WO2021179687A1 - 医疗文献排序方法、装置、电子设备及存储介质 - Google Patents

医疗文献排序方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2021179687A1
WO2021179687A1 PCT/CN2020/131808 CN2020131808W WO2021179687A1 WO 2021179687 A1 WO2021179687 A1 WO 2021179687A1 CN 2020131808 W CN2020131808 W CN 2020131808W WO 2021179687 A1 WO2021179687 A1 WO 2021179687A1
Authority
WO
WIPO (PCT)
Prior art keywords
medical
document
medical document
documents
score
Prior art date
Application number
PCT/CN2020/131808
Other languages
English (en)
French (fr)
Inventor
柴玲
Original Assignee
平安科技(深圳)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2021179687A1 publication Critical patent/WO2021179687A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2458Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465Query processing support for facilitating data mining operations in structured databases
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/248Presentation of query results

Definitions

  • This application relates to the technical field of information recommendation, and specifically relates to a medical document sorting method, device, electronic equipment, and storage medium.
  • the massive amount of medical literature in the medical literature database provides huge research resources and also brings the trouble of screening to the medical researcher. If you want to grasp the core research status of a field or the core context of the research direction, such as the field of lung cancer, you can directly read the high-quality medical literature in the field of lung cancer at different time points is the most efficient method.
  • the quality of each medical article is determined mainly by establishing a citation network, that is, the quality of each medical article is determined by establishing an adjacency matrix.
  • the quality of each medical article can be determined according to the citation status of each medical article. Determine the score of the medical literature that cited the medical literature, and then obtain the score of each medical literature. For example, if medical document B quotes medical document A, then medical document B scores medical document A as 1* ⁇ , where ⁇ is a preset hyperparameter.
  • the accuracy of the determined medical literature scoring depends on the preset hyperparameters, which require a large amount of experimental data and repeated adjustments to be obtained, resulting in a cumbersome process of scoring medical literature and low accuracy.
  • the embodiments of the present application provide a medical document sorting method, device, electronic equipment, and storage medium.
  • the target score of the medical literature can be determined without pre-setting hyperparameters, the scoring process of the medical literature is simplified, and the accuracy of the scoring of the medical literature can be improved.
  • an embodiment of the present application provides a method for sorting medical documents, including:
  • the multiple medical documents are sorted according to the target score of each medical document at the preset time node.
  • an embodiment of the present application provides a medical document sorting device, including:
  • the transceiver unit is used to obtain the citation relationship between multiple medical documents and the publication time of each medical document in the multiple medical documents;
  • a processing unit configured to determine the directed graph of the multiple medical documents under a preset time node according to the citation relationship of the multiple medical documents and the publication time of each medical document;
  • the processing unit is further configured to determine the first score of each medical document in the multiple medical documents according to the directed graph corresponding to the multiple medical documents;
  • the processing unit is further configured to determine the target score of each medical document under the preset time node according to the directed graph corresponding to the multiple medical documents and the first score of each medical document ;
  • the processing unit is further configured to sort the multiple medical documents according to the target score of each medical document at the preset time node.
  • an embodiment of the present application provides an electronic device, including a processor, the processor is connected to a memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory , So that the electronic device executes the following method:
  • the multiple medical documents are sorted according to the target score of each medical document at the preset time node.
  • an embodiment of the present application provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and the computer program causes a computer to execute the following method:
  • the multiple medical documents are sorted according to the target score of each medical document at the preset time node.
  • embodiments of the present application provide a computer program product
  • the computer program product includes a non-transitory computer-readable storage medium storing a computer program
  • the computer is operable to cause the computer to execute the computer program as described in the first aspect Methods.
  • a directed graph can be created based on the citation relationship between medical documents and the publication time, and the score of the medical document can be determined based on the directed graph.
  • FIG. 1 is a schematic flowchart of a method for sorting medical documents according to an embodiment of the application
  • FIG. 2 is a schematic diagram of a directed graph provided by an embodiment of the application.
  • FIG. 3 is a schematic flowchart of another method for sorting medical documents according to an embodiment of the application.
  • FIG. 4 is a block diagram of functional units of a medical document sorting device provided by an embodiment of the application.
  • FIG. 5 is a schematic structural diagram of a medical document sorting device provided by an embodiment of the application.
  • the technical solution of this application can be applied to the fields of artificial intelligence, smart city, digital medical care, blockchain and/or big data technology.
  • the data involved in this application such as medical documents, scores, etc., can be stored in a database, or can be stored in a blockchain, which is not limited by this application.
  • FIG. 1 is a schematic flowchart of a method for sorting medical documents according to an embodiment of the application. This method is applied to a medical document sorting device. The method includes the following steps:
  • the medical document sorting device acquires the citation relationship between multiple medical documents and the publication time of each medical document in the multiple medical documents.
  • the multiple medical documents may be multiple medical documents related to a certain disease in the PUBMED database.
  • the multiple medical documents may be medical documents related to lung cancer, gastric cancer, and tumors.
  • the citation relationship between the multiple medical documents is pre-marked.
  • the citation relationship of the multiple medical documents and the publication time of each medical document can also be obtained.
  • the publication time of each medical document is based on the year as the granularity. For example, if the publication time of a medical document is August 19, 2020, the publication time of the medical document is 2020.
  • the medical document sorting device determines the directed graph of the multiple medical documents under the preset time node according to the citation relationship of the multiple medical documents and the publication time of each medical document.
  • the preset time node is also based on the year.
  • the target medical document of the medical document i cited in the multiple medical documents can be determined, wherein, the medical document i is any medical document in the multiple medical documents, and the value of i is 1 to N, and N is the number of the multiple medical documents, that is, the medical document i is cited in the multiple medical documents, and the publication time
  • the medical document no later than the preset time node is used as the target medical document, and a directed path from the medical document i to the target medical document is created for the medical document i and the target medical document, and the directed graph is obtained.
  • the medical document sorting device determines the first score of each medical document in the multiple medical documents according to the directed graph corresponding to the multiple medical documents.
  • the first score of each medical document in the multiple medical documents is determined according to the directed graph corresponding to the multiple medical documents and the pagerank algorithm.
  • the transition matrix corresponding to the multiple medical documents is determined according to the directed graph (that is, the citation relationship between multiple medical documents and the connection relationship between similar web pages); then, Determine the initial probability of each medical document according to the number of the multiple medical documents, that is, the initial probability of each medical document is 1/N, where N is the number of multiple medical documents; according to the initial probability, transition matrix and preset Super-parameter, through multiple iterations, get the first score of each medical literature, where the first score can also reflect the importance of each medical literature.
  • the score of each medical document can be expressed by formula (1):
  • Pr 1 ⁇ *M*V 0 +(1- ⁇ )*e formula (1)
  • Pr 1 is the vector composed of the scores of each medical document after the first iteration
  • V 0 is the vector composed of the initial probability of each document
  • M is the transition matrix
  • e can be V 0
  • is the preset super Ginseng.
  • the medical document sorting device determines the target score of each medical document under the preset time node according to the directed graph corresponding to the multiple medical documents and the first score of each medical document, so The target score of each medical document is used to indicate the quality of each medical document under the preset time node.
  • the first scores of the multiple medical documents are first normalized to obtain the second score corresponding to each medical document in the multiple medical documents; then, according to the directed graph and each of the medical documents The second score corresponding to the medical document obtains the target score corresponding to the medical document i.
  • the position of each medical document of the medical document i among the medical documents other than the medical document i is determined. Three scores; the third score of each medical document in the other medical documents and the second score of the medical document i are summed to obtain the target score corresponding to the medical document i.
  • the medical literature includes the direct quotation of the medical literature i and the indirect quotation of the medical literature i.
