Method for Determining the Relevance of Knowledge Documents Applied to Mining Scientific Research Knowledge Service Platform

Abstract

This disclosure relates to a method for determining the correlation degree of knowledge documents applied to a mining scientific research knowledge service platform. The method includes: acquiring structured attribute information of knowledge documents in a mining scientific research knowledge base, as well as user click and download records for these documents; for any two knowledge documents, calculating a first correlation degree between them based on the structured attribute information, and calculating a second correlation degree based on the click and download records; and then fusing the first and second correlation degrees using a fusion parameter to obtain the correlation probability between the two knowledge documents. This solution can more comprehensively and accurately reflect the actual correlation degree between mining scientific research knowledge documents.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a method for determining the correlation degree of knowledge documents applied to a mining scientific research knowledge service platform. Background Technology

[0002] In related technologies, with the continuous expansion of the internal knowledge bases of enterprises and research institutions, the number of stored knowledge documents such as technical reports, patents, and papers has surged, and much of this data is unstructured, making it difficult to establish effective semantic relationships between documents. Traditional methods typically perform similarity analysis based on content features such as document titles, abstracts, and keywords, or use attributes such as author, publication date, and source information contained within the documents themselves for matching to identify potential connections between documents. However, these methods mainly rely on the static features of documents and are insufficient to fully explore the deep-seated relationships between them. Summary of the Invention

[0003] To overcome the problems existing in related technologies, this disclosure provides a method for determining the correlation degree of knowledge documents applied to a mining scientific research knowledge service platform.

[0004] According to a first aspect of the present disclosure, a method for determining the relevance of knowledge documents applied to a mining scientific research knowledge service platform is provided, comprising:

[0005] Obtain the structured attribute information of knowledge documents in the mine scientific research knowledge base; Obtain the user's interaction log with the knowledge document; the interaction log includes the user's click records and download records of the knowledge document; For any two knowledge documents, a first degree of correlation between the two knowledge documents is calculated based on the structured attribute information, and a second degree of correlation between the two knowledge documents is calculated based on the click records and download records; The first correlation degree and the second correlation degree are fused using fusion parameters to obtain the correlation probability between the two knowledge documents.

[0006] According to a second aspect of the present disclosure, a knowledge document correlation prediction device applied to a mining scientific research knowledge service platform is provided, comprising: The first acquisition unit is used to acquire the structured attribute information of knowledge documents in the mining scientific research knowledge base; The second acquisition unit is used to acquire the user's interaction log with the knowledge document; the interaction log includes the user's click records and download records of the knowledge document; The calculation unit is used to calculate a first degree of correlation between two knowledge documents based on the structured attribute information, and to calculate a second degree of correlation between the two knowledge documents based on the click records and download records. The fusion unit is used to fuse the first correlation degree and the second correlation degree using fusion parameters to obtain the correlation degree probability between the two knowledge documents.

[0007] According to a third aspect of the present disclosure, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described in any one of the first aspects.

[0008] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of the first aspects.

[0009] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method as described in any one of the first aspects.

[0010] The technical solution provided by the embodiments of this disclosure can include the following beneficial effects: by acquiring the structured attribute information of knowledge documents in the mining scientific research knowledge base, as well as the user's click records and download records of knowledge documents, for any two knowledge documents, a first degree of correlation between the two knowledge documents is calculated based on the structured attribute information, and a second degree of correlation between the two knowledge documents is calculated based on the click records and download records. Then, the first degree of correlation and the second degree of correlation are fused using fusion parameters to obtain the correlation probability between the two knowledge documents. Its beneficial effects are: on the one hand, calculating the first degree of correlation through structured attribute information can explore the inherent connection between documents from the dimension of the document's own features; on the other hand, calculating the second degree of correlation through click records and download records can capture the potential connection between documents from the dimension of user behavior. The correlation probability obtained by fusing the two integrates the multi-dimensional information of static attributes and dynamic behavior, thereby more comprehensively and accurately reflecting the actual degree of correlation between mining scientific research knowledge documents, and providing a reliable correlation data foundation for subsequent knowledge graph construction, intelligent recommendation, or scientific research value assessment.

