement-demand information one-way matching result representation vector into a classifier-based matching result generator to obtain a matching result includes: Based on the association value and distance value of the eigenvalue of the one-way matching result representation vector of the scientific and technological achievements-demand information, the one-way matching result association response matrix of the scientific and technological achievements-demand information and the one-way matching result distance response matrix of the scientific and technological achievements-demand information are determined, that is: ; ;in, and respectively represent the first The eigenvalues ​​and eigenvalues, , represents the one-way matching result vector of the scientific and technological achievements and demand information, represents the set of real numbers, Indicates the length of the vector representing the one-way matching result of the scientific and technological achievement-demand information, In the one-way matching result association response matrix between scientific and technological achievements and demand information The eigenvalues ​​of the positions, Represents the distance response matrix of the one-way matching result between scientific and technological achievements and demand information The eigenvalue of the position; Performing matrix multiplication of the scientific and technological achievement-demand information one-way matching result representation vector and the scientific and technological achievement-demand information one-way matching result association response matrix to obtain a scientific and technological achievement-demand information one-way matching result association response vector; Performing matrix multiplication of the distance response matrix of the one-way matching result of scientific and technological achievements - demand information and the transposed vector of the one-way matching result representation vector of scientific and technological achievements - demand information and then performing transposition to obtain the distance response vector of the one-way matching result of scientific and technological achievements - demand information; After performing a dot product of the scientific and technological achievement-demand information one-way matching result association response matrix and the scientific and technological achievement-demand information one-way matching result distance response matrix, perform a matrix multiplication with the transposed vector of the scientific and technological achievement-demand information one-way matching result representation vector to obtain a scientific and technological achievement-demand information one-way matching result logic bias vector; The scientific and technological achievements-demand information one-way matching result association response vector, the scientific and technological achievements-demand information one-way matching result distance response vector and the scientific and technological achievements-demand information one-way matching result logic offset vector are interpolated to obtain an optimized scientific and technological achievements-demand information one-way matching result representation vector; The optimized scientific and technological achievement-demand information one-way matching result representation vector is input into a matching result generator based on a classifier to obtain the matching result.

[0046] Here, the optimized one-way matching result of scientific and technological achievements and demand information represents the vector It is expressed as: ;exist ,and In the case of: ; ;in, Represents the correlation response matrix of the one-way matching results between scientific and technological achievements and demand information, Represents the distance response matrix of the one-way matching result between scientific and technological achievements and demand information, represents the one-way matching result vector of the scientific and technological achievements and demand information, represents matrix multiplication, It means point multiplication by position. Indicates adding by position point. represents the transpose of a vector, Represents the intermediate vector of the one-way matching result between scientific and technological achievements and demand information, Represents the logical bias vector of the one-way matching result between scientific and technological achievements and demand information, A vector representing the optimized one-way matching result of scientific and technological achievements and demand information.

[0047] Here, the sequence of the achievement requirement semantic encoding feature vector and the sequence of the optimized scientific and technological achievement segment granularity semantic encoding feature vector respectively express the encoded text semantic features of the achievement requirement information and the scientific and technological achievement text data, but the sequence of the optimized scientific and technological achievement segment granularity semantic encoding feature vector performs global context saliency enhancement on the basis of the encoded semantic feature representation of the source semantics. Therefore, after the sequence of the achievement requirement semantic encoding feature vector and the sequence of the optimized scientific and technological achievement segment granularity semantic encoding feature vector are input into the unidirectional attention granularity scanning interactive matching network, the obtained scientific and technological achievement-demand information unidirectional matching result representation vector will also have a large-scale simple repetition in the feature manifold of the scientific and technological achievement-demand information unidirectional matching result representation vector due to the difference in unidirectional attention interactive matching weights under the different feature distribution representations of the achievement requirement semantic encoding feature vector and the optimized scientific and technological achievement segment granularity semantic encoding feature vector, thereby affecting the accuracy of the classification results.