  • the medical literature citing medical literature A includes the medical literature B that directly cites the medical literature A and the medical literature B that indirectly refers to the medical literature A
  • Medical document C Determine the third score of the medical document j for the medical document i according to the second score and publication time of the medical document j, the second score of the medical document i, and the preset time node, wherein, The medical document j refers to any medical document in the medical document i, and the value of j is 1 to M, and M is the number of medical documents citing the medical document i; determine the pair of medical documents that do not cite the medical document i The third score of this medical document i is 0.
  • the first mean value between the medical document j and the second score of the medical document i, and the publication time of the medical document j can be determined
  • the first time difference with the preset time node; according to the first average value and the first time difference, the third score of the medical document j to the medical document i is determined.
  • the medical document j indirectly quotes the medical document i
  • three medical documents are used as examples.
  • the medical document j directly quotes the medical document k (the medical document i is not cited), and the medical document k directly
  • the third score of the medical document j on the medical document j on the medical document k can be determined, and the third score of the medical document k on the medical document i can be determined, and
  • the product of the third score of the medical document j on the medical document k and the third score of the medical document k on the medical document i is used as the third score of the medical document j on the medical document i .
  • the second average value between the second scores of the medical document j and the medical document k, and the second time difference between the publication time of the medical document j and the preset time node can be determined, according to the second average value and the second score.
  • the time difference determines the third score of the medical document j on the medical document k; and determines the third mean value between the medical document k and the second score of the medical document i, and the publication time of the medical document k and the preset time node.
  • the third score of the medical document k on the medical document i is determined according to the third mean value and the third time difference.
  • the third score of medical document j on medical document i can be expressed by formula (2):
  • Pr(i,j) is the third score of medical document j on medical document i
  • Pr(i) is the second score of medical document i
  • Pr(j) is the second score of medical document j
  • T N is the default Time node
  • T j is the publication time of medical document j, among which other situations include that medical document j does not cite medical document i or the publication time of medical document j is later than T N.
  • the target score of medical document i can be expressed by formula (3):
  • Pr i H is the target score of the medical document i
  • Pr(i,j) is the third score of the medical document j on the medical document i
  • Pr i 2 is the second score of the medical document i.
  • the medical document sorting device sorts the multiple medical documents according to the target score of each medical document at the preset time node.
  • the multiple medical documents may be sorted to mine the milestone medical documents under the preset time node from the multiple medical documents.
  • Documents for example, the medical document with the largest target score can be used as the milestone medical document under the preset time node, or a preset number of medical documents can be selected from the multiple medical documents in order of the target score from the largest to the smallest. Milestone medical literature under the preset time node.
  • the scoring parameters between two medical documents with citation relationships can be dynamically set according to the pagerank algorithm, and there is no need to set the super-parameters in advance, thereby simplifying the process of scoring medical documents; moreover, for the first time
  • the pagerank algorithm is applied to the adjacency matrix, and the two scoring results are combined to make the final score of each medical document more accurate. Using the score to rank the quality of the medical literature will make the ranking result more accurate.
  • the medical document ranking method of this application can also be applied to smart medical scenarios. For example, a doctor can sort medical documents before a certain year through the medical document ranking method of this application, which can quickly Finding milestone documents can improve data reference for doctors, improve the efficiency of doctors' diagnosis, and promote the development of medical technology.
  • FIG. 3 is a schematic flowchart of another method for sorting medical documents according to an embodiment of the application.
  • the method is applied to the medical document sorting device, and the repeated content of the method and the embodiment shown in FIG. 1 will not be repeated here.
  • the method of this embodiment includes the following steps:
  • the medical document sorting device acquires the citation relationship between multiple medical documents and the publication time of each medical document in the multiple medical documents.
  • the medical document sorting device determines the directed graph of the multiple medical documents under the preset time node according to the citation relationship of the multiple medical documents and the publication time of each medical document.
  • the medical document sorting device determines the first score of each medical document in the multiple medical documents according to the pagerank algorithm and the directed graph.
  • the medical document sorting device normalizes the first scores of the multiple medical documents to obtain a second score corresponding to each medical document.
  • the medical document sorting device determines, according to the directed graph and the second score of each medical document, that each medical document among the multiple medical documents except the medical document i The third score of medical literature i.
  • the directed graph it is determined that the other medical documents cited the medical documents of the medical document i and the medical documents that did not cite the medical document i (that is, the isolated nodes in the directed graph), wherein the medical documents are cited
  • the medical document of i includes the direct quotation of the medical document i and the indirect quotation of the medical document i; according to the second score and publication time of the medical document j, the second score of the medical document i and the preset time node, the pair of the medical document j is determined
  • the third score of the medical document i where the medical document j refers to any medical document in the medical document i, the value of j is 1 to M, and M is the number of medical documents citing the medical document i , And set the third score of a medical document that does not cite the medical document i to 0.
  • the first mean value between the medical document j and the second score of the medical document i, and the publication time of the medical document j can be determined The first time difference with the preset time node; according to the first mean value, the first time difference, the number of medical documents between the medical document j and the medical document i, and the second score of the medical document j, determine The third score of the medical document j on the medical document i.
  • the medical document j indirectly quotes the medical document i
  • three medical documents are used as examples.
  • the medical document j directly quotes the medical document k (the medical document i is not cited), and the medical document k directly
  • the third score of the medical document j on the medical document j on the medical document k can be determined, and the third score of the medical document k on the medical document i can be determined, and
  • the product of the third score of the medical document j on the medical document k and the third score of the medical document k on the medical document i is taken as the third score of the medical document j on the medical document i.
  • the second average value between the second scores of the medical document j and the medical document k, and the second time difference between the publication time of the medical document j and the preset time node can be determined, according to the second average value, the second Time difference, the number of medical documents between medical document j and medical document k, and the second score of medical document j, determine the third score of medical document j on medical document k; and determine the difference between medical document k and medical document i
  • the third mean value between the second scores and the third time difference between the publication time of the medical document k and the preset time node, according to the third mean value, the third time difference, the medical document k and the medical document i The number of documents and the second score of the medical document k determine the third score of the medical document k on the medical document i.
  • the third score of medical document j on medical document i can be expressed by formula (3):
  • Pr(i,j) is the third score of medical document j on medical document i
  • Pr(i) is the second score of medical document i
  • Pr(j) is the second score of medical document j
  • x is medical document j
  • T N is the preset time node
  • T j is the publication time of the medical document j.
  • Other situations include the publication of the medical document j without quoting the medical document i or the publication of the medical document j The time is later than T N.
  • the second score of medical document j is introduced in formula (3), that is, the importance of medical document j itself is considered in the process of calculating the score of medical document j on medical document i, which is equivalent to taking medical document j
  • the second score of is used as a weighting coefficient to weight the score, so that the obtained medical document j has a more accurate score on the medical document i; and the unimodal distribution function ex is also introduced in formula (3), so that with the medical treatment
  • the distance between document j and medical document i becomes longer (that is, when the number of medical documents between two medical documents is large), even if medical document j itself is important, medical document i will increase with the distance
  • the attenuation further makes the score more accurate.
  • the medical document sorting device sums the third score of the medical document i and the second score of the medical document i for each medical document in the other medical documents to obtain the target corresponding to the medical document i score.
  • the medical document sorting device sorts the multiple medical documents according to the target score of each medical document at the preset time node.
  • the scoring parameters between two medical documents with citation relationships can be dynamically set according to the pagerank algorithm, and there is no need to set the super-parameters in advance, thereby simplifying the process of scoring medical documents; moreover, for the first time
  • the pagerank algorithm is applied to the adjacency matrix, and the two scoring results are combined to make the final score of each medical literature more accurate. Using this score to evaluate the quality of the medical literature will make the evaluation result more accurate.
