Method and device for displaying document efficacy, electronic device, and storage medium

Abstract

The present disclosure relates to a method and device for displaying the efficacy of a document, an electronic device, and a storage medium. The method comprises: extracting keywords representing efficacy from a document text, wherein the keywords include efficacy attributes, and the efficacy attributes represent the attributes of the subject that produces the efficacy; based on the existing efficacy attributes, the efficacy attributes are standardized to obtain standardized efficacy attributes; and the efficacy of the document text is displayed according to the standardized efficacy attributes. In the embodiments of the present disclosure, on the one hand, the classification management of text documents is achieved through the standardization of efficacy attributes; on the other hand, the efficacy of the document text is displayed through the standardized efficacy attributes, briefly summarizing in which specific aspects (i.e., the standardized efficacy attributes) the document has achieved technical effects, so as to facilitate the document owner to display and promote the technology contained in the document in various occasions, and for the document readers to understand the research direction of the technical solution of the document in the shortest time.

Description

Technical Field

[0001] The present disclosure relates to the technical field of text language processing, and in particular to a method and device for displaying the effectiveness of a document, an electronic device, and a storage medium. Background Art

[0002] Literature is an important source of scientific and technological information. Patents, papers, and other documents detailing the effects of technical solutions or scientific innovations often represent crucial information. However, these documents are often lengthy and contain highly specialized text, making them difficult to read and access. There is an urgent need for machines to automatically extract and display the effects of the technologies discussed in these documents. This would help people more quickly understand the technical solutions involved, save time reading, processing, and utilizing these documents, and reduce the workload of literature analysts. Summary of the Invention

[0003] In view of this, the present disclosure proposes a technical solution for displaying the efficacy of documents.

[0004] According to one aspect of the present disclosure, a method for displaying the efficacy of a document is provided, comprising: extracting keywords representing efficacy from a document text, wherein the keywords include efficacy attributes, and the efficacy attributes represent the attributes of a subject that produces the efficacy; based on existing efficacy attributes, standardizing the efficacy attributes to obtain standardized efficacy attributes; and displaying the efficacy of the document text according to the standardized efficacy attributes.

[0005] In a possible implementation, the keyword also includes: an efficacy subject and an efficacy value, wherein the efficacy subject represents the subject that produces the efficacy, and the efficacy value represents the efficacy produced by the attribute; the display of the efficacy of the document text according to the standardized efficacy attribute includes: displaying a keyword group, wherein the keyword group includes at least one of the efficacy subject and the efficacy value and a combination of the standardized efficacy attributes.

[0006] In one possible implementation, the display of the efficacy of the document text according to standardized efficacy attributes includes: displaying the efficacy of the document text according to standardized efficacy attributes in at least one of the following: efficacy matrix, document list page, document details page.

[0007] In one possible implementation, one dimension of the efficacy matrix is ​​the technical classification of the document text, and another dimension is the standardized efficacy attribute or the keyword group; the nodes in the efficacy matrix show the number of document texts in the technical classification corresponding to the node that have the standardized efficacy attribute or keyword group corresponding to the node.

[0008] In a possible implementation, the method further includes: in response to the standardized efficacy attribute, the keyword group or the node being triggered, displaying a list of document texts corresponding to the standardized efficacy attribute, the keyword group or the node.

[0009] In a possible implementation, the standardizing the efficacy attribute based on the existing efficacy attribute to obtain the standardized efficacy attribute includes: matching the efficacy attribute with the existing efficacy attribute to obtain a matching result; and determining the standardized efficacy attribute of the efficacy attribute according to the matching result.

[0010] In a possible implementation, the matching of the efficacy attribute with the existing efficacy attribute to obtain a matching result includes: performing a first matching operation on the efficacy attribute and the existing efficacy attribute, and when the first matching operation is successful, obtaining a first matching result corresponding to the efficacy attribute for which the first matching operation is successful; performing a second matching operation on the efficacy attribute for which the first matching operation is unsuccessful and a synonym of the existing efficacy attribute, and when the second matching operation is successful, obtaining a second matching result corresponding to the efficacy attribute for which the second matching operation is successful; performing a third matching operation on the suffix of the efficacy attribute for which the second matching operation is unsuccessful and the existing efficacy attribute, and when the third matching operation is successful, obtaining a third matching result corresponding to the efficacy attribute for which the third matching operation is successful; converting the efficacy attribute for which the third matching operation is unsuccessful into a word vector, and performing a fourth matching operation on the word vector of the existing efficacy attribute. When the fourth matching operation is successful, a fourth matching result corresponding to the efficacy attribute for which the fourth matching operation is successful is obtained; wherein, the second matching result includes an existing efficacy attribute, and a synonym of the existing efficacy attribute is successfully matched with the efficacy attribute; the fourth matching result includes an existing efficacy attribute, and a word vector of the existing efficacy attribute is successfully matched with the word vector of the efficacy attribute; determining the standardized efficacy attribute of the efficacy attribute based on the matching result includes: when the first matching operation, the second matching operation, the third matching operation or the fourth matching operation of the efficacy attribute is successful, determining the standardized efficacy attribute based on the first matching result, the second matching result, the third matching result or the fourth matching result; when the first matching operation, the second matching operation, the third matching operation and the fourth matching operation of the efficacy attribute are all unsuccessful, setting the standardized efficacy attribute to other.

[0011] In one possible implementation, the method further includes: obtaining at least one short sentence of the document text, the short sentence including the content between adjacent punctuation marks in the document text; determining a keyword group in the same paragraph based on the keywords in the same short sentence and the keywords in the same paragraph; and deleting repeated keyword groups in the determined keyword groups of the document text.

[0012] In a possible implementation, the keyword group in the same paragraph is determined based on the keywords in the same sentence and the keywords in the same paragraph, including: in the same paragraph, the standardized efficacy attribute of each efficacy attribute and the efficacy subject before the efficacy attribute and closest to the efficacy attribute are used as the first phrase; in the same sentence, the standardized efficacy attribute of each efficacy value and the efficacy attribute before the efficacy value and closest to the efficacy value are used as the second phrase; a first phrase and a second phrase containing the same standardized efficacy attribute in the same paragraph are merged into a third phrase; and at least one of the first phrase, the second phrase, and the third phrase is used as the keyword group.

[0013] In one possible implementation, the existing efficacy attributes include general efficacy attributes and high-frequency efficacy attributes; wherein, the general efficacy attributes include efficacy attributes obtained based on general engineering parameters of TRIZ theory; the high-frequency efficacy attributes include a preset number of efficacy attributes obtained by extracting efficacy attributes from existing literature and sorting them by frequency of occurrence from high to low.

[0014] In one possible implementation, the method further includes: extracting the efficacy paragraph from the document text through a second network model; extracting keywords representing efficacy from the document text includes: inputting the efficacy paragraph into the trained first network model to obtain the keywords.

[0015] In a possible implementation, the method further includes: training a first network model based on a document text sample and annotations of keywords representing efficacy in the document text sample to obtain the trained first network model, wherein the annotation indication keywords are efficacy subject, efficacy attribute or efficacy value; wherein the efficacy subject represents the subject that produces the efficacy; the efficacy attribute represents the attribute of the subject; and the efficacy value represents the efficacy produced by the attribute.

[0016] In a possible implementation, the first network model includes a Bert-CRF, LSTM-CRF, or CRF model.

[0017] According to another aspect of the present disclosure, a document efficacy display device is provided, including: a keyword extraction module for extracting keywords representing efficacy in a document text, wherein the keywords include efficacy attributes, and the efficacy attributes represent the attributes of a subject that produces the efficacy; a standardization module for standardizing the efficacy attributes based on existing efficacy attributes to obtain standardized efficacy attributes; and an efficacy display module for displaying the efficacy of the document text according to the standardized efficacy attributes.