[0048] Therefore, by using the self-correlation matrix and self-distance matrix of the one-way matching result representation vector of the scientific and technological achievements-demand information as the statistical reference-free distribution response framework of the one-way matching result representation vector of the scientific and technological achievements-demand information, the simple repetition of feature distribution is avoided based on the retrieval-enhanced reverse response construction of the one-way matching result representation vector of the scientific and technological achievements-demand information, and the surface combination mapping of the one-way matching result representation vector of the scientific and technological achievements-demand information is avoided by ensuring the intrinsic mapping logic of the one-way matching result representation vector of the scientific and technological achievements-demand information based on the retrieval-response context, so as to realize the logical dependency mapping of the one-way matching result representation vector of the scientific and technological achievements-demand information to the classification target domain while maintaining the intuitive response correlation, thereby improving the accuracy of the matching result obtained by the one-way matching result representation vector of the scientific and technological achievements-demand information input into the matching result generator based on the classifier. In this way, the matching result can be accurately generated based on the matching degree between the segment granularity semantics of the scientific and technological achievements text and the semantics of the achievement demand information, so as to determine whether to provide the scientific and technological achievements of the achievement supplier to the achievement demander, and bring more efficient and accurate solutions to the management and transformation of scientific and technological achievements.

[0049] In summary, the above scheme is adopted to collect the text data of scientific and technological achievements and the information of achievement demand respectively at the upload port of the achievement supplier and the release port of the achievement demander, and introduce the data processing and semantic understanding algorithm based on artificial intelligence and deep learning in the achievement supply-demand matching server to perform semantic encoding and segment-by-segment granularity one-way semantic matching on the text data of the scientific and technological achievements and the achievement demand information, so as to determine the matching degree between the text data of the scientific and technological achievements and the achievement demand information, and then return the matching result. In this way, it is possible to determine whether to return the scientific and technological achievements of the achievement supplier to the achievement demander based on the matching degree between the segment-granularity semantics of the scientific and technological achievement text and the semantics of the achievement demand information, thereby improving the intelligent level of scientific and technological achievement management, and avoiding the information loss and low matching accuracy caused by the keyword matching method by matching the full text of the scientific research achievement segment by segment, and at the same time, it can effectively solve the problem that the existing field keyword library may not cover all emerging technologies or interdisciplinary terms and limit the ability to transform scientific and technological achievements, bringing more efficient and accurate solutions to the management and transformation of scientific and technological achievements.

[0050] Figure 2 is a flow chart of a method for managing scientific and technological achievements based on data intelligence according to an exemplary embodiment, such as Figure 2 As shown, the method includes: Step S201: Upload scientific and technological achievement text data, and store the scientific and technological achievement text data in a scientific and technological achievement database; Step S202: Upload the achievement demand information and store the achievement demand information in the demand database; Step S203: Calculating the semantic matching degree between the scientific and technological achievement text data and the achievement demand information to determine whether to recommend an achievement supplier to the achievement demander; Wherein, step S203: calculating the semantic matching degree of the scientific and technological achievement text data and the achievement demand information to determine whether to recommend the achievement supplier to the achievement demander includes: Step S2031: performing segment-based inter-segment context semantic association coding on the scientific and technological achievement text data to obtain a sequence of scientific and technological achievement segment-granularity semantic coding feature vectors; Step S2032: inputting the sequence of the scientific and technological achievement segment granularity semantic coding feature vectors into a global context-based semantic significance optimization module to obtain a sequence of optimized scientific and technological achievement segment granularity semantic coding feature vectors; Step S2033: semantically encode the achievement requirement information to obtain an achievement requirement semantic encoding feature vector; Step S2034, performing interactive matching based on unidirectional granularity scanning on the sequence of the optimized scientific and technological achievement segment granularity semantic coding feature vectors and the achievement requirement semantic coding feature vectors to obtain scientific and technological achievement-requirement information unidirectional matching result information; Step S2035: Generate a matching result based on the one-way matching result information of the scientific and technological achievements-demand information, and the matching result is used to indicate whether the matching degree between the scientific and technological achievements text data and the achievement demand information exceeds a preset threshold. Optionally, the scientific and technological achievements text data is subjected to segment-granularity-based inter-segment context semantic association encoding to obtain a sequence of scientific and technological achievements segment-granularity semantic encoding feature vectors, including: segmenting the scientific and technological achievements text data and then passing through an inter-segment context semantic association encoder including a segment semantic embedding encoding layer to obtain a sequence of scientific and technological achievements segment-granularity semantic encoding feature vectors.