  • a weight coefficient and a unimodal distribution function are introduced to make the determined score of the medical literature more accurate, so that the ranking of the medical literature is more accurate.
  • the medical document sorting device 400 includes: a transceiver unit 401 and a processing unit 402, wherein:
  • the transceiver unit 401 is configured to obtain the citation relationship between multiple medical documents and the publication time of each medical document in the multiple medical documents;
  • the processing unit 402 is configured to determine the directed graph of the multiple medical documents under a preset time node according to the citation relationship of the multiple medical documents and the publication time of each medical document;
  • the processing unit 402 is further configured to determine the first score of each medical document in the multiple medical documents according to the directed graph corresponding to the multiple medical documents;
  • the processing unit 402 is further configured to determine the target score of each medical document under the preset time node according to the directed graph corresponding to the multiple medical documents and the first score of each medical document;
  • the processing unit 402 is further configured to sort the multiple medical documents according to the target score of each medical document at the preset time node.
  • processing Unit 402 is specifically used for:
  • the target medical document corresponding to the medical document among the multiple medical documents is determined, wherein the medical document i Is any medical document in the plurality of medical documents, and the target medical document is a medical document that references the medical document i among the plurality of medical documents;
  • the processing unit 402 in determining the first score of each medical document in the multiple medical documents according to the directed graph corresponding to the multiple medical documents, is specifically configured to:
  • the first score of each medical document in the multiple medical documents is determined.
  • the target of each medical document under the preset time node is determined according to the directed graph corresponding to the multiple medical documents and the first score of each medical document
  • the processing unit 402 is specifically configured to:
  • the target score corresponding to the medical document i is obtained, and the medical document i is any one of the multiple medical documents.
  • the processing unit 402 is specifically configured to:
  • each medical document in the plurality of medical documents other than the medical document i is third to the medical document i. score;
  • the third score of the medical document i and the second score of the medical document i of each medical document in the other medical documents are summed to obtain the target score corresponding to the medical document i.
  • each medical document in the plurality of medical documents other than the medical document i is determined Regarding the third scoring aspect of the medical document i, the processing unit 402 is specifically configured to:
  • the directed graph it is determined that the other medical documents cited the medical documents of the medical document i and the medical documents that did not cite the medical document i (that is, the isolated nodes in the directed graph), where the The medical document citing the medical document i includes direct citing of the medical document i and indirect citing of the medical document i;
  • the third score of the medical document j for the medical document i is determined, wherein the medical Document j refers to any one of the medical documents in the medical document i, and it is determined that the medical document that does not cite the medical document i has a third score of 0 for the medical document i.
  • the processing unit 402 is specifically configured to:
  • the first average value between the medical document j and the second score of the medical document i is determined, and the publication time of the medical document j and Determining the first time difference between the preset time nodes, and determining the third score of the medical document j on the medical document i according to the first average value and the first time difference;
  • the medical document j directly quotes the medical document k, and the medical document i is not cited, and the medical document k directly quotes the medical document i
  • the product of the third score of the medical document i is used as the third score of the medical document j on the medical document i.
  • FIG. 5 is a schematic structural diagram of an electronic device according to an embodiment of the application.
  • the electronic device 500 includes a transceiver 501, a processor 502, and a memory 503. They are connected by a bus 504 between them.
  • the memory 503 is used to store computer programs and data, and can transmit the stored data to the processor 502.
  • the processor 502 is configured to read the computer program in the memory 503 to perform the following operations:
  • the multiple medical documents are sorted according to the target score of each medical document at the preset time node.
  • processing The device 502 is specifically configured to perform the following operations:
  • the target medical document corresponding to the medical document among the multiple medical documents is determined, wherein the medical document i Is any medical document in the plurality of medical documents, and the target medical document is a medical document that references the medical document i among the plurality of medical documents;
  • the processor 502 is specifically configured to perform the following operations :
  • the first score of each medical document in the multiple medical documents is determined.
  • the target of each medical document under the preset time node is determined according to the directed graph corresponding to the multiple medical documents and the first score of each medical document
  • the processor 502 is specifically configured to perform the following operations:
  • the target score corresponding to the medical document i is obtained, and the medical document i is any one of the multiple medical documents.
  • the processor 502 is specifically configured to perform the following operations:
  • each medical document in the plurality of medical documents other than the medical document i is third to the medical document i. score;
  • the third score of the medical document i and the second score of the medical document i of each medical document in the other medical documents are summed to obtain the target score corresponding to the medical document i.
  • each medical document in the plurality of medical documents other than the medical document i is determined Regarding the third scoring of the medical document i, the processor 502 is specifically configured to perform the following operations:
  • the directed graph it is determined that the other medical documents cited the medical documents of the medical document i and the medical documents that did not cite the medical document i (that is, the isolated nodes in the directed graph), where the The medical document citing the medical document i includes direct citing of the medical document i and indirect citing of the medical document i;
  • the third score of the medical document j for the medical document i is determined, wherein the medical Document j refers to any one of the medical documents in the medical document i, and it is determined that the medical document that does not cite the medical document i has a third score of 0 for the medical document i.
  • the processor 502 is specifically configured to perform the following operations:
  • the first average value between the medical document j and the second score of the medical document i is determined, and the publication time of the medical document j and Determining the first time difference between the preset time nodes, and determining the third score of the medical document j on the medical document i according to the first average value and the first time difference;
  • the medical document j directly quotes the medical document k, and the medical document i is not cited, and the medical document k directly quotes the medical document i
  • the product of the third score of the medical document i is used as the third score of the medical document j on the medical document i.
  • the transceiver 501 may be the transceiver unit 401 of the medical document sorting device 400 in the embodiment shown in FIG. 4, and the processor 502 may be the processing unit 402 of the medical document sorting device 400 in the embodiment shown in FIG. .
  • the medical document sorting device in this application can include smart phones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, handheld computers, notebook computers, mobile Internet devices MID (Mobile Internet Devices, referred to as MID) or wearables Type equipment, etc.
  • MID Mobile Internet Devices, referred to as MID
  • the aforementioned medical document sorting device is only an example, not an exhaustive list, and includes but not limited to the aforementioned medical document sorting device. In practical applications, the above-mentioned medical document sorting device may also include: intelligent vehicle-mounted terminals, computer equipment, and so on.
  • the embodiments of the present application also provide a computer-readable storage medium, the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to realize any sort of medical document sorting as described in the above method embodiments Part or all of the steps of the method.
  • the storage medium involved in this application such as a computer-readable storage medium, may be non-volatile or volatile.
  • the embodiments of the present application also provide a computer program product.
  • the computer program product includes a non-transitory computer-readable storage medium storing a computer program.
  • the computer program is operable to cause a computer to execute the method described in the foregoing method embodiment. Part or all of the steps of any sort of medical literature.
  • the disclosed device may be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or in the form of software program modules.
  • the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer readable memory.
  • the technical solution of the present application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory.