[0018] In one possible implementation, the keyword also includes: an efficacy subject and an efficacy value, wherein the efficacy subject represents the subject that produces the efficacy, and the efficacy value represents the efficacy produced by the attribute; the efficacy display module includes: a keyword group display sub-module, used to display keyword groups, and the keyword group includes at least one of the efficacy subject and the efficacy value and a combination of the standardized efficacy attributes.

[0019] In a possible implementation, the efficacy display module includes: an efficacy display submodule, which is used to display the efficacy of the document text according to standardized efficacy attributes in at least one of the following: efficacy matrix, document list page, and document details page.

[0020] In one possible implementation, one dimension of the efficacy matrix is ​​the technical classification of the document text, and another dimension is the standardized efficacy attribute or the keyword group; the nodes in the efficacy matrix show the number of document texts in the technical classification corresponding to the node that have the standardized efficacy attribute or keyword group corresponding to the node.

[0021] In a possible implementation, the device further includes: a trigger display module for displaying a list of document texts corresponding to the standardized efficacy attribute, the keyword group or the node in response to the standardized efficacy attribute, the keyword group or the node being triggered.

[0022] In a possible implementation, the standardization module includes: a matching submodule, configured to match the efficacy attribute with an existing efficacy attribute to obtain a matching result; and a standardized efficacy attribute determination submodule, configured to determine a standardized efficacy attribute of the efficacy attribute based on the matching result.

[0023] In a possible implementation, the matching submodule is used to: perform a first matching operation on the efficacy attribute and the existing efficacy attribute, and when the first matching operation is successful, obtain a first matching result corresponding to the efficacy attribute that is successful in the first matching operation; perform a second matching operation on the efficacy attribute that is unsuccessful in the first matching operation and the synonym of the existing efficacy attribute, and when the second matching operation is successful, obtain a second matching result corresponding to the efficacy attribute that is successful in the second matching operation; perform a third matching operation on the suffix of the efficacy attribute that is unsuccessful in the second matching operation and the existing efficacy attribute, and when the third matching operation is successful, obtain a third matching result corresponding to the efficacy attribute that is successful in the third matching operation; convert the efficacy attribute that is unsuccessful in the third matching operation into a word vector, and perform a fourth matching operation on the word vector of the existing efficacy attribute, and in the fourth When the matching operation is successful, a fourth matching result corresponding to the efficacy attribute for which the fourth matching operation is successful is obtained; wherein, the second matching result includes an existing efficacy attribute, and the synonym of the existing efficacy attribute is successfully matched with the efficacy attribute; the fourth matching result includes an existing efficacy attribute, and the word vector of the existing efficacy attribute is successfully matched with the word vector of the efficacy attribute; the standardized efficacy attribute determination submodule is used to: when the first matching operation, the second matching operation, the third matching operation or the fourth matching operation of the efficacy attribute is successful, determine the standardized efficacy attribute according to the first matching result, the second matching result, the third matching result or the fourth matching result; when the first matching operation, the second matching operation, the third matching operation and the fourth matching operation of the efficacy attribute are all unsuccessful, set the standardized efficacy attribute to other.

[0024] In one possible implementation, the device further includes: a short sentence acquisition module, used to acquire at least one short sentence of the document text, wherein the short sentence includes the content between adjacent punctuation marks in the document text; a keyword group determination module, used to determine the keyword group in the same paragraph based on the keywords in the same short sentence and the keywords in the same paragraph; and a repeated phrase deletion module, used to delete repeated keyword groups in the determined keyword groups of the document text.

[0025] In one possible implementation, the keyword group determination module includes: a first phrase determination submodule, which is used to use the standardized efficacy attribute of each efficacy attribute and the efficacy subject before the efficacy attribute and closest to the efficacy attribute in the same paragraph as the first phrase; a second phrase determination submodule, which is used to use the standardized efficacy attribute of each efficacy value and the efficacy attribute before the efficacy value and closest to the efficacy value in the same short sentence as the second phrase; a third phrase determination submodule, which is used to merge a first phrase and a second phrase containing the same standardized efficacy attribute in the same paragraph into a third phrase; and a keyword group determination submodule, which is used to use at least one of the first phrase, the second phrase, and the third phrase as the keyword group.

[0026] In one possible implementation, the existing efficacy attributes include general efficacy attributes and high-frequency efficacy attributes; wherein, the general efficacy attributes include efficacy attributes obtained based on general engineering parameters of TRIZ theory; the high-frequency efficacy attributes include a preset number of efficacy attributes obtained by extracting efficacy attributes from existing literature and sorting them by frequency of occurrence from high to low.

[0027] In one possible implementation, the device also includes: an efficacy paragraph extraction module, which is used to extract the efficacy paragraph in the document text through the second network model; and the keyword extraction module, which is used to input the efficacy paragraph into the trained first network model to obtain the keyword.

[0028] In one possible implementation, the device also includes: a first network training module, used to train a first network model based on a document text sample and an annotation of keywords representing efficacy in the document text sample to obtain the trained first network model, wherein the annotation indication keyword is an efficacy subject, an efficacy attribute or an efficacy value; wherein the efficacy subject represents the subject that produces the efficacy; the efficacy attribute represents the attribute of the subject; and the efficacy value represents the efficacy produced by the attribute.

[0029] In a possible implementation, the first network model includes a Bert-CRF, LSTM-CRF, or CRF model.

[0030] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to call the instructions stored in the memory to execute the above method.

[0031] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the above method when executed by a processor.

[0032] The document efficacy display method of the disclosed embodiment extracts keywords representing efficacy from the document text. On the one hand, it standardizes the efficacy attributes in the keywords to realize the classification management of the text documents; on the other hand, it displays the efficacy of the document text according to the standardized efficacy attributes, and briefly summarizes in which specific aspects (i.e., the standardized efficacy attributes) the document has achieved technical effects, so as to facilitate the document owner to display and promote the technology contained in the document on various occasions and the document readers to understand the research direction of the technical solution of the document in the shortest time.

[0033] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, rather than limiting the present disclosure. Other features and aspects of the present disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0035] Figure 1 A flow chart showing a method for displaying document efficacy according to an embodiment of the present disclosure is shown.

[0036] Figure 2 A schematic diagram illustrating the composition of keywords representing efficacy according to an embodiment of the present disclosure.

[0037] Figure 3 A flow chart showing a method for displaying document efficacy according to an embodiment of the present disclosure is shown.

[0038] Figure 4 A flow chart showing a method for displaying document efficacy according to an embodiment of the present disclosure is shown.

[0039] Figure 5 An example diagram showing the effects of patent documents according to embodiments of the present disclosure.

[0040] Figure 6 A block diagram of a document efficacy display device according to an embodiment of the present disclosure is shown.

[0041] Figure 7 A block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0042] Figure 8 A block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0043] Figure 9 A schematic diagram of efficacy matrix analysis according to an embodiment of the present disclosure is shown.

[0044] Figure 10A schematic diagram of a patent details page according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0045] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

[0046] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0047] The term "and / or" herein simply describes an association relationship between associated objects, indicating that three relationships can exist. For example, "A and / or B" can represent the existence of three situations: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" herein refers to any combination of at least two of any one or more of a plurality of items. For example, "at least one of A, B, and C" can represent any one or more elements selected from the set consisting of A, B, and C.

[0048] In addition, numerous specific details are provided in the following detailed description to better illustrate the present disclosure. Those skilled in the art will appreciate that the present disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art are not described in detail in order to highlight the main points of the present disclosure.

[0049] With the rapid development of economy and science and technology, the number of scientific and technological documents in my country continues to increase. Among them, the display of the efficacy of the technologies involved in the documents can enable document owners to better display their research results on various publicity channels such as websites, and analysts to understand the documents in the shortest possible time, which is of great benefit to document analysis and indexing.

[0050] The efficacy of a document is the technical effect achieved by the technical means used in the document and is an important component of the document's technical solution. This embodiment of the application can improve the efficiency of document analysis, indexing, and reading by extracting keywords representing efficacy from the document text, standardizing the efficacy attributes in the keywords, and displaying the efficacy of the document text based on the standardized efficacy attributes.