[0011] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0012] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0013] Figure 1This is a flowchart illustrating a method for determining the correlation degree of knowledge documents applied to a mining scientific research knowledge service platform, according to an exemplary embodiment.

[0014] Figure 2 This is a block diagram illustrating a knowledge document correlation prediction device applied to a mining scientific research knowledge service platform, according to an exemplary embodiment.

[0015] Figure 3 This is a block diagram illustrating an apparatus for determining the correlation degree of knowledge documents applied to a mining scientific research knowledge service platform, according to an exemplary embodiment. Detailed Implementation

[0016] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0017] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the present disclosure. The singular forms “a” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0018] It should be understood that although the terms first, second, third, etc., may be used to describe various information in embodiments of this disclosure, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of embodiments of this disclosure, and similarly, second information may also be referred to as first information. Depending on the context, the words “if” and “suppose” as used herein may be interpreted as “when”, “when”, or “in response to a determination”.

[0019] Furthermore, various forms of processes shown in the embodiments of this disclosure can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and no limitation is imposed herein.

[0020] It should be noted that the collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0021] Figure 1 This is a flowchart illustrating a method for determining the relevance of knowledge documents applied to a mining scientific research knowledge service platform, according to an exemplary embodiment. Figure 1 As shown, it should be noted that the knowledge document correlation determination method of this disclosure embodiment applied to the mining scientific research knowledge service platform is applied to the knowledge document correlation prediction device applied to the mining scientific research knowledge service platform. For example... Figure 1 As shown, the method may include the following steps: Step 101: Obtain the structured attribute information of knowledge documents in the mining scientific research knowledge base.

[0022] In some embodiments of this disclosure, the mine research knowledge base stores a large number of knowledge documents, including but not limited to technical reports, patents, papers, and software copyrights. These knowledge documents may initially exist in unstructured forms, such as PDF files and Word documents.

[0023] As an example, these knowledge documents can be preprocessed, such as by removing redundant text and erroneous characters, and extracting structured attribute information from them.

[0024] Specifically, the extractable attribute information can include author, file name, creation time, source, etc. This information is stored as structured data of the knowledge document to form the document's attribute set.

[0025] Understandably, this structured attribute information provides the foundational data for subsequent calculations of the relationships between documents. By extracting structured attribute information, unstructured documents can be transformed into structured data representations, facilitating computer processing and analysis.

[0026] Step 102: Obtain the user's interaction log with the knowledge document.

[0027] The interaction log includes records of user clicks and downloads of knowledge documents.

[0028] As an example, knowledge service platforms record user interactions with knowledge documents, creating interaction logs.

[0029] In this embodiment of the disclosure, these interaction logs are obtained, including at least user click records and download records for knowledge documents. Click records reflect user attention to or browsing behavior on the document, while download records reflect a deeper user need for the document, indicating that the document has high value to the user.

[0030] It's understandable that user interactions imply potential connections between documents. For example, if the same user clicks on or downloads two documents consecutively within a short period, it might mean that these two documents are related in content or topic. By obtaining click and download records, connections between documents can be uncovered from the perspective of user behavior.

[0031] Step 103: For any two knowledge documents, calculate the first degree of association between the two knowledge documents based on the structured attribute information, and calculate the second degree of association between the two knowledge documents based on the click records and download records.

[0032] In this embodiment, for any two knowledge documents a and b, a first correlation degree is calculated based on structured attribute information. This involves comparing the similarity of the documents across various attribute dimensions, considering the importance of different attributes and a preset similarity threshold, to quantify the intrinsic connection between the two documents from the perspective of their own characteristics. A second correlation degree is calculated based on click and download records. This involves statistically analyzing users' continuous clicks, continuous downloads, and click-download hybrid behaviors within different time windows, considering the importance of different behavior types and the weight of different time granularities, to uncover the potential connection between the two documents from the user behavior perspective. The parallel calculation of these two dimensions provides a foundation for subsequent fusion to obtain the final correlation probability.

[0033] In some embodiments of this disclosure, step 103 may specifically include the following sub-steps: Step a1: For each attribute n, calculate the cosine similarity (attribute[a,n], attribute[b,n], n) between two knowledge documents a and b on that attribute.