  • a number of instructions are included to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
  • the program can be stored in a computer-readable memory, and the memory can include: a flash disk , Read-only memory (English: Read-Only Memory, abbreviation: ROM), random access device (English: Random Access Memory, abbreviation: RAM), magnetic disk or optical disc, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Fuzzy Systems (AREA)
  • Software Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Mathematical Physics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

一种医疗文献排序方法、装置、电子设备及存储介质。该方法包括:医疗文献排序装置获取多篇医疗文献之间的引用关系以及所述多篇医疗文献中每篇医疗文献的发表时间(101);医疗文献排序装置根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图(102);医疗文献排序装置根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分(103);医疗文献排序装置根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分,所述每篇医疗文献的目标评分用于表示所述每篇医疗文献在所述预设时间节点下的质量(104);医疗文献排序装置根据所述每篇医疗文献在所述预设时间节点下的目标评分,对所述多篇医疗文献进行排序(105)。

Description

医疗文献排序方法、装置、电子设备及存储介质
本申请要求于2020年10月23日提交中国专利局、申请号为202011153172.4,发明名称为“医疗文献排序方法、装置、电子设备及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及信息推荐技术领域,具体涉及一种医疗文献排序方法、装置、电子设备及存储介质。
背景技术
对于一个医学研究者来说,医学文献库中海量的医疗文献在提供了巨大研究资源,也给医学研究者带来了筛选的麻烦。如果想把握一个领域最核心的研究现状或者研究方向核心脉络,如肺癌领域,可直接阅读肺癌领域在不同时间点的高质量医疗文献是最高效的方法。
发明人意识到,目前主要通过基于建立引文网络的方式,确定每篇医疗的质量,即通过建立邻接矩阵的方式确定每篇医疗文献的质量,比如,可根据每篇医疗文献的被引用情况,确定引用该医疗文献的医疗文献对该医疗文献的评分,进而得到每篇医疗文献的评分。比如,医疗文献B引用医疗文献A,则医疗文献B对医疗文献A的评分为1*γ,其中,γ为预设的超参数。
因此,确定出的医疗文献的评分的精确度依赖于预设的超参数,这个超参数需要大量的实验数据以及反复调整才能得出,导致对医疗文献的评分过程比较繁琐,精度比较低。
发明内容
本申请实施例提供了一种医疗文献排序方法、装置、电子设备及存储介质。无需预设超参数即可确定出医疗文献的目标评分,简化对医疗文献的评分过程,以及提高对医疗文献的评分精度。
第一方面,本申请实施例提供一种医疗文献排序方法,包括:
获取多篇医疗文献之间的引用关系以及所述多篇医疗文献中每篇医疗文献的发表时间;
根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图;
根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分;
根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分;
根据所述每篇医疗文献在所述预设时间节点下的目标评分,对所述多篇医疗文献进行排序。
第二方面,本申请实施例提供一种医疗文献排序装置,包括:
收发单元,用于获取多篇医疗文献之间的引用关系以及所述多篇医疗文献中每篇医疗文献的发表时间;
处理单元,用于根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图;
所述处理单元,还用于根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分;
所述处理单元,还用于根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分;
所述处理单元,还用于根据所述每篇医疗文献在所述预设时间节点下的目标评分,对 所述多篇医疗文献进行排序。
第三方面,本申请实施例提供一种电子设备,包括:处理器,所述处理器与存储器相连,所述存储器用于存储计算机程序,所述处理器用于执行所述存储器中存储的计算机程序,以使得所述电子设备执行以下方法:
获取多篇医疗文献之间的引用关系以及所述多篇医疗文献中每篇医疗文献的发表时间;
根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图;
根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分;
根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分;
根据所述每篇医疗文献在所述预设时间节点下的目标评分,对所述多篇医疗文献进行排序。
第四方面,本申请实施例提供一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,所述计算机程序使得计算机执行以下方法:
获取多篇医疗文献之间的引用关系以及所述多篇医疗文献中每篇医疗文献的发表时间;
根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图;
根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分;
根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分;
根据所述每篇医疗文献在所述预设时间节点下的目标评分,对所述多篇医疗文献进行排序。
第五方面,本申请实施例提供一种计算机程序产品,所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质,所述计算机可操作来使计算机执行如第一方面所述的方法。
实施本申请实施例,可基于医疗文献之间的引用关系以及发表时间创建有向图,根据该有向图可确定出医疗文献的评分,无需提前设置超参数,从而简化了对医疗文献评分的过程,提高了每篇医疗文献的评分精确。
附图说明
为了更清楚地说明本申请实施例中的技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图是本申请的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的一种医疗文献排序方法的流程示意图;
图2为本申请实施例提供的一种有向图的示意图;
图3为本申请实施例提供的另一种医疗文献排序方法的流程示意图;
图4为本申请实施例提供的一种医疗文献排序装置的功能单元组成框图;
图5为本申请实施例提供的一种医疗文献排序装置的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
本申请的说明书和权利要求书及所述附图中的术语“第一”、“第二”、“第三”和“第四”等是用于区别不同对象,而不是用于描述特定顺序。此外,术语“包括”和“具有”以及它们任何变形,意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元,而是可选地还包括没有列出的步骤或单元,或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。
在本文中提及“实施例”意味着,结合实施例描述的特定特征、结果或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例,也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是,本文所描述的实施例可以与其它实施例相结合。
本申请的技术方案可应用于人工智能、智慧城市、数字医疗、区块链和/或大数据技术领域。可选的,本申请涉及的数据如医疗文献、评分等可存储于数据库中,或者可以存储于区块链中,本申请不做限定。
参阅图1,图1为本申请实施例提供的医疗文献排序方法的流程示意图。该方法应用于医疗文献排序装置。该方法包括以下步骤:
101:医疗文献排序装置获取多篇医疗文献之间的引用关系以及所述多篇医疗文献中每篇医疗文献的发表时间。
其中,该多篇医疗文献可以为PUBMED数据库中与某一种疾病相关的多篇医疗文献,比如,该多篇医疗文献可以为与肺癌、胃癌、肿瘤相关的医疗文献。