[0051] In an exemplary application scenario, a document retrieval or analysis platform may execute the method according to the embodiment of the present application on the document text it acquires or stores, obtain the efficacy of the document text and display it to the user.

[0052] Documents may include any document available for review and analysis, such as journal or conference papers, patents, and articles published on the Internet. For patent documents, efficacy demonstration may indicate the technical effects that can be achieved by the patent, or the efficacy brought about by the technical solution. For papers, it may be the efficacy produced by the scientific research innovation proposed in the paper. In order to better illustrate the present disclosure and highlight the main purpose of the present disclosure, the specific embodiments herein are described with reference to documents such as patents. Those skilled in the art should understand that the present disclosure can also be implemented with reference to other documents such as papers.

[0053] Figure 1 A flow chart showing the method for displaying document efficacy according to an embodiment of the present disclosure is shown as follows: Figure 1 As shown, the literature efficacy display methods include:

[0054] In step S11, keywords representing efficacy are extracted from the document text, wherein the keywords include efficacy attributes, wherein the efficacy attributes represent the attributes of the subject that produces the efficacy, generally physical and chemical attributes of the subject, such as speed, time, etc.

[0055] In step S12, the efficacy attributes are standardized based on the existing efficacy attributes to obtain standardized efficacy attributes.

[0056] In step S13, the efficacy of the document text is displayed according to the standardized efficacy attributes.

[0057] Through steps S11-S13, keywords representing efficacy are extracted from the document text, the efficacy attributes in the keywords are standardized, and the efficacy of the document text is displayed based on the standardized efficacy attributes.

[0058] The terms used in literature to describe efficacy attributes may be inconsistent and non-standard due to the different expression habits of the authors, which can affect readers' understanding and also affect the retrieval, analysis, and other processing of the literature. "Standardization" can be the process of matching or replacing efficacy attributes extracted from the literature with existing, standard efficacy attributes to obtain standardized efficacy attributes. This makes the displayed standardized efficacy attributes uniform, standard, easy to understand, and easy to retrieve and analyze the literature.

[0059] In one example, a passage in a patent document reads as follows: "The present utility model is provided with a sealing device and a sealing gasket, which can effectively ensure the sealing of the device, as well as the reliability and stability of its use." The efficacy attributes of the text are extracted and standardized to obtain the standardized efficacy attributes "sealing, stability, and reliability". Based on these standardized efficacy attributes, the efficacy of the patent text can be briefly demonstrated.

[0060] For the embodiments disclosed herein, on the one hand, by displaying the efficacy of text documents through the standardized efficacy attributes of the document text, it is possible to briefly summarize in which specific aspects (i.e., the standardized efficacy attributes) the document has achieved the effect, which greatly facilitates the document owner to display and promote the technology contained in the document on various occasions, and allows users to understand the research direction of the technical solution of the document in the shortest time; on the other hand, by standardizing the efficacy attributes and replacing them with existing efficacy attributes, it is convenient to classify and manage text documents, and to find similar text documents, which greatly saves the workload of document analysts; in addition, the document efficacy display method can also be widely used in projects such as automatic document efficacy indexing and efficacy search.

[0061] In one possible implementation, the existing efficacy attributes include general efficacy attributes and high-frequency efficacy attributes; wherein, the general efficacy attributes include efficacy attributes obtained based on general engineering parameters of TRIZ theory; the high-frequency efficacy attributes include a preset number of efficacy attributes obtained by extracting efficacy attributes from existing literature and sorting them by frequency of occurrence from high to low.

[0062] Specifically, the universal engineering parameters of TRIZ theory are collected and summarized through the study of extensive patent data. The universal performance attributes extracted from these universal engineering parameters are highly representative. High-frequency performance attributes, which appear frequently in existing literature, can represent common research directions in current patents. Therefore, incorporating universal and high-frequency performance attributes into existing performance attributes can better categorize performance attributes extracted from textual documents.

[0063] In one possible implementation, a big data approach can be used to extract efficacy attributes from existing literature, and the frequency of occurrence of each efficacy attribute (e.g., the ratio of the number of occurrences to the total number of efficacy attributes) can be counted. A predetermined number of efficacy attributes, ranked from highest to lowest in frequency, can be obtained as high-frequency efficacy attributes. This disclosure does not specifically limit the method for obtaining high-frequency efficacy attributes or the specific value of the predetermined number.

[0064] In one possible implementation, Figure 2 As shown, the keywords in step S11 also include: efficacy subject, which indicates the subject that produces the efficacy, generally a word related to the technical subject of the document, such as engine, mobile terminal, etc.; efficacy value, which indicates the efficacy produced by the attribute, such as improvement, reduction, decrease, increase, etc.

[0065] Clearly defining the categories of keywords representing efficacy can improve the identification of inventions, facilitate user understanding of the document, enhance the user reading experience, facilitate the commercialization of the technologies in the document, and further enhance the practical value of the document. Keywords representing efficacy alone may not fully demonstrate the technical effects achieved by the technologies mentioned in the document. However, by combining the efficacy subject and at least one of the efficacy values ​​with standardized efficacy attributes to generate keyword groups, a more complete and concise demonstration of efficacy can be achieved.

[0066] In one example, a patent document contains the following: "The terahertz wave polarization beam splitter with a dual-resonance cavity structure of the present invention has the advantages of simple structure, high beam splitting efficiency, small size, low cost, and easy manufacturing, meeting the requirements of applications in terahertz wave imaging, medical diagnosis, terahertz wave communication, and other fields."

[0067] In this text, "terahertz wave polarization beam splitter" is the efficacy subject, "structure" is the efficacy attribute, "simple" is the efficacy value, "splitting rate" is the efficacy attribute, "high" is the efficacy value, "size" is the efficacy attribute, "cost" is the efficacy attribute, and "low" is the efficacy value. Assuming that "structure," "splitting rate," "size," and "cost" are standardized efficacy attributes, combining the efficacy subject, standardized efficacy attributes, and efficacy values ​​can form at least four groups of keyword phrases: (terahertz wave polarization beam splitter, structure, simple), (terahertz wave polarization beam splitter, splitting rate, high), (terahertz wave polarization beam splitter, size, small), and (terahertz wave polarization beam splitter, cost, low). These four phrases provide a complete and concise presentation of the technical effects achieved by the terahertz wave polarization beam splitter in this text in terms of structure, splitting rate, size, and cost.

[0068] Furthermore, the efficacy of the document text is displayed based on the standardized efficacy attributes, including displaying keyword groups. The keywords in each keyword group may be components of the same efficacy display. By displaying keyword groups, the technical effects achieved by the document can be more comprehensively summarized, the document can be better displayed, and it is greatly convenient for users to understand the technical solution and technical effects achieved by the document in the shortest possible time.

[0069] Standardized efficacy attributes and keyword phrases obtained from text documents can be displayed in various scenarios, allowing users to quickly identify the efficacy obtained from the text document and quickly understand the content of the text document, saving time and improving efficiency. In one possible implementation, the efficacy of the document text is displayed based on standardized efficacy attributes, including:

[0070] The efficacy of the document text is displayed according to standardized efficacy attributes in at least one of the following: an efficacy matrix, a document list page, and a document details page.

[0071] The page that displays the efficacy of the document text can also be a page related to other text documents. The present disclosure does not specifically limit the page that displays the efficacy of the document text. Among them, the efficacy matrix uses the two dimensions of technology and efficacy to analyze the current status of patents in a certain field; the document list page includes any page that displays a document list, such as a page that displays search results, a page that displays a workspace or folder of documents, a favorites, etc.; the file details page is a page that specifically describes a text document. The present disclosure does not specifically limit the types of pages included in the document list page, and does not limit the specific display content and display format of the efficacy matrix, document list page, and document details page.