[0034] In this embodiment, for any two knowledge documents a and b, it is necessary to compare their similarity across all attributes. Cosine similarity is a commonly used vector similarity metric, which measures the similarity between two vectors by calculating the cosine of the angle between them. The value range is [-1, 1], where 1 indicates identical documents, 0 indicates orthogonal (irrelevant), and -1 indicates completely opposite documents. For each attribute n, the values ​​of documents a and b on that attribute are converted into vector form, and the cosine similarity between the two knowledge documents is calculated. In this way, the similarity scores of documents a and b across each attribute dimension can be obtained.

[0035] Step a2: Obtain the importance weights Q(n) of each attribute, and ∑Q(n)=1.

[0036] In some embodiments of this disclosure, different attributes may have varying degrees of importance in determining the correlation between documents. For example, in the field of mining research, the author attribute may reflect the professional relevance of a document more effectively than the filename attribute. Therefore, based on statistical data from actual usage of the knowledge service platform, this disclosure assigns an importance weight Q(n) to each attribute n, and the sum of the weights of all attributes is 1. The larger the value of the weight Q(n), the greater the importance of that attribute in determining the correlation between documents. By setting weights, the differentiated contributions of different attributes in the correlation calculation can be reflected.

[0037] Step a3, calculate the first correlation degree similarity_compare(a,b) using the following formula: Where β is a preset similarity threshold.

[0038] In some embodiments of this disclosure, a threshold β is set to ensure that only attributes with a certain meaningful association are included in the calculation. When the cosine similarity of an attribute is greater than β, the similarity of that attribute is included in the calculation of the first association degree. The numerator in the calculation formula is a weighted sum of the cosine similarities of all valid attributes (i.e., attributes with similarity greater than β), and the denominator is the sum of all weights (since ∑Q(n)=1, the denominator is actually 1, but retaining the denominator form is more general). In this way, the first association degree similarity_compare(a,b) integrates the similarity information of multiple attributes and considers the importance and validity threshold of the attributes, thereby more accurately reflecting the degree of association between documents a and b at the static attribute level.

[0039] Understandably, the first correlation degree mines the inherent connections between documents from the dimension of the document's own features, providing a foundation for subsequent fusion.

[0040] Step b1: Set multiple time windows ti, each time window corresponds to a time period weight S(i), and ∑S(i)=1.

[0041] In this embodiment, the timing of user interaction is crucial for determining document association. For example, a user clicking two documents consecutively within a very short timeframe indicates a much stronger association than clicking them separately over a longer period. Therefore, this disclosure sets multiple time windows ti, such as within 1 second, 1 minute, 1 day, or 1 month. Each time window corresponds to a time period weight S(i), and the sum of all time period weights is 1. The principle for setting the time period weight is: the smaller the time window, the shorter the time the user's behavior occurs, and the stronger the association; therefore, the larger the time period weight value. The time period weight reflects the differences in the strength of behavioral association at different time granularities.

[0042] Step b2, within each time window ti: The function `scan(a,b,ti)` counts the number of times the same user clicks on documents a and b consecutively, and `scan(ti)` counts the total number of times the same user clicks on any two knowledge documents consecutively. Count the number of times the same user downloads documents a and b consecutively (download(a,b,ti), and the total number of times the same user downloads any two knowledge documents consecutively (download(ti)). Count the number of times the same user clicks on one document and downloads another document consecutively, mix(a,b,ti), and the total number of times the same user clicks on and downloads any two knowledge documents consecutively, mix(ti).

[0043] In some embodiments of this disclosure, for each time window ti, three types of user behavior are statistically analyzed: Click-click behavior: The number of times the same user clicks documents a and b consecutively is denoted as scan(a,b,ti); the total number of times the same user clicks any two knowledge documents consecutively (i.e., the total number of times all document pairs are clicked consecutively by the same user) is denoted as scan(ti).

[0044] Download - Download behavior: The number of times the same user downloads documents a and b consecutively is denoted as download(a,b,ti); the total number of times the same user downloads any two knowledge documents consecutively is denoted as download(ti).

