Technical document data analysis method, computer device and computer readable storage medium

Abstract

The present invention provides a technical document data analysis method, a computer device and a computer-readable storage medium, the method comprising obtaining a target keyword, obtaining a target technical document according to the target keyword; obtaining molecular structure information of compounds in the target technical document, the number of compounds obtained being two or more; identifying the skeleton structure of the compound according to the molecular structure information of the compound, and obtaining the skeleton structure of each compound; counting the number of occurrences of each skeleton structure, obtaining several skeleton structures with the largest number of occurrences as high-frequency skeleton structures, and displaying the technical document information corresponding to each high-frequency skeleton structure. The present invention also provides a computer device and a computer-readable storage medium for implementing the above method. The present invention can facilitate researchers to obtain molecular structure information of compounds in chemical technical documents.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing, and in particular to a method for data analysis of chemical technical literature, and also to a computer device and a computer-readable storage medium for implementing the method. Background Art

[0002] Patent information and technical papers are common technical information, which are of great significance for studying the development of technology. By statistically analyzing patent information and technical papers to form technical literature data, we can study the development trend of a certain technical field. Analyzing technical literature data is of great significance for studying the development direction of chemical products, medicines, etc.

[0003] Most of the existing technical literature data analysis methods are to search for technical literature based on keywords input by users, for example, by matching keywords to obtain multiple technical literatures, thereby obtaining multiple technical literatures related to a certain technical field. Existing technical literature data analysis systems are usually able to perform simple statistics and analysis on technical literature data, such as the number of technical literatures retrieved, publication dates, patent applicants, and inventors. However, for chemical technologies, researchers hope to understand the molecular structure information of the compounds introduced in the technical literature for a certain technical field by analyzing the molecular structures introduced in the technical literature, and hope to perform statistics and analysis on the molecular structures of various compounds introduced in the field to understand the research results in the field of technology.

[0004] However, the existing technical literature analysis methods do not have intelligent analysis of compound molecular structure information. If they rely on manual analysis of compound molecular structure information, the technical literature data analysis in the field of chemistry will suffer from large analysis workload and low analysis efficiency, which is not conducive to promoting technical literature data statistics in the field of chemistry, nor is it conducive to the sharing of technical information in the field of chemistry. Summary of the invention

[0005] The first object of the present invention is to provide a technical literature data analysis method that can intelligently realize the molecular structure information analysis of compounds.

[0006] The second object of the present invention is to provide a computer device for implementing the above-mentioned operating device technical document data analysis method.

[0007] The third object of the present invention is to provide a computer-readable storage medium for implementing the above-mentioned operating device technical document data analysis method.

[0008] To achieve the main purpose of the present invention, the technical literature data analysis method provided by the present invention includes obtaining target keywords, obtaining target technical documents based on the target keywords; obtaining molecular structure information of compounds in the target technical documents, and the number of compounds obtained is more than two; identifying the skeleton structure of the compound based on the molecular structure information of the compound, and obtaining the skeleton structure of each compound; counting the number of occurrences of each skeleton structure, obtaining several skeleton structures with the largest number of occurrences as high-frequency skeleton structures, and displaying the technical literature information corresponding to each high-frequency skeleton structure.

[0009] It can be seen from the above scheme that the present invention obtains analytical information, such as high-frequency skeleton structures, by analyzing the molecular structures of the compounds in each target technical document and obtaining the skeleton structures of the compounds. Researchers can easily obtain several skeleton structures that appear most frequently in this technical field, providing good basic information for subsequent research.

[0010] A preferred solution is that displaying the technical literature information corresponding to each high-frequency skeleton structure includes: displaying the number of technical literature corresponding to each high-frequency skeleton structure and the summary information of each technical literature corresponding to each high-frequency skeleton structure.

[0011] It can be seen that users can easily browse the number of technical documents corresponding to each high-frequency skeleton structure, so as to quickly determine the frequency of each high-frequency skeleton structure appearing in the target technical document, which is convenient for researchers' subsequent research work.

[0012] A further solution is that identifying the skeleton structure of the compound according to the molecular structure information of the compound includes: identifying the initial skeleton structure of the compound, clustering the identified multiple initial skeleton structures, and obtaining multiple clustered skeleton structures.

[0013] It can be seen that by clustering the initial skeleton structures and reducing the number of displayed skeleton structures, researchers can more accurately understand the distribution of compounds with various skeleton structures in the target technical literature.

[0014] A further solution is that after displaying the technical literature information corresponding to each high-frequency skeleton structure, the following is further performed: extracting keywords from the technical literature information corresponding to each high-frequency skeleton structure, and classifying the technical literature corresponding to the same high-frequency skeleton structure.