[0072] In a possible implementation, one dimension of the efficacy matrix is ​​the technical classification of the document text, and another dimension is the standardized efficacy attribute or the keyword group. Figure 9 As shown, the nodes in the efficacy matrix show the number of document texts that have the standardized efficacy attributes or keyword groups corresponding to the nodes in the technical classification corresponding to the nodes. Among them, the technical classification can represent the category to which the technology involved in the document belongs, such as the category classified by field, etc. For example, in the efficacy matrix, the node in the 1st row and 1st column represents that the technical classification is "production and processing", and there are 11 documents with the standardized efficacy attribute of "cost". Furthermore, the size of the node icon in the efficacy matrix can reflect the number of document texts corresponding to the node. Through the efficacy matrix, the number of document texts with standardized efficacy attributes or keyword groups corresponding to a certain technical classification can be displayed very intuitively, which is convenient for quickly determining technical gaps or technical hotspots, and has important guiding significance for enterprises to circumvent patent barriers and conduct patent layout.

[0073] In one possible implementation, the document details page may choose to display the keyword phrases and / or standardized efficacy attributes of the document. Further, the document details page may choose to display the efficacy paragraphs in the document. Figure 10 As shown, the document details page includes the document's efficacy paragraph (i.e., intelligent efficacy extraction), standardized efficacy attributes (i.e., intelligent efficacy terms), and keyword phrases (i.e., intelligent efficacy terms - detailed), helping you quickly understand the research content of the document. The efficacy paragraph is not described in detail here and will be introduced later in the text.

[0074] In one possible implementation, the document list page can display the keyword phrases and / or standardized efficacy attributes of a document in the list, and can also display efficacy paragraphs. Figure 10 Similar displays.

[0075] In one possible implementation, the method further includes: in response to the standardized efficacy attribute, the keyword phrase, or the node being triggered, displaying a list of literature texts corresponding to the standardized efficacy attribute, the keyword phrase, or the node. By linking the standardized efficacy attribute, the keyword phrase, or the node with the list of literature texts corresponding to the standardized efficacy attribute, the keyword phrase, or the node, once the standardized efficacy attribute, the keyword phrase, or the node is triggered, the user is quickly redirected to the list of literature texts corresponding to the standardized efficacy attribute, the keyword phrase, or the node, thereby facilitating quick access to the literature corresponding to the standardized efficacy attribute, the keyword phrase, or the node.

[0076] In one example, Figure 9 In the utility matrix shown, clicking a node in the matrix displays a list of documents corresponding to the clicked node. For example, clicking the node in row 1, column 1 displays a list of 11 documents with the technology classification "Production and Processing" and the standardized utility attribute "Cost."

[0077] In one example, Figure 10 In the patent details page shown in , the smart efficacy words are equivalent to standardized efficacy attributes, and the smart efficacy words-details are equivalent to keyword phrases. Clicking on the words or phrases in the smart efficacy words or smart efficacy words-details will display a list of documents corresponding to the clicked standardized efficacy attributes or keyword phrases. For example, clicking on "convenience" in the smart efficacy words will jump to and display a list of document texts with the standardized efficacy attribute "convenience". This disclosure does not specifically limit the scope of the documents displayed in the list.

[0078] In one example, on a document list page, clicking on a keyword phrase or standardized efficacy attribute shown in a document in the list will display a list of documents corresponding to the clicked standardized efficacy attribute or keyword phrase. This disclosure does not specifically limit the scope of the documents displayed in the list.

[0079] In a possible implementation, before step S11, the efficacy paragraph of the document text may be extracted through the second network model; in step S11, the efficacy paragraph is input into the trained first network model to obtain the keyword.

[0080] By extracting efficacy paragraphs through the second network model and eliminating paragraphs unrelated to efficacy, the processing volume of the first network model can be reduced and processing efficiency can be improved. The second network model can be trained using data that pre-labels whether the literature paragraphs are efficacy paragraphs. This application does not limit the implementation method of the second network model.

[0081] For extracting keywords representing efficacy from literature, existing technologies usually use models such as word2vec and Transformer to obtain word vectors, which are then input into a BiLSTM-CRF model to identify keywords representing efficacy. This method has the following disadvantages: (1) It does not clearly define the categories of keywords representing efficacy, resulting in the results being of little significance to productization and having low practical value. It only uses Bert as a way to obtain word vectors, rather than using it as a basic model for fine-tuning to achieve better results; (2) It only uses Bert as a way to obtain word vectors, rather than using it as a basic model for fine-tuning to achieve better results; (3) It does not use a pre-trained language model related to the literature, resulting in low prediction accuracy.

[0082] In one possible implementation, a first network model is trained based on a document text sample and annotations of keywords representing efficacy in the document text sample to obtain the trained first network model, wherein the annotation indication keywords are efficacy subject, efficacy attribute or efficacy value; wherein the efficacy subject represents the subject that produces the efficacy; the efficacy attribute represents the attribute of the subject; and the efficacy value represents the efficacy produced by the attribute. Figure 5 The text fragment is marked with keywords that represent efficacy, and the first phrase (efficacy subject, efficacy attribute) and the second phrase (efficacy attribute, efficacy value) that constitute the keyword. Figure 5 In

[15] , the label "Theme" represents the efficacy subject, the label "Attr" represents the efficacy attribute, and the label "Val" represents the efficacy value. The two efficacy keywords that constitute the first phrase and the second phrase are connected by a connecting line, and are marked "Theme of" and "Attribute of" on the connecting line to distinguish them. The arrows on the connecting line represent the attribution relationship. As described above, the first phrase and the second phrase of the keyword group are marked in the document text to realize the training of the first network model.

[0083] Figure 4 A flowchart of an embodiment of the present disclosure is shown, and the process of training the first network model includes:

[0084] S101. Mark the efficacy attributes, efficacy subject, and efficacy value in the efficacy paragraph;

[0085] S102: Based on the labeled data in S101, use the first network model to perform training and parameter adjustment to obtain a trained first network model.

[0086] In a possible implementation, the first network model may include a Bert-CRF, LSTM-CRF, or CRF model. This application does not limit the implementation of the first network model.

[0087] In one example, Bert-CRF was used as the first network model. A key factor in the success of deep learning is a training set consisting of a large amount of labeled data. The Bert-CRF model was used to extract three target entities from literature text: efficacy subject, efficacy attribute, and efficacy value. By fine-tuning the parameters of the pre-trained Bert-CRF model, using a small amount of literature domain word segmentation annotation data, and then using the Bert-CRF network structure to optimize word segmentation, the Bert network parameters were fine-tuned. The fine-tuned word vectors were fused using different strategies to generate coarse-grained vector representations of literature domain-specific vocabulary. This method not only helps improve the accuracy of literature domain word segmentation, but also achieves the goal of generating high-quality word vector representations for the literature domain using only a small amount of literature domain annotated data. It not only has unique advantages in text feature expression, but also saves a lot of time and can achieve better training results using less literature text data, making it very efficient.

[0088] In a possible embodiment, the document effectiveness display method also includes: obtaining at least one short sentence of the document text, where the short sentence is the content between adjacent punctuation marks in the document text; determining the keyword group in the same paragraph based on the keywords in the same short sentence and the keywords in the same paragraph; and deleting repeated keyword groups in the determined keyword groups of the document text.

[0089] Punctuation marks are used to indicate pauses and are used to mark sentences. They include commas, colons, semicolons, periods, question marks, and exclamation marks. Punctuation marks are used to divide a document into sections, with the content between the punctuation marks being considered as a short sentence.

[0090] After segmenting the literature's efficacy paragraphs into short sentences, keyword phrases representing efficacy can be constructed simultaneously for multiple short sentences in the same paragraph, which can improve the efficiency of literature efficacy display. Deleting repeated keyword phrases in the literature text helps to remove redundant and repetitive information, making the obtained literature efficacy display more concise and more readable.