[0045] Click-download mixed behavior: The number of times the same user clicks on one document and downloads another document consecutively (in any order) is denoted as mix(a,b,ti); the total number of times the same user clicks on and downloads any two knowledge documents consecutively (i.e., the total number of times all document pairs are clicked and downloaded consecutively by the same user) is denoted as mix(ti).

[0046] Understandably, these statistics provide the basis for subsequent calculations of conditional probabilities. scan(a,b,ti) / scan(ti) reflects the probability that documents a and b are clicked consecutively in a click action; similarly, download(a,b,ti) / download(ti) reflects the probability that documents a and b are downloaded consecutively in a download action; mix(a,b,ti) / mix(ti) reflects the probability that documents a and b are clicked and downloaded consecutively in a mixed action.

[0047] Step b3, calculate the click-download correlation of two knowledge documents a and b using the following formula: Where R1 is the weight corresponding to scan(ti), R2 is the weight corresponding to download(ti), R3 is the weight corresponding to mix(ti), and R1+R2+R3=1.

[0048] In some embodiments of this disclosure, different types of user behavior may have varying degrees of importance in determining document association. For example, downloading behavior generally reflects a user's approval of a document more than clicking behavior, so its weight can be set higher. This disclosure sets behavior type weights R1, R2, and R3, corresponding to click-click, download-download, and click-download behaviors, respectively, and the sum of the three is 1. For each time window ti, the behavior association component within that window is first calculated: the conditional probability of each of the three behaviors is multiplied by its corresponding behavior weight, and then divided by the sum of the behavior weights (since R1+R2+R3=1, the denominator is actually 1, but retaining the denominator form is more general). Then, the association components of each time window are weighted and averaged according to the time period weight S(i) to obtain the final second association degree mix(a,b).

[0049] Understandably, the second correlation degree captures the potential correlation between documents from the perspective of user behavior. Through the design of multi-level weighting (behavior type weight + time period weight), it can accurately reflect the correlation strength under different behavior patterns and time granularities.

[0050] Through steps a1-a3 and b1-b3, this disclosure obtains the first correlation degree similarity_compare(a,b) and the second correlation degree mix(a,b), respectively. The first correlation degree is based on the static attributes of the documents, while the second correlation degree is based on the dynamic behavior of the users. The two describe the degree of correlation between documents from different dimensions.

[0051] Step 104: Use the fusion parameters to fuse the first relevance and the second relevance to obtain the relevance probability between the two knowledge documents.

[0052] In some embodiments of this disclosure, as an example, step 104 may specifically include the following sub-steps: Step c1: Calculate the probability of association between two knowledge documents, P_pre(a,b), using the following formula:

[0053] in, These are the preset fusion parameters, and similarity_compare(a,b) represents the first degree of correlation, and mix(a,b) represents the second degree of correlation.

[0054] In some embodiments of this disclosure, the fusion parameter α is used to balance the contributions of the first and second relevance scores to the final relevance probability. When α is close to 1, the final relevance score focuses more on the static attributes of the document; when α is close to 0, it focuses more on the dynamic behavior of the user; when α = 0.5, the contributions of the two are equal. The specific value of α can be determined through statistical or machine learning methods based on the actual operation of the knowledge service platform.

[0055] It should be noted that the first correlation coefficient, similarity_compare(a,b), has a value range of [-1,1], while the second correlation coefficient, mix(a,b), has a value range of [0,1]. Before fusion, the first correlation coefficient can be normalized to map it to the [0,1] interval to ensure that the two are fused linearly under the same dimensions. For example, it can be mapped to [0,1] using the expression (similarity_compare+1) / 2.

[0056] In step 104, this disclosure organically integrates the static attribute features of documents and the dynamic behavioral features of users to obtain the final probability of correlation between two knowledge documents. This probability value integrates multi-dimensional information and can more comprehensively and accurately reflect the actual degree of correlation between mining scientific research knowledge documents.