[0051] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present application. The terminal device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0052] like Figure 3 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0053] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0054] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present application are executed.

[0055] It should be noted that the computer-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0056] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0057] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0058] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0059] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0060] The modules involved in the embodiments described in this application can be implemented by software or hardware. The name of the module does not limit the module itself in some cases. For example, the test parameter acquisition module can also be described as a "module for acquiring device test parameters corresponding to the target device".

[0061] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0062] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0063] Figure 4 FIG. 1 is an application scenario diagram of a scientific and technological achievement management platform based on data intelligence according to an exemplary embodiment. Figure 4 As shown, in this application scenario, first, obtain the text data of scientific and technological achievements (for example Figure 4 C1) and outcome requirements information (e.g. Figure 4 Then, the obtained scientific and technological achievement text data and achievement demand information are input into a server (e.g. Figure 4 In S) shown in , the server is capable of processing the scientific and technological achievement text data and the achievement demand information based on a data intelligent scientific and technological achievement management algorithm to generate a matching result, and the matching result is used to indicate whether the matching degree between the scientific and technological achievement text data and the achievement demand information exceeds a preset threshold.

[0064] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

[0065] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or to be performed in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the application. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0066] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. A scientific and technological achievement management platform based on data intelligence, It is characterized in that include: The achievement supplier upload port is used to upload the scientific and technological achievement text data and store the scientific and technological achievement text data in the scientific and technological achievement database; The result demander release port is used to upload the result demand information and store the result demand information in the demand database; A result supply-demand matching server is used to calculate the semantic matching degree between the scientific and technological result text data and the result demand information to determine whether to recommend a result supplier to the result demander; The achievement supply-demand matching server includes: A scientific and technological achievement segment granularity semantic coding module is used to perform segment granularity-based inter-segment context semantic association coding on the scientific and technological achievement text data to obtain a sequence of scientific and technological achievement segment granularity semantic coding feature vectors; A scientific and technological achievement segment granularity semantic saliency optimization module, used for inputting the sequence of the scientific and technological achievement segment granularity semantic coding feature vectors into the global context-based semantic saliency optimization module to obtain a sequence of optimized scientific and technological achievement segment granularity semantic coding feature vectors; An achievement requirement semantic coding module, used for semantically coding the achievement requirement information to obtain an achievement requirement semantic coding feature vector; A one-way interactive matching module for scientific and technological achievements and demand information is used to interactively match the sequence of the optimized scientific and technological achievements segment granularity semantic coding feature vectors and the achievement demand semantic coding feature vectors based on one-way granularity scanning to obtain one-way matching result information of scientific and technological achievements and demand information; The matching result generation module is used to generate a matching result based on the one-way matching result information of the scientific and technological achievement-demand information, and the matching result is used to indicate whether the matching degree between the scientific and technological achievement text data and the achievement demand information exceeds a preset threshold.

2. According to the data intelligence-based scientific and technological achievement management platform of claim 1, It is characterized in that The scientific and technological achievement segment granularity semantic encoding module is used to: after segmenting the scientific and technological achievement text data, obtain a sequence of the scientific and technological achievement segment granularity semantic encoding feature vectors through an inter-segment context semantic association encoder including a segment semantic embedding encoding layer.