[0091] In one example, a functional paragraph is extracted from the text of a patent document: "The thermal insulation material of the present invention has low thermal conductivity, simple structure, and good thermal insulation effect". The paragraph is divided into three short sentences by commas, among which "The thermal insulation material of the present invention has low thermal conductivity" is a short sentence, "Simple structure" is a short sentence, and "Good thermal insulation effect" is another short sentence. After the paragraph is divided into short sentences, all the keywords in the entire paragraph are extracted (thermal insulation material, thermal conductivity, low, structure, simple, thermal insulation effect, good), and these keywords can be divided into the short sentences to which they belong: the keywords extracted in the first sentence are "thermal insulation material", "thermal conductivity", and "low", the keywords extracted in the second sentence are "structure", "simple", and the keywords extracted in the third sentence are "thermal insulation effect" and "good". Assuming that "thermal conductivity", "structure", and "thermal insulation effect" are standardized functional attributes, the keyword groups can be constructed for the three short sentences at the same time to determine the keyword groups of the paragraph (thermal insulation material, thermal conductivity, low), (structure, simple), and (thermal insulation effect, good). After identifying the keyword phrases in the paragraph, check all keyword phrases in the patent text and delete any duplicate keyword phrases. For example, if the keyword phrase (insulation material, thermal conductivity, low) appears in multiple places throughout the patent text, delete the duplicates and retain only one instance of the keyword phrase to facilitate reading and improve the user experience.

[0092] In one possible implementation, determining the keyword group in the same paragraph includes: in the same paragraph, taking the standardized efficacy attribute of each efficacy attribute and the efficacy subject preceding the efficacy attribute and being closest to the efficacy attribute as the first phrase; in the same short sentence, taking each efficacy value and the standardized efficacy attribute of the efficacy attribute preceding the efficacy value and being closest to the efficacy value as the second phrase; merging a first phrase and a second phrase containing the same efficacy attribute in the same paragraph into a third phrase; and taking at least one of the first phrase, the second phrase, and the third phrase as the keyword group.

[0093] Through the above method, we can identify the key words in the efficacy paragraph and simultaneously break the relatively complex problem of finding the third phrase (efficacy subject, efficacy attribute, efficacy value) in the key words into two relatively simple and similar sub-problems: finding (efficacy subject, efficacy attribute) and (efficacy attribute, efficacy value). After solving the sub-problems, we merge the sub-problems to obtain the original problem. This recursive approach helps reduce the complexity of problem solving and efficiently find key words in the document text.

[0094] In one example, a paragraph in the patent document reads as follows: "The terahertz wave polarization beam splitter with a dual-resonance cavity structure of the present invention has the advantages of simple structure, high beam splitting efficiency, small size, low cost, and easy manufacturing, meeting the requirements of applications in terahertz wave imaging, medical diagnosis, terahertz wave communication, and other fields."

[0095] In this efficacy paragraph, there is an efficacy subject: terahertz wave polarization beam splitter, there are efficacy attributes: structure, splitting rate, size, cost, and there are efficacy values: simple, high, small, and low. The standardization process of efficacy attributes will not be described in detail here, but will be introduced in the following text. The process of obtaining the keyword group is: first, traverse to the efficacy subject "terahertz wave polarization beam splitter" that is closest to the efficacy attribute "structure" before the efficacy attribute "structure" in the paragraph; then, according to the standardized efficacy attribute "structure" of "structure", a first phrase (terahertz wave polarization beam splitter, structure) is formed, and similarly, the other three first phrases (terahertz wave polarization beam splitter, splitting rate), (terahertz wave polarization beam splitter, size) and (terahertz wave polarization beam splitter, cost) are obtained; when traversing to the efficacy value "simple", the efficacy attribute "structure" that is closest to the efficacy value is selected before the efficacy value in the short sentence where the efficacy value is located as the efficacy value pair. According to the standardized efficacy attribute of "structure", the second phrase (structure, simple) is obtained. Similarly, the other three second phrases (splitting rate, high), (size, small), and (cost, low) are obtained. The first phrase (terahertz wave polarization beam splitter, structure) and the second phrase (structure, simple) containing the standardized efficacy attribute of structure in the same paragraph are merged to obtain the third phrase (terahertz wave polarization beam splitter, structure, simple). Similarly, the other three third phrases (terahertz wave polarization beam splitter, splitting rate, high), (terahertz wave polarization beam splitter, size, small), and (terahertz wave polarization beam splitter, cost, low) are obtained. So far, the keyword groups obtained in this efficacy paragraph include four third phrases, four second phrases, and four first phrases. Further, the keyword groups to be displayed can be selected according to actual needs.

[0096] Because the names of the efficacy attributes in the generated keyword groups may appear inconsistent due to synonyms, redundant prefixes, and non-standard wording, but the actual content is the same, this interference will confuse users, hinder the discovery of similar technologies, and reduce user experience. Therefore, it is necessary to standardize the efficacy attributes.

[0097] Currently, there is no standardization of keywords representing efficacy in existing technologies. Without standardization of efficacy attributes, a large number of different text documents may use keywords with different names but the same content. This makes it difficult to quickly classify documents studying the same efficacy, thereby limiting the scope of application of the documents, resulting in inaccurate efficacy matrix analysis and inconsistent automatic indexing of literature efficacy.

[0098] In a possible implementation, the efficacy attribute is matched with an existing efficacy attribute to obtain a matching result; and based on the matching result, a standardized efficacy attribute of the efficacy attribute is determined.

[0099] The matching operation is the standardization of efficacy attributes. By matching the efficacy attributes in the keyword group with the existing efficacy attributes, all efficacy attributes are standardized into unified various existing efficacy attributes. On the one hand, the document is more readable, making it easier for users to understand the effects achieved by the document and find documents with similar technical effects; on the other hand, this operation helps to expand the application scope of the document and is applied in efficacy matrix analysis and automatic indexing of document efficacy.

[0100] Among them, the existing efficacy attributes can be stored as an efficacy attribute list. In addition, a synonym word list of the existing efficacy attributes is also provided to facilitate user query and use.

[0101] In one possible implementation, the efficacy attributes in the keyword group are matched with existing efficacy attributes, such as Figure 3 As shown in the flowchart shown, it includes:

[0102] S131: performing a first matching operation on the efficacy attribute in the keyword group and the existing efficacy attributes, and obtaining a first matching result corresponding to the efficacy attribute for which the first matching operation succeeds when the first matching operation succeeds;

[0103] S132: performing a second matching operation on the efficacy attribute for which the first matching operation failed and the synonyms of the existing efficacy attribute, and obtaining a second matching result corresponding to the efficacy attribute for which the second matching operation succeeded when the second matching operation succeeds;

[0104] S133: performing a third matching operation on the suffix of the efficacy attribute for which the second matching operation failed and the existing efficacy attributes, and obtaining a third matching result corresponding to the efficacy attribute for which the third matching operation succeeded when the third matching operation succeeds;

[0105] S134: performing a fourth matching operation on the word vectors of the efficacy attributes for which the third matching operation failed, and the word vectors of the existing efficacy attributes. When the fourth matching operation succeeds, a fourth matching result corresponding to the efficacy attributes for which the fourth matching operation succeeds is obtained.

[0106] Wherein, the second matching result includes an existing efficacy attribute, and a synonym of the existing efficacy attribute successfully matches the efficacy attribute in the keyword group;

[0107] The fourth matching result includes an existing efficacy attribute, and the word vector of the existing efficacy attribute successfully matches the word vector of the efficacy attribute in the keyword group.

[0108] The efficacy attributes are standardized using the four progressive methods of first match, second match, third match and fourth match, making the standardization more accurate and comprehensive and avoiding omissions.

[0109] When the first and third matching results of the efficacy attribute in the document are successful matches, it may indicate that the efficacy attribute is the same as an existing efficacy attribute, or the suffix of the efficacy attribute is the same as an existing efficacy attribute. Therefore, the first and third matching results may not include the matched existing efficacy attribute, but instead return response information or identification information indicating a successful match, such as a preset symbol or string indicating a successful match. The second matching result may include the existing efficacy attribute, and the synonym of the existing efficacy attribute matches the efficacy attribute in the keyword group. The fourth matching result may include the existing efficacy attribute, and the word vector of the existing efficacy attribute matches the word vector of the efficacy attribute in the keyword group.