[0057] As an example, this disclosure can further process the fused correlation probability, such as setting a threshold to determine whether to establish a citation relationship between documents, or using it as basic data for subsequent applications such as knowledge graph construction, intelligent recommendation, and scientific research value assessment. It is understood that the correlation probability obtained through the above methods has high reliability and practicality.

[0058] In some embodiments of this disclosure, as an example, the time window includes multiple windows with different time granularities, and the time period weight S(i) is a normalized weight, wherein the time granularity corresponding to the same time window is inversely proportional to the time period weight value. That is, the smaller the time window (the finer the time granularity), the larger the time period weight value; the larger the time window (the coarser the time granularity), the smaller the time period weight value. This setting conforms to intuitive understanding: when a user operates on two documents consecutively within a very short period of time, their correlation is more significant, and therefore they should be given a higher weight.

[0059] The method for determining the correlation degree of knowledge documents applied to a mining scientific research knowledge service platform, as proposed in this embodiment, obtains the structured attribute information of knowledge documents in the mining scientific research knowledge base, as well as user click and download records of knowledge documents. For any two knowledge documents, a first correlation degree is calculated based on the structured attribute information, and a second correlation degree is calculated based on the click and download records. Then, the first and second correlation degrees are fused using fusion parameters to obtain the correlation probability between the two knowledge documents. Its beneficial effects are: on the one hand, calculating the first correlation degree through structured attribute information can explore the inherent connection between documents from the dimension of document characteristics; on the other hand, calculating the second correlation degree through click and download records can capture the potential connection between documents from the dimension of user behavior. The correlation probability obtained by fusing the two integrates multi-dimensional information of static attributes and dynamic behavior, thereby more comprehensively and accurately reflecting the actual correlation degree between mining scientific research knowledge documents, providing a reliable correlation data foundation for subsequent knowledge graph construction, intelligent recommendation, or scientific research value assessment.

[0060] Figure 2 This is a block diagram illustrating a knowledge document relevance prediction device applied to a mining scientific research knowledge service platform, according to an exemplary embodiment. (Refer to...) Figure 2 The device includes a first acquisition unit 201, a second acquisition unit 202, a calculation unit 203, and a fusion unit 204.

[0061] The first acquisition unit 201 is used to acquire the structured attribute information of knowledge documents in the mining scientific research knowledge base; The second acquisition unit 202 is used to acquire the user's interaction log with the knowledge document; the interaction log includes the user's click records and download records of the knowledge document; The calculation unit 203 is used to calculate a first degree of correlation between two knowledge documents based on the structured attribute information, and to calculate a second degree of correlation between the two knowledge documents based on the click records and download records. The fusion unit 204 is used to fuse the first correlation degree and the second correlation degree using fusion parameters to obtain the correlation degree probability between the two knowledge documents.

[0062] In some embodiments of this application, the computing unit 203 may specifically be used for: For each attribute n, calculate the cosine similarity (attribute[a,n], attribute[b,n], n) between two knowledge documents a and b on that attribute; Obtain the importance weights Q(n) for each attribute, and ; The first degree of similarity, similarity_compare(a,b), is calculated using the following formula:

[0063] Where β is a preset similarity threshold.

[0064] In some embodiments of this application, the computing unit 203 may specifically be used for: Multiple time windows ti are defined, each time window corresponds to a time period weight S(i), and ; Within each time window ti: The function `scan(a,b,ti)` counts the number of times the same user clicks on documents a and b consecutively, and `scan(ti)` counts the total number of times the same user clicks on any two knowledge documents consecutively. Count the number of times the same user downloads documents a and b consecutively (download(a,b,ti), and the total number of times the same user downloads any two knowledge documents consecutively (download(ti)). Count the number of times the same user clicks on one document and downloads another document consecutively, mix(a,b,ti), and the total number of times the same user clicks on and downloads any two knowledge documents consecutively, mix(ti). The click-download correlation of two knowledge documents a and b is calculated using the following formula: mix(a,b)

[0065] Where R1 is the weight corresponding to scan(ti), R2 is the weight corresponding to download(ti), R3 is the weight corresponding to mix(ti), and R1+R2+R3=1.