其中,该多篇医疗文献之间的引用关系是预先标注好的,在从PUBMED数据库获取该多篇医疗文献的过程,还可获取该多篇医疗文献的引用关系以及每篇医疗文献的发表时间。其中,每篇医疗文献的发表时间是以年份为粒度的,比如,某篇医疗文献的发表时间为2020年8月19号,则该医疗文献的发表时间为2020年。
102:医疗文献排序装置根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图。
其中,该预设时间节点也是以年份为粒度的。
示例性的,可根据该多篇医疗文献中篇医疗文献之间的引用关系以及每篇医疗文献的发表时间,确定该多篇医疗文献中引用医疗文献i的目标医疗文献,其中,该医疗文献i为该多篇医疗文献中的任意一篇医疗文献,i的取值为1到N,N为该多篇医疗文献的数量,即将该多篇医疗文献中引用了医疗文献i,且发表时间不晚于预设时间节点的医疗文献作为该目标医疗文献,并为该医疗文献i与该目标医疗文献创建医疗从医疗文献i到该目标医疗文献的有向路径,得到该有向图。应理解,对于该多篇医疗中引用了该医疗文献i,但发表时间是晚于该预设时间节点的医疗文献以及对于没有引用医疗文献i的医疗文献(无论发表时间是否晚于该预设时间点),不能为这些医疗文献与医疗文献i之间创建有向路径,将这些孤立的节点,通过创建医疗文献i的有向路径,得到该有向图。
举例来说,如图2所示,若医疗文献B和医疗文献D都引用了医疗文献A,医疗文献C引用了医疗文献B,医疗文献A、医疗文献B、医疗文献C以及医疗文献D的发表时间分别为Ta、Tb、Tc和Td,若Tb和Tc不晚于预设时间节点T N,则可以创建一条从医疗文献A到医疗文献B的有向路径,以及创建一条从医疗文献B到医疗文献C的有向路径。若Td晚于预设时间节点T N,虽然医疗文献D也引用了医疗文献A,但是不能创建一条从医疗文献A到医疗文献B的有向路径,将医疗文献D作为一个孤立的节点。
103:医疗文献排序装置根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分。
示例性的,根据该多篇医疗文献对应的有向图以及pagerank算法,确定该多篇医疗文献中每篇医疗文献的第一评分。
示例性的,与确定网页重要性的方法类似,根据该有向图(即多篇医疗文献之间的引用关系,类似网页的连接关系)确定所述多篇医疗文献对应的转移矩阵;然后,根据该多篇医疗文献的数量确定每篇医疗文献的初始概率,即每篇医疗文献的初始概率为1/N,N为多篇医疗文献的数量;根据该初始概率、转移矩阵以及预设的超参,进行多次迭代,得到每篇医疗文献的第一评分,其中,该第一评分也可以反映每篇医疗文献的重要性程度。
示例性的,在第一次迭代的过程中,每篇医疗文献的评分可通过公式(1)表示:
Pr 1=α*M*V 0+(1-α)*e    公式(1);
其中,Pr 1为第一次迭代后每篇医疗文献的评分组成的向量,V 0为每篇文献的初始概率组成的向量,M为转移矩阵,e可以为V 0,α为预设的超参。
104:医疗文献排序装置根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分,所述每篇医疗文献的目标评分用于表示所述每篇医疗文献在所述预设时间节点下的质量。
示例性的,先对该多篇医疗文献的第一评分进行归一化,得到该多篇医疗文献中每篇医疗文献对应的第二评分;然后,根据所述有向图以及所述每篇医疗文献对应的第二评分,得到医疗文献i对应的目标评分。示例性的,根据该有向图以及每篇医疗文献的第二评分,确定该多篇医疗文献中除所述医疗文献i之外的其他医疗文献中每篇医疗文献对该医疗文献i的第三评分;将所述其他医疗文献中每篇医疗文献对该医疗文献i的第三评分以及所述医疗文献i的第二评分进行求和,得到该医疗文献i对应的目标评分。
具体的,根据该有向图,确定该其他医疗文献中引用了医疗文献i的医疗文献以及未引用该医疗文献i的医疗文献(即有向图中的孤立节点),其中,引用医疗文献i的医疗文献包括直接引用该医疗文献i和间接引用该医疗文献i,比如,如图2所示,引用医疗文献A的医疗文献包括直接引用医疗文献A的医疗文献B以及间接引用医疗文献A的医疗文献C;根据医疗文献j的第二评分和发表时间、所述医疗文献i的第二评分以及所述预设时间节点,确定该医疗文献j对该医疗文献i的第三评分,其中,该医疗文献j为引用该医疗文献i中的任意一篇医疗文献,j的取值为1到M,M为引用该医疗文献i的医疗文献的数量;确定未引用医疗文献i的医疗文献对该医疗文献i的第三评分为0。
示例性的,在该医疗文献j直接引用该医疗文献i的情况下,则可确定该医疗文献j与该医疗文献i的第二评分之间的第一均值,以及该医疗文献j的发表时间与该预设时间节点之间的第一时间差;根据该第一均值以及该第一时间差,确定该医疗文献j对医疗文献i的第三评分。
示例性的,在医疗文献j间接引用该医疗文献i的情况下,以三篇医疗文献进行举例说明,比如,医疗文献j直接引用医疗文献k(未引用医疗文献i),且医疗文献k直接引用医疗文献i的情况下,则可确定所述医疗文献j对所述医疗文献j对医疗文献k的第三评分,以及所述医疗文献k对所述医疗文献i的第三评分,并将所述医疗文献j对所述医疗文献k的第三评分以及所述医疗文献k对所述医疗文献i的第三评分的乘积,作为所述医疗文献j对所述医疗文献i的第三评分。具体的,可确定医疗文献j与医疗文献k的第二评分之间的第二均值,以及该医疗文献j发表时间与预设时间节点之间的第二时间差,根据该第二均值以及第二时间差确定该医疗文献j对医疗文献k的第三评分;并确定医疗文献k与医疗文献i的第二评分之间的第三均值,以及该医疗文献k的发表时间与预设时间节点的第三时间差,根据该第三均值以及第三时间差确定该医疗文献k对医疗文献i的第三评分。
示例性的,医疗文献j对医疗文献i的第三评分可以通过公式(2)表示:
Figure PCTCN2020131808-appb-000001
Pr(i,j)为医疗文献j对医疗文献i的第三评分,Pr(i)为医疗文献i的第二评分,Pr(j)为医疗文献j的第二评分,T N为预设时间节点,T j为医疗文献j的发表时间,其中,其他情况包括医疗文献j未引用医疗文献i或者医疗文献j的发表时间晚于T N
示例性的,医疗文献i的目标评分可以通过公式(3)表示:
Figure PCTCN2020131808-appb-000002
其中,Pr i H为医疗文献i的目标评分,Pr(i,j)为医疗文献j对医疗文献i的第三评分,Pr i 2为医疗文献i的第二评分。之所以最后叠加每篇医疗文献的第二评分,主要是考虑一些孤立的医疗文献本身是具有一定影响力的,避免将这种医疗文献的目标评分设置为0,从而使每篇医疗文献的目标评分更加具有说服力。
105:医疗文献排序装置根据所述每篇医疗文献在所述预设时间节点下的目标评分,对所述多篇医疗文献进行排序。
示例性的,在得到每篇医疗文献在预设时间节点下的目标评分之后,可对该多篇医疗文献进行排序,以从该多篇医疗文献中挖掘出在预设时间节点下的里程碑医疗文献,比如,可以将目标评分最大的医疗文献作为该预设时间节点下的里程碑医文献,或者按照目标评分从大到小的顺序从该多篇医疗文献中选出预设数量的医疗文献作为该预设时间节点下的里程碑医疗文献。
可以看出,在本申请实施方式中,可根据pagerank算法动态设置两个具有引用关系的医疗文献之间的评分参数,无需预先设置超参,从而简化了对医疗文献评分的过程;而且,首次将pagerank算法应用到邻接矩阵中,将两种评分结果进行结合,使最终得到的每篇医疗文献的评分更加精确,使用该评分对医疗文献的质量进行排序,会使排序结果更加精确。
在本申请的一个实施方式中,本申请的医疗文献排序方法还可应用到智慧医疗场景,比如,医生可以通过本申请的医疗文献排序方法对某个年份之前的医疗文献进行排序,可以快速的找到里程碑文献,为医生提高数据参考,提高医生诊断效率,进而推动医疗科技的发展。
参阅图3,图3为本申请实施例提供的另一种医疗文献排序方法的流程示意图。该方法应用于医疗文献排序装置,该方法与图1所示的实施例中的重复内容在此不再重复描述。本实施例方法包括以下步骤:
301:医疗文献排序装置获取多篇医疗文献之间的引用关系以及所述多篇医疗文献中每篇医疗文献的发表时间。
302:医疗文献排序装置根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图。
303:医疗文献排序装置根据pagerank算法以及所述有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分。
304:医疗文献排序装置对所述多篇医疗文献的第一评分进行归一化,得到所述每篇医 疗文献对应的第二评分。
305:医疗文献排序装置根据所述有向图以及每篇医疗文献的第二评分,确定所述多篇医疗文献中除所述医疗文献i之外的其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分。
示例性的,根据该有向图,确定该其他医疗文献中引用了医疗文献i的医疗文献以及未引用该医疗文献i的医疗文献(即有向图中的孤立节点),其中,引用医疗文献i的医疗文献包括直接引用该医疗文献i和间接引用该医疗文献i;根据医疗文献j的第二评分和发表时间、医疗文献i的第二评分以及预设时间节点,确定该医疗文献j对该医疗文献i的第三评分,其中,该医疗文献j为引用该医疗文献i中的任意一篇医疗文献,j的取值为1到M,M为引用该医疗文献i的医疗文献的数量,并且设置未引用医疗文献i的医疗文献对该医疗文献i的第三评分为0。