[0110] The similarity of word vectors can be determined using a similarity measurement method, such as the distance or angle between the word vectors. When the similarity value is greater than a threshold, the word vectors of the two words being compared are determined to be similar. Similarity measurement methods can include Euclidean distance, cosine similarity, Pearson correlation coefficient, etc. The specific similarity measurement method used is not limited by this disclosure.

[0111] In one possible implementation, determining the standardized efficacy attribute of the efficacy attribute based on the matching result may include: when the first matching operation, the second matching operation, the third matching operation or the fourth matching operation of the efficacy attribute is successful, determining the standardized efficacy attribute based on the first matching result, the second matching result, the third matching result or the fourth matching result; when the first matching operation, the second matching operation, the third matching operation and the fourth matching operation of the efficacy attribute are all unsuccessful, setting the standardized efficacy attribute to "other".

[0112] For example, if the first matching operation of a certain efficacy attribute is successful, the efficacy attribute itself can be directly used as its standardized efficacy attribute. If the second matching operation is successful, the efficacy attribute returned in the second matching result can be used as its standardized efficacy attribute. If the third matching operation is successful, the suffix of the efficacy attribute itself can be used as its standardized efficacy attribute. If the fourth matching operation is successful, the efficacy attribute returned in the fourth matching result can be used as its standardized efficacy attribute. If all the above matching operations are unsuccessful, the standardized efficacy attribute can be set to "Other".

[0113] In one example, the second network model extracts the following efficacy paragraph: "The present invention can send processable data access requests from client data access requests to the database for processing based on the database's processing capabilities, thereby ensuring that the database can promptly process the processable data access requests. This reduces the database's processing pressure while also improving data processing efficiency, enhancing data processing capabilities, and increasing data processing speed."

[0114] The efficiency attributes extracted from this paragraph are: processing pressure, processing efficiency, capacity, and rate. Matching operations are performed on these four efficiency attributes:

[0115] The first matching operation is performed against the efficacy attribute list containing existing common efficacy attribute words. The word "capability" is matched, resulting in a first matching result corresponding to the efficacy attribute for which the first matching operation succeeded. The first matching result for "capability" is "matched successfully." "Processing pressure," "Processing efficiency," and "rate" are not matched successfully, so the second matching operation is performed against the synonym word list.

[0116] The second matching operation: A match is performed against a synonym word list containing synonyms for existing common efficacy attribute words. The word "rate" is matched. As is known, "rate" in the synonym word list is a synonym for "speed" in the efficacy attribute list. The second matching result for the efficacy attribute for which the second matching operation succeeded is obtained. The second matching result for "rate" is "matched successfully" and "speed," a synonym for "rate." "Processing pressure" and "Processing efficiency" do not match successfully. A third matching operation is performed against their suffixes, "pressure" and "efficiency," in the efficacy attribute list.

[0117] The third matching operation: The suffixes "pressure" and "efficiency" of the two words "processing pressure" and "processing efficiency" are matched against the efficacy attribute list. If the matches are successful, the third matching result corresponding to the efficacy attribute for which the third matching operation succeeded is obtained. The matching results for "processing pressure" and "processing efficiency" are "matched successfully." All four efficacy attributes, "processing pressure," "processing efficiency," "capacity," and "rate," have been matched, and the matching operation is complete.

[0118] Therefore, the efficacy attributes “processing pressure”, “processing efficiency”, “capacity” and “rate” extracted from the literature were standardized, and the standardized efficacy attributes obtained were “pressure”, “efficiency”, “capacity” and “speed”.

[0119] In one example, the second network model extracts the efficacy paragraph "The thermal insulation material of the present invention has low thermal conductivity, simple structure, and good thermal insulation effect." The efficacy attributes extracted from this paragraph are: thermal conductivity, structure, and thermal insulation effect. Matching operations are performed on these three efficacy attributes:

[0120] The first matching operation is to match the efficacy attribute list that stores existing common efficacy attribute words. If "thermal conductivity", "structure" and "thermal insulation effect" are not matched successfully, the second matching operation is continued in the synonym word list.

[0121] The second matching operation: matching with the synonym word list that stores the existing synonyms of common efficacy attribute vocabulary, "thermal conductivity", "structure" and "thermal insulation effect" are not matched successfully, "thermal conductivity" and "thermal insulation effect" continue to perform the third matching operation in the efficacy attribute list with their suffixes "coefficient" and "effect", and "structure" has no suffix, so the fourth matching operation is performed.

[0122] The third matching operation: the suffixes "coefficient" and "effect" of the two words "thermal conductivity" and "thermal insulation effect" are matched in the efficacy attribute list respectively. If the matching is unsuccessful, the fourth matching operation is continued for "thermal conductivity" and "thermal insulation effect".

[0123] Fourth matching operation: The three efficacy attributes "thermal conductivity," "structure," and "insulation effect" are mapped to word vectors using the trained word2vec word vectors. Cosine similarity is calculated with the vectors of each word in the predefined efficacy attribute list. Results with a value greater than 0.9 are selected. "Structure" matches "structure," resulting in the fourth matching result corresponding to the efficacy attribute for which the fourth matching operation succeeded. The fourth matching result for "Structure" includes "Match Successful" and "Structure," which matches the word vector for "Structure." No matching results are found for the efficacy attributes "thermal conductivity" and "insulation effect," and the result returns "Other." "Thermal conductivity," "Structure," and "Insulation effect" have all been matched, and the matching operation is complete.

[0124] Therefore, after the efficiency attributes “thermal conductivity”, “structure” and “thermal insulation effect” extracted from the literature were standardized, the standardized efficiency attributes obtained were “others”, “structure” and “others”.

[0125] In this way, the standardization of efficacy attributes in document texts is achieved. In an exemplary application scenario, the standardized efficacy attributes "pressure", "efficiency", "capacity" and "speed" can be displayed. When the displayed "speed" is selected, documents containing the standardized efficacy attribute can be retrieved, for example, documents containing the efficacy attribute "rate" and "speed" with the standardized efficacy attribute of "speed" can be retrieved. The retrieved documents can be presented in a list. In addition, the documents after standardization can also be widely used in other application scenarios, such as document retrieval, classification, and as indexed samples for model training, etc.

[0126] It is understood that the above-mentioned various method embodiments mentioned in this disclosure can be combined with each other to form combined embodiments without violating the principle logic. Due to space limitations, this disclosure will not go into details. It is understood by those skilled in the art that in the above-mentioned methods of specific implementation, the specific execution order of each step should be determined by its function and possible internal logic.

[0127] In addition, the present disclosure also provides a document efficacy display device, an electronic device, a computer-readable storage medium, and a program, all of which can be used to implement any document efficacy display method provided by the present disclosure. The corresponding technical solutions and descriptions can be found in the corresponding records in the method section and will not be repeated here.

[0128] Figure 6 A block diagram of a document efficacy display device according to an embodiment of the present disclosure is shown as follows: Figure 6 As shown, the device includes:

[0129] A keyword extraction module 61 is used to extract keywords representing efficacy from the document text, wherein the keywords include efficacy attributes, and the efficacy attributes represent the attributes of the subject that produces the efficacy;

[0130] A standardization module 62 is configured to standardize the efficacy attributes based on the existing efficacy attributes to obtain standardized efficacy attributes;

[0131] The efficacy display module 63 is used to display the efficacy of the document text according to the standardized efficacy attributes.

[0132] In one possible implementation, the keyword also includes: an efficacy subject and an efficacy value, wherein the efficacy subject represents the subject that produces the efficacy, and the efficacy value represents the efficacy produced by the attribute; the efficacy display module includes: a keyword group display sub-module, used to display keyword groups, and the keyword group includes at least one of the efficacy subject and the efficacy value and a combination of the standardized efficacy attributes.