[0015] It can be seen that for a high-frequency skeleton structure, by classifying the corresponding technical literature, users can understand the technical distribution of the corresponding technical literature of the high-frequency skeleton structure, so as to further understand the historical development trend of the research results on this high-frequency skeleton structure.

[0016] A preferred solution is to classify the technical documents corresponding to the same high-frequency skeleton structure, including: dividing the technical documents corresponding to the same high-frequency skeleton structure into promotion technology, inhibition technology, and synthesis technology.

[0017] In this way, by classifying multiple different technical fields, it will be convenient for researchers to further understand the development status of promotion technology, inhibition technology, and synthesis technology under the obtained high-frequency skeleton structure.

[0018] Furthermore, after the technical documents corresponding to the same high-frequency skeleton structure are classified, the technical document information under each classification is displayed.

[0019] In this way, researchers can have a clearer understanding of the literature on various classification information of high-frequency skeleton structures.

[0020] A further solution is that displaying the technical document information under each category includes: a display format of the technical document information under one category is different from a display format of the technical document information under another category.

[0021] In this way, researchers can intuitively understand the technical literature information of different categories, which is convenient for subsequent research work.

[0022] To achieve the second objective mentioned above, the computer device provided by the present invention includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, each step of the above technical document data analysis method is implemented.

[0023] To achieve the third objective mentioned above, the present invention provides a computer readable storage medium storing a computer program, and when the computer program is executed by a processor, each step of the above technical document data analysis method is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flow chart of an embodiment of the technical document data analysis method of the present invention.

[0025] Figure 2 It is the initial skeleton structure diagram of the compound identified in the embodiment of the technical literature data analysis method of the present invention.

[0026] Figure 3 It is a schematic diagram of the skeleton structure after clustering according to the embodiment of the technical literature data analysis method of the present invention.

[0027] The present invention is further described below in conjunction with the accompanying drawings and embodiments. DETAILED DESCRIPTION

[0028] The technical document data analysis method of the present invention is applied to an electronic device with a display screen, for example, the electronic device is a smart terminal device, which can run third-party applications, or access the Internet through a browser, and can access a specified web page to obtain technical document information. Preferably, the above-mentioned electronic device is provided with a processor and a memory, and a computer program is stored in the memory, and the technical document data analysis method is implemented by the computer program.

[0029] Technical literature data analysis method embodiment:

[0030] The technical literature data analysis method of this embodiment is mainly aimed at the analysis of technical literature in the field of chemistry, especially the analysis of technical literature containing the molecular structure of compounds. The molecular structure of the compound is analyzed to obtain the skeleton structure of the compound, and the obtained multiple skeleton structures are analyzed, especially the technical literature information is counted to obtain statistical data, so as to facilitate researchers to understand the technological development status and historical development trends in a certain technical field.

[0031] See also Figure 1 , this embodiment first executes step S1 to obtain the target keyword. For example, after the user opens the patent search page, multiple search fields are displayed on the page, and the user enters keywords in the corresponding search field according to the research matter. After the user enters the keyword, the background server can obtain the corresponding technical document from the technical document database, that is, execute step S2, and the obtained technical document is the target technical document. For example, according to the search field where the keyword is located, search for keywords from the corresponding part of the technical document, such as from the abstract, claims, instructions and other parts of the patent document to see if they contain the corresponding keywords. If the corresponding part of the technical document contains the keyword entered by the user, the technical document is determined as the target technical document and added to the target technical document list.

[0032] Next, step S3 is executed to obtain the molecular structure information of the compound in the target technical document. Specifically, the molecular structure information can be a molecular structure diagram of a polymer compound. In the present embodiment, the molecular structure diagram of the compound recorded in the target technical document is identified by performing image recognition on the target technical document. Preferably, for patent documents, the molecular structure diagram of the compound recorded in the target technical document is not limited to being scanned from the specification drawings of the patent document, but also includes being obtained from the contents recorded in the claims, specifications and abstracts of the patent document. Specifically, known image recognition techniques are applied, such as convolutional neural networks, to intelligently identify the claims, specifications and abstracts, and specification drawings of the patent document, and identify the molecular structure diagram of the compound recorded in the patent document. Usually, the number of retrieved target technical documents is large, and a large number of target technical documents record a large number of molecular structure diagrams of compounds. Therefore, step S3 can obtain the molecular structure information of multiple compounds. Furthermore, if the same target technical document records the molecular structure information of multiple compounds, it is necessary to obtain the molecular structure information of each compound separately. If the molecular structure information of the same compound appears multiple times in the same target technical document, for example, the molecular structure information of the same compound is recorded in the claims and the specification respectively, then step S3 only records the molecular structure information of the compound once to avoid sufficient calculation of the same compound recorded in the same technical document.