示例性的,在该医疗文献j直接引用该医疗文献i的情况下,则可确定该医疗文献j与该医疗文献i的第二评分之间的第一均值,以及该医疗文献j的发表时间与该预设时间节点之间的第一时间差;根据该第一均值、该第一时间差、医疗文献j和医疗文献i之间间隔的医疗文献的数量以及该医疗文献j的第二评分,确定该医疗文献j对医疗文献i的第三评分。
示例性的,在医疗文献j间接引用该医疗文献i的情况下,以三篇医疗文献进行举例说明,比如,医疗文献j直接引用医疗文献k(未引用医疗文献i),且医疗文献k直接引用医疗文献i的情况下,则可确定所述医疗文献j对所述医疗文献j对医疗文献k的第三评分,以及所述医疗文献k对所述医疗文献i的第三评分,并将所述医疗文献j对医疗文献k的第三评分以及所述医疗文献k对所述医疗文献i的第三评分的乘积,作为所述医疗文献j对所述医疗文献i的第三评分。具体的,可确定医疗文献j与医疗文献k的第二评分之间的第二均值,以及该医疗文献j发表时间与预设时间节点之间的第二时间差,根据该第二均值、第二时间差、医疗文献j和医疗文献k之间间隔的医疗文献的数量以及医疗文献j的第二评分,确定该医疗文献j对医疗文献k的第三评分;并确定医疗文献k与医疗文献i的第二评分之间的第三均值,以及该医疗文献k的发表时间与预设时间节点的第三时间差,根据该第三均值、第三时间差、医疗文献k和医疗文献i之间间隔的医疗文献的数量以及医疗文献k的第二评分、确定该医疗文献k对医疗文献i的第三评分。
示例性的,医疗文献j对医疗文献i的第三评分可以通过公式(3)表示:
Figure PCTCN2020131808-appb-000003
Pr(i,j)为医疗文献j对医疗文献i的第三评分,Pr(i)为医疗文献i的第二评分,Pr(j)为医疗文献j的第二评分,x为医疗文献j与医疗文献i之间间隔的医疗文献的数量,T N为预设时间节点,T j为医疗文献j的发表时间,其中,其他情况包括医疗文献j未引用医疗文献i或者医疗文献j的发表时间晚于T N
可以看出,公式(3)中引入了医疗文献j的第二评分,即在计算医疗文献j对医疗文献i的评分的过程中考虑到了医疗文献j本身的重要性,相当于将医疗文献j的第二评分作为一个权重系数,对评分进行加权,这样求出的医疗文献j对医疗文献i的评分更加精确;并且,公式(3)中还引入了单峰分布函数e-x,这样随着医疗文献j与医疗文献i之间的距离变远(即两篇医学文献之间的医学文献数量较多的情况下),即使医疗文献j本身很重要,对医疗文献i也是要随着距离的增加而衰减,进一步使评分更加精确。
306:医疗文献排序装置将所述其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分以及所述医疗文献i的第二评分进行求和,得到所述医疗文献i对应的目标评分。
307:医疗文献排序装置根据所述每篇医疗文献在所述预设时间节点下的目标评分,对所述多篇医疗文献进行排序。
可以看出,在本申请实施方式中,可根据pagerank算法动态设置两个具有引用关系的医疗文献之间的评分参数,无需预先设置超参,从而简化了对医疗文献评分的过程;而且,首次将pagerank算法应用到邻接矩阵中,将两种评分结果进行结合,使最终得到的每篇医疗文献的评分更加精确,使用该评分对医疗文献的质量进行评价会使评价结果更加精确。并且,在确定医疗文献的评分的过程中,引入了权重系数以及单峰分布函数,使确定出的医疗文献的评分更加精确,从而使医疗文献的排序更加精确。
参阅图4,图4本申请实施例提供的一种医疗文献排序装置的功能单元组成框图。医疗文献排序装置400包括:收发单元401和处理单元402,其中:
收发单元401,用于获取多篇医疗文献之间的引用关系以及所述多篇医疗文献中每篇医疗文献的发表时间;
处理单元402,用于根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图;
处理单元402,还用于根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分;
处理单元402,还用于根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分;
处理单元402,还用于根据所述每篇医疗文献在所述预设时间节点下的目标评分,对所述多篇医疗文献进行排序。
在一些可能的实施方式中,在根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图方面,处理单元402,具体用于:
根据所述多篇医疗文献中篇医疗文献之间的引用关系以及医疗文献i的发表时间,确定所述多篇医疗文献中与所述医疗文献对应的目标医疗文献,其中,所述医疗文献i为所述多篇医疗文献中的任意一篇医疗文献,所述目标医疗文献为所述多篇医疗文献中引用所述医疗文献i的医疗文献;
创建从所述所述医疗文献i到所述目标医疗文献的有向路径,以及将所述多篇医疗文献中除所述目标医疗文献之外的医疗文献作为孤立节点,得到所述多篇医疗文献在预设时间节点下的有向图。
在一些可能的实施方式中,在根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分方面,处理单元402,具体用于:
根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献对应的转移矩阵;
根据所述多篇医疗文献对应的转移矩阵以及所述多篇医疗文献的数量,确定所述多篇医疗文献中每篇医疗文献的第一评分。
在一些可能的实施方式中,在根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分方面,处理单元402,具体用于:
对所述多篇医疗文献的第一评分进行归一化,得到所述每篇医疗文献对应的第二评分;
根据所述有向图以及所述每篇医疗文献对应的第二评分,得到医疗文献i对应的目标评分,所述医疗文献i为所述多篇医疗文献中的任意一篇医疗文献。
在一些可能的实施方式中,在根据所述有向图以及所述每篇医疗文献对应的第二评分,得到医疗文献i对应的目标评分方面,处理单元402,具体用于:
根据所述有向图以及每篇医疗文献的第二评分,确定所述多篇医疗文献中除所述医疗 文献i之外的其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分;
将所述其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分以及所述医疗文献i的第二评分进行求和,得到所述医疗文献i对应的目标评分。
在一些可能的实施方式中,在根据所述有向图以及每篇医疗文献的第二评分,确定所述多篇医疗文献中除所述医疗文献i之外的其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分方面,处理单元402,具体用于:
根据所述有向图,确定所述其他医疗文献中引用了所述医疗文献i的医疗文献以及未引用所述医疗文献i的医疗文献(即有向图中的孤立节点),其中,所述引用了所述医疗文献i的医疗文献包括直接引用所述医疗文献i和间接引用所述医疗文献i;
根据医疗文献j的第二评分和发表时间、所述医疗文献i的第二评分以及所述预设时间节点,确定所述医疗文献j对该医疗文献i的第三评分,其中,所述医疗文献j为所述引用了所述医疗文献i中的任意一篇医疗文献,并确定所述未引用医疗文献i的医疗文献对所述医疗文献i的第三评分为0。
在一些可能的实施方式中,在根据医疗文献j的第二评分和发表时间、所述医疗文献i的第二评分以及所述预设时间节点,确定所述医疗文献j对该医疗文献i的第三评分方面,处理单元402,具体用于:
在所述医疗文献j直接引用所述医疗文献i的情况下,确定所述医疗文献j与所述医疗文献i的第二评分之间的第一均值,以及所述医疗文献j的发表时间与所述预设时间节点之间的第一时间差,并根据所述第一均值以及所述第一时间差,确定所述医疗文献j对所述医疗文献i的第三评分;
在所述医疗文献j直接引用医疗文献k,且未引用所述医疗文献i,且所述医疗文献k直接引用了所述医疗文献i的情况下,确定所述医疗文献j对所述医疗文献j对医疗文献k的第三评分,以及所述医疗文献k对所述医疗文献i的第三评分,并将所述医疗文献j对所述医疗文献k的第三评分以及所述医疗文献k对所述医疗文献i的第三评分的乘积,作为所述医疗文献j对所述医疗文献i的第三评分。
参阅图5,图5为本申请实施例提供的一种电子设备的结构示意图。如图5所示,电子设备500包括收发器501、处理器502和存储器503。它们之间通过总线504连接。存储器503用于存储计算机程序和数据,并可与将存储的数据传输给处理器502。
处理器502用于读取存储器503中的计算机程序执行以下操作:
控制收发器501获取多篇医疗文献之间的引用关系以及所述多篇医疗文献中每篇医疗文献的发表时间;
根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图;
根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分;
根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分;
根据所述每篇医疗文献在所述预设时间节点下的目标评分,对所述多篇医疗文献进行排序。