[0133] In a possible implementation, the efficacy display module includes: an efficacy display submodule, which is used to display the efficacy of the document text according to standardized efficacy attributes in at least one of the following: efficacy matrix, document list page, and document details page.

[0134] In one possible implementation, one dimension of the efficacy matrix is ​​the technical classification of the document text, and another dimension is the standardized efficacy attribute or the keyword group; the nodes in the efficacy matrix show the number of document texts in the technical classification corresponding to the node that have the standardized efficacy attribute or keyword group corresponding to the node.

[0135] In a possible implementation, the device further includes: a trigger display module for displaying a list of document texts corresponding to the standardized efficacy attribute, the keyword group or the node in response to the standardized efficacy attribute, the keyword group or the node being triggered.

[0136] In a possible implementation, the standardization module includes: a matching submodule, configured to match the efficacy attribute with an existing efficacy attribute to obtain a matching result; and a standardized efficacy attribute determination submodule, configured to determine a standardized efficacy attribute of the efficacy attribute based on the matching result.

[0137] In a possible implementation, the matching submodule is used to: perform a first matching operation on the efficacy attribute and the existing efficacy attribute, and when the first matching operation is successful, obtain a first matching result corresponding to the efficacy attribute that is successful in the first matching operation; perform a second matching operation on the efficacy attribute that is unsuccessful in the first matching operation and the synonym of the existing efficacy attribute, and when the second matching operation is successful, obtain a second matching result corresponding to the efficacy attribute that is successful in the second matching operation; perform a third matching operation on the suffix of the efficacy attribute that is unsuccessful in the second matching operation and the existing efficacy attribute, and when the third matching operation is successful, obtain a third matching result corresponding to the efficacy attribute that is successful in the third matching operation; convert the efficacy attribute that is unsuccessful in the third matching operation into a word vector, and perform a fourth matching operation on the word vector of the existing efficacy attribute, and in the fourth When the matching operation is successful, a fourth matching result corresponding to the efficacy attribute for which the fourth matching operation is successful is obtained; wherein, the second matching result includes an existing efficacy attribute, and the synonym of the existing efficacy attribute is successfully matched with the efficacy attribute; the fourth matching result includes an existing efficacy attribute, and the word vector of the existing efficacy attribute is successfully matched with the word vector of the efficacy attribute; the standardized efficacy attribute determination submodule is used to: when the first matching operation, the second matching operation, the third matching operation or the fourth matching operation of the efficacy attribute is successful, determine the standardized efficacy attribute according to the first matching result, the second matching result, the third matching result or the fourth matching result; when the first matching operation, the second matching operation, the third matching operation and the fourth matching operation of the efficacy attribute are all unsuccessful, set the standardized efficacy attribute to other.

[0138] In one possible implementation, the device further includes: a short sentence acquisition module, used to acquire at least one short sentence of the document text, wherein the short sentence includes the content between adjacent punctuation marks in the document text; a keyword group determination module, used to determine the keyword group in the same paragraph based on the keywords in the same short sentence and the keywords in the same paragraph; and a repeated phrase deletion module, used to delete repeated keyword groups in the determined keyword groups of the document text.

[0139] In one possible implementation, the keyword group determination module includes: a first phrase determination submodule, which is used to use the standardized efficacy attribute of each efficacy attribute and the efficacy subject before the efficacy attribute and closest to the efficacy attribute in the same paragraph as the first phrase; a second phrase determination submodule, which is used to use the standardized efficacy attribute of each efficacy value and the efficacy attribute before the efficacy value and closest to the efficacy value in the same short sentence as the second phrase; a third phrase determination submodule, which is used to merge a first phrase and a second phrase containing the same standardized efficacy attribute in the same paragraph into a third phrase; and a keyword group determination submodule, which is used to use at least one of the first phrase, the second phrase, and the third phrase as the keyword group.

[0140] In one possible implementation, the existing efficacy attributes include general efficacy attributes and high-frequency efficacy attributes; wherein, the general efficacy attributes include efficacy attributes obtained based on general engineering parameters of TRIZ theory; the high-frequency efficacy attributes include a preset number of efficacy attributes obtained by extracting efficacy attributes from existing literature and sorting them by frequency of occurrence from high to low.

[0141] In one possible implementation, the device also includes: an efficacy paragraph extraction module, which is used to extract the efficacy paragraph in the document text through the second network model; and the keyword extraction module, which is used to input the efficacy paragraph into the trained first network model to obtain the keyword.

[0142] In one possible implementation, the device also includes: a first network training module, used to train a first network model based on a document text sample and an annotation of keywords representing efficacy in the document text sample to obtain the trained first network model, wherein the annotation indication keyword is an efficacy subject, an efficacy attribute or an efficacy value; wherein the efficacy subject represents the subject that produces the efficacy; the efficacy attribute represents the attribute of the subject; and the efficacy value represents the efficacy produced by the attribute.

[0143] In a possible implementation, the first network model includes a Bert-CRF, LSTM-CRF, or CRF model.

[0144] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0145] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium may be a non-volatile computer-readable storage medium.

[0146] An embodiment of the present disclosure further proposes an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above method.

[0147] The embodiment of the present disclosure further provides a computer program product, including computer-readable code. When the computer-readable code is run on a device, a processor in the device executes instructions for implementing the above method.

[0148] The embodiment of the present disclosure further provides a computer-readable storage medium having computer program instructions stored thereon, and the computer program instructions implement the above method when executed by a processor.

[0149] The electronic device may be provided as a terminal, a server, or other forms of devices.

[0150] Figure 7 The block diagram of an electronic device 800 according to an embodiment of the present disclosure is shown. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like.

[0151] Reference Figure 7 , the electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0152] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 802 may include one or more modules to facilitate interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

[0153] The memory 804 is configured to store various types of data to support operations on the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0154] The power supply component 806 provides power to the various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 800.

[0155] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the electronic device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0156] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), which is configured to receive external audio signals when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0157] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0158] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the electronic device 800, the relative positioning of components, such as the display and keypad of the electronic device 800. The sensor assembly 814 can also detect changes in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a complementary metal oxide semiconductor (CMOS) or charge coupled device (CCD) image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0159] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as a wireless network (WiFi), a second generation mobile communication technology (2G) or a third generation mobile communication technology (3G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0160] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0161] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 804 including computer program instructions. The computer program instructions can be executed by the processor 820 of the electronic device 800 to perform the above method.

[0162] Figure 8FIG1 shows a block diagram of an electronic device 1900 according to an embodiment of the present disclosure. For example, the electronic device 1900 can be provided as a server. The processing result of the server can be sent to the terminal device and displayed by the terminal device. Figure 8 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute the instructions to perform the above-described method.

[0163] Electronic device 1900 may also include a power supply component 1926 configured to perform power management for electronic device 1900, a wired or wireless network interface 1950 configured to connect electronic device 1900 to a network, and an input / output (I / O) interface 1958. Electronic device 1900 may operate based on an operating system stored in memory 1932, such as Microsoft Windows Server™, Apple's Mac OS X™, a multi-user multi-process computer operating system (Unix™), a free and open source Unix-like operating system (Linux™), an open source Unix-like operating system (FreeBSD™), or the like. In an exemplary embodiment, a non-volatile computer-readable storage medium, such as memory 1932, including computer program instructions is also provided. The computer program instructions are executable by processing component 1922 of electronic device 1900 to perform the above-described method.

[0164] The present disclosure may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0165] A computer-readable storage medium can be a tangible device that can hold and store instructions for use by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: 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), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination thereof. As used herein, a computer-readable storage medium is not to be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through an electrical wire.