[0033] Next, step S4 is executed to perform skeleton structure recognition on the molecular structure information of the identified compound, thereby identifying the initial skeleton structure of each compound. The skeleton structure of this embodiment includes the carbon chain structure of the compound, and also includes heteroatoms in the compound, such as specific heteroatoms such as phosphorus, nitrogen, and chlorine. Generally, the molecular structure diagram of the compound usually includes the connection structure between carbon atoms. By analyzing the connection structure between carbon atoms and analyzing the specific heteroatoms connected to the carbon atoms, the initial skeleton structure of each compound can be obtained. Figure 2 (a), (b) and (c) are the initial skeleton structures of three different polymer compounds.

[0034] In this embodiment, an initial skeleton structure can be identified for each compound's molecular structure information, so the number of initial skeleton structures identified in step S4 is equal to the number of molecular structures of the compound obtained in step S3. Since the number of compounds identified in step S3 is usually large, the number of initial skeleton structures of the compound identified in step S4 is also large. If all the identified initial skeleton structures are displayed to the user, it will be difficult for the user to identify which compounds appear more frequently, which is not conducive to the user's analysis.

[0035] Then, execute step S5 to perform cluster analysis on the multiple initial skeleton structures obtained. This embodiment uses a known clustering algorithm to cluster the multiple initial skeleton structures. For example, multiple skeleton structure types are pre-set and each initial skeleton structure is clustered into a pre-set skeleton structure type, thereby reducing the number of skeleton structures obtained. Figure 3 This is a schematic diagram of a skeleton structure obtained after clustering. By clustering the initial skeleton structure, it is possible to identify skeleton structures of the same type in multiple initial skeleton structures, which is beneficial to the subsequent research work of researchers.

[0036] Preferably, the number of skeleton structure types set should be multiple, that is, after clustering calculation, the obtained clustered skeleton structures are more than two, so that researchers can understand which skeleton structures are contained in the target technical literature retrieved by preset keywords, and through subsequent statistical analysis of the data of various skeleton structures, the distribution of various skeleton structures in the target technical literature can be analyzed.

[0037] After cluster analysis of the initial skeleton structure, execute step S6 to count the number of times each skeleton structure appears in the target technical document among the multiple skeleton structures obtained in step S5, and sort them according to the number of times each skeleton structure appears to obtain multiple high-frequency skeleton structures. One way is to use a preset percentage of the number of skeleton structures as a high-frequency skeleton structure. For example, the total number of skeleton structures identified in step S5 is 50, and 20% of them are used as high-frequency skeleton structures, that is, the number of high-frequency skeleton structures is 10. At this time, the top 10 skeleton structures with the largest number of appearances are used as high-frequency skeleton structures. Another way is to use a certain number as a criterion for judging a high-frequency skeleton structure. For example, if the number of skeleton structures appearing in the target technical document is more than 50 times, the skeleton structure is judged to be a high-frequency skeleton structure.

[0038] Preferably, when counting the number of occurrences of each skeleton structure in the target technical document, if multiple initial skeleton structures recorded in the same technical document are clustered and identified as the same skeleton structure, the number of occurrences of the same skeleton structure in the target technical document is calculated according to the number of initial skeleton structures, rather than merging the multiple initial skeleton structures, thereby ensuring the statistical accuracy of the number of occurrences of the skeleton structure.

[0039] Then, step S7 is executed to display the technical document information corresponding to each high-frequency skeleton structure. For example, in the search result list, the skeleton structure diagram of each high-frequency skeleton structure is displayed, and the number of target technical documents corresponding to the high-frequency skeleton structure and the number of occurrences in all target technical documents are displayed. Preferably, the summary information of the target technical document corresponding to the high-frequency skeleton structure can also be displayed. If the user clicks on a target technical document, the detailed content of the target technical document can be displayed.

[0040] Furthermore, in order to facilitate the researchers to analyze multiple target technical documents corresponding to a certain high-frequency skeleton structure, step S8 is also performed to extract keywords from the technical document information corresponding to each high-frequency skeleton structure, and classify the technical documents corresponding to the same high-frequency skeleton structure. For example, the technical documents corresponding to the same high-frequency skeleton structure can be divided into promotion technology, inhibition technology, and synthesis technology. Specifically, by identifying and analyzing the target technical document, the target technical document is divided into different technology types according to the content of the target technical document, thereby marking each target technical document.