在一些可能的实施方式中,在根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图方面,处理器502,具体用于执行以下操作:
根据所述多篇医疗文献中篇医疗文献之间的引用关系以及医疗文献i的发表时间,确定所述多篇医疗文献中与所述医疗文献对应的目标医疗文献,其中,所述医疗文献i为所 述多篇医疗文献中的任意一篇医疗文献,所述目标医疗文献为所述多篇医疗文献中引用所述医疗文献i的医疗文献;
创建从所述所述医疗文献i到所述目标医疗文献的有向路径,以及将所述多篇医疗文献中除所述目标医疗文献之外的医疗文献作为孤立节点,得到所述多篇医疗文献在预设时间节点下的有向图。
在一些可能的实施方式中,在根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分方面,处理器502,具体用于执行以下操作:
根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献对应的转移矩阵;
根据所述多篇医疗文献对应的转移矩阵以及所述多篇医疗文献的数量,确定所述多篇医疗文献中每篇医疗文献的第一评分。
在一些可能的实施方式中,在根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分方面,处理器502,具体用于执行以下操作:
对所述多篇医疗文献的第一评分进行归一化,得到所述每篇医疗文献对应的第二评分;
根据所述有向图以及所述每篇医疗文献对应的第二评分,得到医疗文献i对应的目标评分,所述医疗文献i为所述多篇医疗文献中的任意一篇医疗文献。
在一些可能的实施方式中,在根据所述有向图以及所述每篇医疗文献对应的第二评分,得到医疗文献i对应的目标评分方面,处理器502,具体用于执行以下操作:
根据所述有向图以及每篇医疗文献的第二评分,确定所述多篇医疗文献中除所述医疗文献i之外的其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分;
将所述其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分以及所述医疗文献i的第二评分进行求和,得到所述医疗文献i对应的目标评分。
在一些可能的实施方式中,在根据所述有向图以及每篇医疗文献的第二评分,确定所述多篇医疗文献中除所述医疗文献i之外的其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分方面,处理器502,具体用于执行以下操作:
根据所述有向图,确定所述其他医疗文献中引用了所述医疗文献i的医疗文献以及未引用所述医疗文献i的医疗文献(即有向图中的孤立节点),其中,所述引用了所述医疗文献i的医疗文献包括直接引用所述医疗文献i和间接引用所述医疗文献i;
根据医疗文献j的第二评分和发表时间、所述医疗文献i的第二评分以及所述预设时间节点,确定所述医疗文献j对该医疗文献i的第三评分,其中,所述医疗文献j为所述引用了所述医疗文献i中的任意一篇医疗文献,并确定所述未引用医疗文献i的医疗文献对所述医疗文献i的第三评分为0。
在一些可能的实施方式中,在根据医疗文献j的第二评分和发表时间、所述医疗文献i的第二评分以及所述预设时间节点,确定所述医疗文献j对该医疗文献i的第三评分方面,处理器502,具体用于执行以下操作:
在所述医疗文献j直接引用所述医疗文献i的情况下,确定所述医疗文献j与所述医疗文献i的第二评分之间的第一均值,以及所述医疗文献j的发表时间与所述预设时间节点之间的第一时间差,并根据所述第一均值以及所述第一时间差,确定所述医疗文献j对所述医疗文献i的第三评分;
在所述医疗文献j直接引用医疗文献k,且未引用所述医疗文献i,且所述医疗文献k直接引用了所述医疗文献i的情况下,确定所述医疗文献j对所述医疗文献j对医疗文献k的第三评分,以及所述医疗文献k对所述医疗文献i的第三评分,并将所述医疗文献j对所述医疗文献k的第三评分以及所述医疗文献k对所述医疗文献i的第三评分的乘积,作为所述医疗文献j对所述医疗文献i的第三评分。
具体地,上述收发器501可为图4所述的实施例的医疗文献排序装置400的收发单元401,上述处理器502可以为图4所述的实施例的医疗文献排序装置400的处理单元402。
本申请中的医疗文献排序装置可以包括智能手机(如Android手机、iOS手机、Windows Phone手机等)、平板电脑、掌上电脑、笔记本电脑、移动互联网设备MID(Mobile Internet Devices,简称:MID)或穿戴式设备等。上述医疗文献排序装置仅是举例,而非穷举,包含但不限于上述医疗文献排序装置。在实际应用中,上述医疗文献排序装置还可以包括:智能车载终端、计算机设备等。
本申请实施例还提供一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行以实现如上述方法实施例中记载的任何一种医疗文献排序方法的部分或全部步骤。
可选的,本申请涉及的存储介质如计算机可读存储介质可以是非易失性的,也可以是易失性的。
本申请实施例还提供一种计算机程序产品,所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质,所述计算机程序可操作来使计算机执行如上述方法实施例中记载的任何一种医疗文献排序方法的部分或全部步骤。
需要说明的是,对于前述的各方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本申请并不受所描述的动作顺序的限制,因为依据本申请,某些步骤可以采用其他顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于可选实施例,所涉及的动作和模块并不一定是本申请所必须的。
在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述的部分,可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中,应该理解到,所揭露的装置,可通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件程序模块的形式实现。
所述集成的单元如果以软件程序模块的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储器中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储器中,包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储器包括:U盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成,该程序可以存储于一计算机可读存储器中,存储器可以包 括:闪存盘、只读存储器(英文:Read-Only Memory,简称:ROM)、随机存取器(英文:Random Access Memory,简称:RAM)、磁盘或光盘等。
以上对本申请实施例进行了详细介绍,本文中应用了具体个例对本申请的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本申请的方法及其核心思想;同时,对于本领域的一般技术人员,依据本申请的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本申请的限制。

Claims (20)

  1. 一种医疗文献排序方法,包括:
    获取多篇医疗文献之间的引用关系以及所述多篇医疗文献中每篇医疗文献的发表时间;
    根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图;
    根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分;
    根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分;
    根据所述每篇医疗文献在所述预设时间节点下的目标评分,对所述多篇医疗文献进行排序。
  2. 根据权利要求1所述的方法,其中,所述根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图,包括:
    根据所述多篇医疗文献中篇医疗文献之间的引用关系以及医疗文献i的发表时间,确定所述多篇医疗文献中与所述医疗文献对应的目标医疗文献,其中,所述医疗文献i为所述多篇医疗文献中的任意一篇医疗文献,所述目标医疗文献为所述多篇医疗文献中引用所述医疗文献i的医疗文献;
    创建从所述所述医疗文献i到所述目标医疗文献的有向路径,以及将所述多篇医疗文献中除所述目标医疗文献之外的医疗文献作为孤立节点,得到所述多篇医疗文献在预设时间节点下的有向图。
  3. 根据权利要求1所述的方法,其中,所述根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分,包括:
    根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献对应的转移矩阵;
    根据所述多篇医疗文献对应的转移矩阵以及所述多篇医疗文献的数量,确定所述多篇医疗文献中每篇医疗文献的第一评分。