[0066] In some embodiments of this application, the fusion unit 204 may specifically be used for: The following formula is used to calculate the probability of association between two knowledge documents. :

[0067] in, These are the preset fusion parameters. similarity_compare(a,b) represents the first degree of correlation, and mix(a,b) represents the second degree of correlation.

[0068] In some embodiments of this application, the time window includes multiple windows with different time granularities, and the time period weight S(i) is a normalized weight, wherein the time granularity corresponding to the same time window is inversely proportional to the value of the time period weight.

[0069] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0070] The knowledge document correlation prediction device for a mining scientific research knowledge service platform proposed in this embodiment obtains structured attribute information of knowledge documents in the mining scientific research knowledge base, as well as user click and download records of knowledge documents. For any two knowledge documents, it calculates a first correlation degree between the two knowledge documents based on the structured attribute information, and calculates a second correlation degree between the two knowledge documents based on the click and download records. Then, it uses fusion parameters to fuse the first and second correlation degrees to obtain the correlation probability between the two knowledge documents. Its beneficial effects are: on the one hand, calculating the first correlation degree through structured attribute information can explore the inherent connection between documents from the dimension of document features; on the other hand, calculating the second correlation degree through click and download records can capture the potential connection between documents from the dimension of user behavior. The correlation probability obtained by fusing the two integrates multi-dimensional information of static attributes and dynamic behavior, thereby more comprehensively and accurately reflecting the actual correlation degree between mining scientific research knowledge documents, and providing a reliable correlation data foundation for subsequent knowledge graph construction, intelligent recommendation, or scientific research value assessment.

[0071] Figure 3 This is a block diagram illustrating an apparatus for determining the correlation degree of knowledge documents applied to a mining scientific research knowledge service platform, according to an exemplary embodiment. For example, apparatus 300 may be an electronic device, such as a mobile phone, computer, digital broadcasting terminal, messaging device, tablet device, personal digital assistant, etc.

[0072] Reference Figure 3 The device 300 may include one or more of the following components: processing component 302, memory 304, power component 306, multimedia component 308, audio component 310, input / output (I / O) interface 312, sensor component 314, and communication component 316.

[0073] Processing component 302 typically controls the overall operation of device 300, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 302 may include one or more processors 320 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 302 may include one or more modules to facilitate interaction between processing component 302 and other components. For example, processing component 302 may include a multimedia module to facilitate interaction between multimedia component 308 and processing component 302.

[0074] Memory 304 is configured to store various types of data to support the operation of device 300. Examples of such data include instructions for any application or method operating on device 300, contact data, phonebook data, messages, pictures, videos, etc. Memory 304 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 storage, flash memory, magnetic disk, or optical disk.

[0075] The power supply component 306 provides power to the various components of the device 300. The power supply component 306 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to the device 300.

[0076] Multimedia component 308 includes a screen that provides an output interface between the device 300 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 may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 308 includes a front-facing camera and / or a rear-facing camera. When the device 300 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0077] Audio component 310 is configured to output and / or input audio signals. For example, audio component 310 includes a microphone (MIC) configured to receive external audio signals when device 300 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 304 or transmitted via communication component 316. In some embodiments, audio component 310 also includes a speaker for outputting audio signals.

[0078] I / O interface 312 provides an interface between processing component 302 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, start buttons, and lock buttons.

[0079] Sensor assembly 314 includes one or more sensors for providing status assessments of various aspects of device 300. For example, sensor assembly 314 may detect the on / off state of device 300, the relative positioning of components such as the display and keypad of device 300, changes in the position of device 300 or a component of device 300, the presence or absence of user contact with device 300, the orientation or acceleration / deceleration of device 300, and temperature changes of device 300. Sensor assembly 314 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 314 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 314 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0080] Communication component 316 is configured to facilitate wired or wireless communication between device 300 and other devices. Device 300 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 316 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 316 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0081] In an exemplary embodiment, the apparatus 300 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 methods described above.

[0082] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 304 including instructions, which can be executed by a processor 320 of the device 300 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0083] In an exemplary embodiment, a computer program product is also provided, including a computer program that implements the above-described method when executed by the processor 320 of the device 300.