[0166] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0167] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, 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 via 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., utilizing an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions. The electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0168] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0169] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0170] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0171] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and the part of the module, program segment or instruction contains one or more executable instructions for realizing the prescribed logical function. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two consecutive boxes 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 box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the prescribed function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0172] While various embodiments of the present disclosure have been described above, the foregoing description is intended to be illustrative, non-exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or technological improvements in the marketplace, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for displaying the efficacy of a document, characterized in that: include: Extracting keywords representing efficacy from the document text, wherein the keywords include efficacy attributes, and the efficacy attributes represent attributes of a subject that produces the efficacy; Based on existing efficacy attributes, the efficacy attributes are standardized to obtain standardized efficacy attributes; the existing efficacy attributes include general efficacy attributes and high-frequency efficacy attributes; wherein the general efficacy attributes include efficacy attributes obtained based on general engineering parameters of TRIZ theory; the high-frequency efficacy attributes include a preset number of efficacy attributes obtained by sorting efficacy attributes extracted from existing literature in descending order of frequency of occurrence; Demonstrating the efficacy of the document text based on standardized efficacy attributes; The step of standardizing the efficacy attributes based on the existing efficacy attributes to obtain standardized efficacy attributes includes: Matching the efficacy attribute with existing efficacy attributes to obtain a matching result; determining a standardized efficacy attribute of the efficacy attribute based on the matching result; The step of matching the efficacy attribute with the existing efficacy attribute to obtain a matching result includes: Performing a first matching operation on the efficacy attribute and the existing efficacy attribute, and obtaining a first matching result corresponding to the efficacy attribute for which the first matching operation succeeds when the first matching operation succeeds; Performing a second matching operation on the efficacy attribute for which the first matching operation failed and the synonyms of the existing efficacy attribute, and obtaining a second matching result corresponding to the efficacy attribute for which the second matching operation succeeded when the second matching operation succeeds; Performing a third matching operation on the suffix of the efficacy attribute for which the second matching operation failed with the existing efficacy attribute, and obtaining a third matching result corresponding to the efficacy attribute for which the third matching operation succeeded when the third matching operation succeeds; Performing a fourth matching operation on the word vectors of the efficacy attributes for which the third matching operation failed, and the word vectors of the existing efficacy attributes, and obtaining a fourth matching result corresponding to the efficacy attributes for which the fourth matching operation succeeded, when the fourth matching operation succeeds; Wherein, the second matching result includes an existing efficacy attribute, and a synonym of the existing efficacy attribute successfully matches the efficacy attribute; The fourth matching result includes an existing efficacy attribute, and the word vector of the existing efficacy attribute successfully matches the word vector of the efficacy attribute.

2. The method according to claim 1, characterized in that The keywords also include: efficacy subject and efficacy value, wherein the efficacy subject represents the subject that produces the efficacy, and the efficacy value represents the efficacy produced by the attribute; The display of the efficacy of the document text according to the standardized efficacy attribute includes: A keyword group is presented, the keyword group including a combination of at least one of the efficacy subject and the efficacy value and the standardized efficacy attribute.

3. The method according to claim 1 or 2, characterized in that The display of the efficacy of the document text according to the standardized efficacy attribute includes: The efficacy of the document text is displayed according to standardized efficacy attributes in at least one of the following: an efficacy matrix, a document list page, and a document details page.

4. The method according to claim 3, characterized in that One dimension of the efficacy matrix is ​​the technical classification of the document text, and another dimension is the standardized efficacy attribute or the keyword group; A node in the efficacy matrix shows the number of document texts in the technical category corresponding to the node that have the standardized efficacy attribute or keyword group corresponding to the node.

5. The method according to claim 4, characterized in that The method further comprises: In response to the standardized efficacy attribute, the keyword group or the node being triggered, a list of document texts corresponding to the standardized efficacy attribute, the keyword group or the node is displayed.

6. The method according to claim 1, wherein Determining the standardized efficacy attribute of the efficacy attribute based on the matching result includes: When the first matching operation, the second matching operation, the third matching operation or the fourth matching operation of the efficacy attribute is successful, determining the standardized efficacy attribute according to the first matching result, the second matching result, the third matching result or the fourth matching result; When the first matching operation, the second matching operation, the third matching operation and the fourth matching operation of the efficacy attribute are all unsuccessful, the standardized efficacy attribute is set to other.

7. The method according to claim 2, characterized in that The method further comprises: Acquire at least one short sentence of the document text, wherein the short sentence includes content between adjacent punctuation marks in the document text; According to the keywords in the same short sentence and the keywords in the same paragraph, determine the keyword group in the same paragraph; Delete repeated keyword groups in the determined keyword groups of the document text.

8. The method according to claim 7, characterized in that Determining the keyword group in the same paragraph based on the keywords in the same sentence and the keywords in the same paragraph includes: In the same paragraph, the standardized efficacy attribute of each efficacy attribute and the efficacy subject preceding the efficacy attribute and closest to the efficacy attribute are taken as the first phrase; In the same short sentence, each efficacy value and the standardized efficacy attribute of the efficacy attribute that precedes the efficacy value and is closest to the efficacy value are used as a second phrase; Merging a first phrase and a second phrase in the same paragraph containing the same standardized efficacy attribute into a third phrase; At least one of the first word group, the second word group, and the third word group is used as the keyword group.

9. The method according to claim 1, characterized in that The method further comprises: extracting efficacy paragraphs from the document text through a second network model; The extracted keywords representing efficacy in the literature text include: The efficacy paragraph is input into the trained first network model to obtain the keywords.

10. The method according to claim 9, characterized in that The method further comprises: Training a first network model based on a document text sample and annotations of keywords representing efficacy in the document text sample to obtain the trained first network model, wherein the annotations are used to indicate that the keywords are efficacy subjects, efficacy attributes, or efficacy values; Among them, efficacy subject refers to the subject that produces efficacy; Efficacy attributes, representing the attributes of the subject; The efficacy value represents the efficacy produced by the attribute.

11. The method according to claim 9 or 10, characterized in that The first network model includes a Bert-CRF, LSTM-CRF or CRF model.

12. A document efficacy display device, characterized in that: include: A keyword extraction module is used to extract keywords representing efficacy from the document text, wherein the keywords include efficacy attributes, and the efficacy attributes represent the attributes of the subject that produces the efficacy; A standardization module is configured to standardize existing efficacy attributes based on the efficacy attributes to obtain standardized efficacy attributes; the existing efficacy attributes include general efficacy attributes and high-frequency efficacy attributes; wherein the general efficacy attributes include efficacy attributes obtained based on general engineering parameters of TRIZ theory; and the high-frequency efficacy attributes include a preset number of efficacy attributes obtained by sorting efficacy attributes extracted from existing literature in descending order of frequency of occurrence; An efficacy display module, used to display the efficacy of the document text according to standardized efficacy attributes; The standardization module is further used to: Matching the efficacy attribute with existing efficacy attributes to obtain a matching result; Determining a standardized efficacy attribute of the efficacy attribute based on the matching result; wherein matching the efficacy attribute with the existing efficacy attribute to obtain a matching result includes: Performing a first matching operation on the efficacy attribute and the existing efficacy attribute, and obtaining a first matching result corresponding to the efficacy attribute for which the first matching operation succeeds when the first matching operation succeeds; Performing a second matching operation on the efficacy attribute for which the first matching operation failed and the synonyms of the existing efficacy attribute, and obtaining a second matching result corresponding to the efficacy attribute for which the second matching operation succeeded when the second matching operation succeeds; Performing a third matching operation on the suffix of the efficacy attribute for which the second matching operation failed with the existing efficacy attribute, and obtaining a third matching result corresponding to the efficacy attribute for which the third matching operation succeeded when the third matching operation succeeds; Performing a fourth matching operation on the word vectors of the efficacy attributes for which the third matching operation failed, and the word vectors of the existing efficacy attributes, and obtaining a fourth matching result corresponding to the efficacy attributes for which the fourth matching operation succeeded, when the fourth matching operation succeeds; Wherein, the second matching result includes an existing efficacy attribute, and a synonym of the existing efficacy attribute successfully matches the efficacy attribute; The fourth matching result includes an existing efficacy attribute, and the word vector of the existing efficacy attribute successfully matches the word vector of the efficacy attribute.

13. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 11.

14. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images