3. According to the data intelligence-based scientific and technological achievement management platform of claim 2, It is characterized in that The scientific and technological achievements segment granularity semantic saliency optimization module includes: A data calculation unit, used to respectively calculate the mean and maximum values ​​of each scientific and technological achievement segment granularity semantic coding feature vector in the sequence of the scientific and technological achievement segment granularity semantic coding feature vector to obtain a scientific and technological achievement segment granularity semantic global representation vector composed of multiple vector means and a scientific and technological achievement segment granularity semantic prominent representation vector composed of multiple vector maximum values; The first convolutional coding unit is used to perform one-dimensional convolutional coding on the global semantic representation vector of the scientific and technological achievement segment granularity and then pass The activation function is used to process the global semantic representation vector of the segment granularity of the activated expression of scientific and technological achievements; The second convolutional coding unit is used to perform matrix multiplication of the activation expression scientific and technological achievement segment granularity semantic global representation vector with the first trainable linear transformation weight matrix after one-dimensional convolutional coding to obtain the scientific and technological achievement segment granularity global semantic activation representation feature vector; The activation unit is used to perform one-dimensional convolution encoding on the segment granularity semantic highlight representation vector of the scientific and technological achievements and then pass it through The activation function is used to process the segment-granular semantics of the scientific and technological achievements to obtain the activation expression vector; The third convolutional coding unit is used to perform matrix multiplication of the activation expression of the segment granularity semantic prominence representation vector of the scientific and technological achievements with the second trainable linear transformation weight matrix after one-dimensional convolution coding to obtain the scientific and technological achievements segment granularity prominence semantic activation representation feature vector; A vector fusion unit is used to fuse the global semantic activation representation feature vector of the scientific and technological achievement segment granularity and the prominent semantic activation representation feature vector of the scientific and technological achievement segment granularity to obtain the global-prominent semantic association activation feature vector of the scientific and technological achievement segment granularity, and then perform nonlinear activation processing on the global-prominent semantic association activation feature vector of the scientific and technological achievement segment granularity to obtain the global-prominent semantic association weight feature vector of the scientific and technological achievement segment granularity; The weight multiplication unit is used to use the global-prominent semantic association weight feature vector of the scientific and technological achievement segment granularity as the weight, perform positional point multiplication on the sequence of the semantic coding feature vectors of the scientific and technological achievement segment granularity, and add the sequence of the semantic coding feature vectors of the scientific and technological achievement segment granularity to obtain the sequence of the optimized scientific and technological achievement segment granularity semantic coding feature vectors.

4. According to the data intelligence-based scientific and technological achievement management platform of claim 3, It is characterized in that The vector fusion unit is used for: The global semantic activation representation feature vector of the scientific and technological achievement segment granularity and the prominent semantic activation representation feature vector of the scientific and technological achievement segment granularity are integrated to obtain the global-prominent semantic association activation feature vector of the scientific and technological achievement segment granularity; Using the hyperbolic tangent function and The function performs activation processing on the global-prominent semantic association activation feature vector of the scientific and technological achievement segment granularity to obtain the global-prominent feature hyperbolic tangent activation semantic representation vector of the scientific and technological achievement segment granularity and the global-prominent feature S-type activation semantic representation vector of the scientific and technological achievement segment granularity; The global-salient feature hyperbolic tangent activation semantic representation vector of the scientific and technological achievement segment granularity and the global-salient feature S-type activation semantic representation vector of the scientific and technological achievement segment granularity are multiplied by position point to obtain the global-salient semantic association weight feature vector of the scientific and technological achievement segment granularity.

5. According to the data intelligence-based scientific and technological achievement management platform of claim 4, It is characterized in that The scientific and technological achievement-demand information one-way interactive matching module is used to: input the sequence of the optimized scientific and technological achievement segment granularity semantic coding feature vector and the achievement demand semantic coding feature vector into the one-way attention granularity scanning interactive matching module to obtain the scientific and technological achievement-demand information one-way matching result representation vector as the scientific and technological achievement-demand information one-way matching result information.