[0041] Therefore, when displaying the target technical document information, the technical document information of each category under the high-frequency skeleton structure can be displayed. For example, the display format of the technical document information under one category is different from the display format of the technical document information under another category, that is, different display formats are used for displaying target technical documents of different categories, such as setting different background patterns, font colors, etc., so that users can intuitively understand the target technical documents of different categories and obtain the required target technical documents more accurately.

[0042] It can be seen that the present invention obtains analytical information, such as high-frequency skeleton structures, by analyzing the molecular structures of the compounds in each target technical document and obtaining the skeleton structures of the compounds. Researchers can easily obtain several skeleton structures that appear most frequently in this technical field, providing good basic information for subsequent research.

[0043] Computer device embodiment:

[0044] The computer device of this embodiment can be an electronic device with human-computer interaction function, such as an intelligent terminal device. The electronic device has a processor, a memory, and a computer program stored in the memory and executable on the processor, such as an information processing program for implementing the above-mentioned information processing method. When the processor executes the computer program, each step of the above-mentioned technical literature data analysis method is implemented.

[0045] For example, a computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to complete each module of the present invention. One or more modules may be a series of computer program instruction segments capable of completing a specific function, and the instruction segments are used to describe the execution process of the computer program in a terminal device.

[0046] It should be noted that the terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram of the present invention is only an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the figure, or may combine certain components, or different components. For example, the terminal device may also include an input / output device, a network access device, a bus, etc.

[0047] The processor referred to in the present invention may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0048] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0049] Computer readable storage medium:

[0050] If the computer program stored in the computer device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement each step of the above-mentioned technical document data analysis method.

[0051] Among them, the computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form, etc. Computer readable media may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer readable media do not include electric carrier signals and telecommunication signals.

[0052] Finally, it should be emphasized that the present invention is not limited to the above-mentioned embodiments. For example, changes in the specific identification method of the molecular structure information of the compounds in the target technical literature through neural networks and changes in the specific clustering algorithm of the initial skeleton structure should also be included in the scope of protection of the claims of the present invention.

Claims

1. A method for analyzing technical literature data, comprising: Obtain target keywords, and obtain target technical documents according to the target keywords; Features: Using image recognition technology to obtain molecular structure information of compounds in the target technical document, the number of compounds obtained is two or more, if the molecular structure information of the same compound appears multiple times in the same target technical document, the molecular structure information of the compound is recorded only once; Identifying the skeleton structure of the compound according to the molecular structure information of the compound, and obtaining the skeleton structure of each of the compounds; When identifying the skeleton structure of the compound, the connection structure between the carbon atoms of the compound is analyzed, and the specific heteroatoms connected to the carbon atoms are analyzed to obtain the initial skeleton structure of each of the compounds, the initial skeleton structure of the compound is identified, and the identified multiple initial skeleton structures are clustered to obtain multiple clustered skeleton structures, and the number of the identified initial skeleton structures is equal to the number of the obtained molecular structures of the compound; The number of occurrences of each skeleton structure is counted, several skeleton structures with the largest number of occurrences are obtained as high-frequency skeleton structures, and the technical literature information corresponding to each of the high-frequency skeleton structures is displayed.

2. The technical document data analysis method according to claim 1, characterized in that: Displaying the technical literature information corresponding to each of the high-frequency skeleton structures includes: displaying the number of technical literature corresponding to each of the high-frequency skeleton structures and the summary information of each of the technical literature corresponding to each of the high-frequency skeleton structures.

3. The technical document data analysis method according to claim 1 or 2, characterized in that: After displaying the technical literature information corresponding to each high-frequency skeleton structure, the following is further performed: Keywords are extracted from the technical literature information corresponding to each of the high-frequency skeleton structures, and the technical literature corresponding to the same high-frequency skeleton structure is classified.

4. The method for analyzing technical literature data according to claim 3, characterized in that: Classifying the technical literature corresponding to the same high-frequency skeleton structure includes: dividing the technical literature corresponding to the same high-frequency skeleton structure into promotion technology, inhibition technology, and synthesis technology.

5. The technical document data analysis method according to claim 3, characterized in that: Also includes: After the technical documents corresponding to the same high-frequency skeleton structure are classified, the technical document information under each classification is displayed.

6. The method for analyzing technical literature data according to claim 5, characterized in that: Displaying the technical document information under each category includes: the display format of the technical document information under one category is different from the display format of the technical document information under another category.

7. A computer device, characterized in that It comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, each step of the technical document data analysis method as described in any one of claims 1 to 6 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the technical document data analysis method according to any one of claims 1 to 6 is implemented.

Images