[0084] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0085] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for determining the relevance of knowledge documents applied to a mining scientific research knowledge service platform, characterized in that, include: Obtain the structured attribute information of knowledge documents in the mine scientific research knowledge base; Obtain the user's interaction log with the knowledge document; the interaction log includes the user's click records and download records of the knowledge document; For any two knowledge documents, a first degree of correlation between the two knowledge documents is calculated based on the structured attribute information, and a second degree of correlation between the two knowledge documents is calculated based on the click records and download records; The first correlation degree and the second correlation degree are fused using fusion parameters to obtain the correlation probability between the two knowledge documents.

2. The method for determining the relevance of knowledge documents applied to a mining scientific research knowledge service platform according to claim 1, characterized in that, The calculation of the first correlation degree between two knowledge documents based on the structured attribute information includes: For each attribute n, calculate the cosine similarity (attribute[a,n], attribute[b,n], n) between two knowledge documents a and b on that attribute; Obtain the importance weights Q(n) for each attribute, and ; The first degree of similarity, similarity_compare(a,b), is calculated using the following formula: Where β is a preset similarity threshold.

3. The method for determining the relevance of knowledge documents applied to a mining scientific research knowledge service platform according to claim 1, characterized in that, The calculation of the second correlation degree between the two knowledge documents based on the click records and download records includes: Multiple time windows ti are defined, each time window corresponds to a time period weight S(i), and ; Within each time window ti: The function `scan(a,b,ti)` counts the number of times the same user clicks on documents a and b consecutively, and `scan(ti)` counts the total number of times the same user clicks on any two knowledge documents consecutively. Count the number of times the same user downloads documents a and b consecutively (download(a,b,ti), and the total number of times the same user downloads any two knowledge documents consecutively (download(ti)). Count the number of times the same user clicks on one document and downloads another document consecutively, mix(a,b,ti), and the total number of times the same user clicks on and downloads any two knowledge documents consecutively, mix(ti). The click-download correlation of two knowledge documents a and b is calculated using the following formula: mix(a,b) Where R1 is the weight corresponding to scan(ti), R2 is the weight corresponding to download(ti), R3 is the weight corresponding to mix(ti), and R1+R2+R3=1.

4. The method for determining the relevance of knowledge documents applied to a mining scientific research knowledge service platform according to claim 1, characterized in that, The process of fusing the first correlation degree and the second correlation degree using fusion parameters to obtain the correlation degree probability between the two knowledge documents includes: The following formula is used to calculate the probability of association between two knowledge documents. : in, These are the preset fusion parameters. similarity_compare(a,b) represents the first degree of correlation, and mix(a,b) represents the second degree of correlation.

5. The method for determining the correlation degree of knowledge documents applied to a mining scientific research knowledge service platform according to claim 3, characterized in that, The time window includes multiple windows with different time granularities, and the time period weight S(i) is a normalized weight, wherein the time granularity corresponding to the same time window is inversely proportional to the time period weight value.

6. A knowledge document correlation prediction device applied to a mining scientific research knowledge service platform, characterized in that, include: The first acquisition unit is used to acquire the structured attribute information of knowledge documents in the mining scientific research knowledge base; The second acquisition unit is used to acquire the user's interaction log with the knowledge document; the interaction log includes the user's click records and download records of the knowledge document; The calculation unit is used to calculate a first degree of correlation between two knowledge documents based on the structured attribute information, and to calculate a second degree of correlation between the two knowledge documents based on the click records and download records. The fusion unit is used to fuse the first correlation degree and the second correlation degree using fusion parameters to obtain the correlation degree probability between the two knowledge documents.

7. The knowledge document correlation determination device applied to a mining scientific research knowledge service platform according to claim 6, characterized in that, The computing unit is specifically used for: For each attribute n, calculate the cosine similarity (attribute[a,n], attribute[b,n], n) between two knowledge documents a and b on that attribute; Obtain the importance weights Q(n) for each attribute, and ; The first degree of similarity, similarity_compare(a,b), is calculated using the following formula: Where β is a preset similarity threshold.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described in any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that, The computer program, when executed by a processor, implements the method as described in any one of claims 1 to 5.

Images