6. According to the data intelligence-based scientific and technological achievement management platform of claim 5, It is characterized in that The scientific and technological achievements-demand information one-way interactive matching module includes: A semantic association unit, used for calculating the semantic association between each optimized scientific and technological achievement segment granularity semantic coding feature vector in the sequence of optimized scientific and technological achievement segment granularity semantic coding feature vectors and the achievement requirement semantic coding feature vector to obtain a sequence of semantic measurement coefficients of one-way matching of scientific and technological achievement-requirement information; A normalization processing unit, used for normalizing the sequence of semantic measurement coefficients of one-way matching of scientific and technological achievements and demand information to obtain a sequence of semantic measurement weights of one-way matching of scientific and technological achievements and demand information; A vector weighting unit, used to calculate the weighted sum of the sequence of the semantic measurement weights of the one-way matching of scientific and technological achievements and demand information as weights, so as to obtain the interactive reshaping feature vector of the one-way matching of scientific and technological achievements and demand information; The differential feature vector calculation unit is used to calculate the differential feature vector between the one-way matching interactive reshaping feature vector of the scientific and technological achievement-demand information and the semantic encoding feature vector of the achievement demand as the one-way matching result representation vector of the scientific and technological achievement-demand information.

7. According to the data intelligence-based scientific and technological achievement management platform of claim 6, It is characterized in that The semantic relevance unit is used to: Inputting the optimized scientific and technological achievement segment granularity semantic coding feature vector and the achievement requirement semantic coding feature vector into a feature combination module for cascade processing to obtain a scientific and technological achievement-requirement information semantic combination feature vector; After calculating the matrix multiplication of the scientific and technological achievement-demand information semantic joint feature vector and the parameter matrix, the obtained feature vector is added to the bias vector by position to obtain a linear transformation scientific and technological achievement-demand information semantic joint feature vector; use The function activates the linear transformation scientific and technological achievement-demand information semantic joint feature vector to obtain the scientific and technological achievement-demand information one-way matching semantic measurement coefficient.

8. According to the data intelligence-based scientific and technological achievement management platform of claim 7, It is characterized in that The matching result generation module is used to: input the scientific and technological achievement-demand information one-way matching result representation vector into a classifier-based matching result generator to obtain a matching result, and the matching result is used to indicate whether the matching degree between the scientific and technological achievement text data and the achievement demand information exceeds a preset threshold.

9. A method for managing scientific and technological achievements based on data intelligence. It is characterized in that include: Upload scientific and technological achievements text data, and store the scientific and technological achievements text data in the scientific and technological achievements database; Upload the achievement demand information and store the achievement demand information in the demand database; Calculating the semantic matching degree between the scientific and technological achievement text data and the achievement demand information to determine whether to recommend an achievement supplier to the achievement demander; The process of calculating the semantic matching degree between the scientific and technological achievement text data and the achievement demand information to determine whether to recommend an achievement supplier to the achievement demander includes: Performing segment-granularity-based inter-segment context semantic association coding on the scientific and technological achievement text data to obtain a sequence of scientific and technological achievement segment-granularity semantic coding feature vectors; Inputting the sequence of the scientific and technological achievement segment granularity semantic coding feature vectors into a global context-based semantic significance optimization module to obtain a sequence of optimized scientific and technological achievement segment granularity semantic coding feature vectors; Semantically encoding the achievement requirement information to obtain an achievement requirement semantic encoding feature vector; Perform interactive matching based on unidirectional granularity scanning on the sequence of the optimized scientific and technological achievement segment granularity semantic coding feature vectors and the achievement requirement semantic coding feature vectors to obtain scientific and technological achievement-requirement information unidirectional matching result information; A matching result is generated based on the scientific and technological achievement-demand information one-way matching result information, and the matching result is used to indicate whether the matching degree between the scientific and technological achievement text data and the achievement demand information exceeds a preset threshold.

10. According to the method for managing scientific and technological achievements based on data intelligence according to claim 9, It is characterized in that The scientific and technological achievement text data is encoded based on segment granularity inter-segment contextual semantic association coding to obtain a sequence of scientific and technological achievement segment granularity semantic coding feature vectors, including: segmenting the scientific and technological achievement text data and then passing it through an inter-segment contextual semantic association encoder including a segment semantic embedding coding layer to obtain a sequence of scientific and technological achievement segment granularity semantic coding feature vectors.

Images