  4. 根据权利要求1-3中任一项所述的方法,其中,所述根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分,包括:
    对所述多篇医疗文献的第一评分进行归一化,得到所述每篇医疗文献对应的第二评分;
    根据所述有向图以及所述每篇医疗文献对应的第二评分,得到医疗文献i对应的目标评分,所述医疗文献i为所述多篇医疗文献中的任意一篇医疗文献。
  5. 根据权利要求4所述的方法,其中,所述根据所述有向图以及所述每篇医疗文献对应的第二评分,得到医疗文献i对应的目标评分,包括:
    根据所述有向图以及每篇医疗文献的第二评分,确定所述多篇医疗文献中除所述医疗文献i之外的其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分;
    将所述其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分以及所述医疗文献i的第二评分进行求和,得到所述医疗文献i对应的目标评分。
  6. 根据权利要求5所述的方法,其中,所述根据所述有向图以及每篇医疗文献的第二评分,确定所述多篇医疗文献中除所述医疗文献i之外的其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分,包括:
    根据所述有向图,确定所述其他医疗文献中引用了所述医疗文献i的医疗文献以及未引用所述医疗文献i的医疗文献(即有向图中的孤立节点),其中,所述引用了所述医疗文献i的医疗文献包括直接引用所述医疗文献i和间接引用所述医疗文献i;
    根据医疗文献j的第二评分和发表时间、所述医疗文献i的第二评分以及所述预设时间 节点,确定所述医疗文献j对该医疗文献i的第三评分,其中,所述医疗文献j为所述引用了所述医疗文献i中的任意一篇医疗文献,并确定所述未引用医疗文献i的医疗文献对所述医疗文献i的第三评分为0。
  7. 根据权利要求6所述的方法,其中,所述根据医疗文献j的第二评分和发表时间、所述医疗文献i的第二评分以及所述预设时间节点,确定所述医疗文献j对该医疗文献i的第三评分,包括:
    在所述医疗文献j直接引用所述医疗文献i的情况下,确定所述医疗文献j与所述医疗文献i的第二评分之间的第一均值,以及所述医疗文献j的发表时间与所述预设时间节点之间的第一时间差,并根据所述第一均值以及所述第一时间差,确定所述医疗文献j对所述医疗文献i的第三评分;
    在所述医疗文献j直接引用医疗文献k,且未引用所述医疗文献i,且所述医疗文献k直接引用了所述医疗文献i的情况下,确定所述医疗文献j对所述医疗文献j对医疗文献k的第三评分,以及所述医疗文献k对所述医疗文献i的第三评分,并将所述医疗文献j对所述医疗文献k的第三评分以及所述医疗文献k对所述医疗文献i的第三评分的乘积,作为所述医疗文献j对所述医疗文献i的第三评分。
  8. 一种医疗文献排序装置,包括:
    收发单元,用于获取多篇医疗文献之间的引用关系以及所述多篇医疗文献中每篇医疗文献的发表时间;
    处理单元,用于根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图;
    所述处理单元,还用于根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分;
    所述处理单元,还用于根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分;
    所述处理单元,还用于根据所述每篇医疗文献在所述预设时间节点下的目标评分,对所述多篇医疗文献进行排序。
  9. 一种电子设备,包括:处理器,所述处理器与存储器相连,所述存储器用于存储计算机程序,所述处理器用于执行所述存储器中存储的计算机程序,以使得所述电子设备执行以下方法:
    获取多篇医疗文献之间的引用关系以及所述多篇医疗文献中每篇医疗文献的发表时间;
    根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图;
    根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分;
    根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分;
    根据所述每篇医疗文献在所述预设时间节点下的目标评分,对所述多篇医疗文献进行排序。
  10. 根据权利要求9所述的电子设备,其中,所述根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图时,具体执行:
    根据所述多篇医疗文献中篇医疗文献之间的引用关系以及医疗文献i的发表时间,确定所述多篇医疗文献中与所述医疗文献对应的目标医疗文献,其中,所述医疗文献i为所述多篇医疗文献中的任意一篇医疗文献,所述目标医疗文献为所述多篇医疗文献中引用所 述医疗文献i的医疗文献;
    创建从所述所述医疗文献i到所述目标医疗文献的有向路径,以及将所述多篇医疗文献中除所述目标医疗文献之外的医疗文献作为孤立节点,得到所述多篇医疗文献在预设时间节点下的有向图。
  11. 根据权利要求9所述的电子设备,其中,所述根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分时,具体执行:
    根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献对应的转移矩阵;
    根据所述多篇医疗文献对应的转移矩阵以及所述多篇医疗文献的数量,确定所述多篇医疗文献中每篇医疗文献的第一评分。
  12. 根据权利要求9-11中任一项所述的电子设备,其中,所述根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分时,具体执行:
    对所述多篇医疗文献的第一评分进行归一化,得到所述每篇医疗文献对应的第二评分;
    根据所述有向图以及所述每篇医疗文献对应的第二评分,得到医疗文献i对应的目标评分,所述医疗文献i为所述多篇医疗文献中的任意一篇医疗文献。
  13. 根据权利要求12所述的电子设备,其中,所述根据所述有向图以及所述每篇医疗文献对应的第二评分,得到医疗文献i对应的目标评分时,具体执行:
    根据所述有向图以及每篇医疗文献的第二评分,确定所述多篇医疗文献中除所述医疗文献i之外的其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分;
    将所述其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分以及所述医疗文献i的第二评分进行求和,得到所述医疗文献i对应的目标评分。
  14. 根据权利要求13所述的电子设备,其中,所述根据所述有向图以及每篇医疗文献的第二评分,确定所述多篇医疗文献中除所述医疗文献i之外的其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分时,具体执行:
    根据所述有向图,确定所述其他医疗文献中引用了所述医疗文献i的医疗文献以及未引用所述医疗文献i的医疗文献(即有向图中的孤立节点),其中,所述引用了所述医疗文献i的医疗文献包括直接引用所述医疗文献i和间接引用所述医疗文献i;
    根据医疗文献j的第二评分和发表时间、所述医疗文献i的第二评分以及所述预设时间节点,确定所述医疗文献j对该医疗文献i的第三评分,其中,所述医疗文献j为所述引用了所述医疗文献i中的任意一篇医疗文献,并确定所述未引用医疗文献i的医疗文献对所述医疗文献i的第三评分为0。
  15. 一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行以实现以下方法:
    获取多篇医疗文献之间的引用关系以及所述多篇医疗文献中每篇医疗文献的发表时间;
    根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下的有向图;
    根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分;
    根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分;
    根据所述每篇医疗文献在所述预设时间节点下的目标评分,对所述多篇医疗文献进行排序。
  16. 根据权利要求15所述的计算机可读存储介质,其中,所述根据所述多篇医疗文献的引用关系以及所述每篇医疗文献的发表时间,确定所述多篇医疗文献在预设时间节点下 的有向图时,具体实现:
    根据所述多篇医疗文献中篇医疗文献之间的引用关系以及医疗文献i的发表时间,确定所述多篇医疗文献中与所述医疗文献对应的目标医疗文献,其中,所述医疗文献i为所述多篇医疗文献中的任意一篇医疗文献,所述目标医疗文献为所述多篇医疗文献中引用所述医疗文献i的医疗文献;
    创建从所述所述医疗文献i到所述目标医疗文献的有向路径,以及将所述多篇医疗文献中除所述目标医疗文献之外的医疗文献作为孤立节点,得到所述多篇医疗文献在预设时间节点下的有向图。
  17. 根据权利要求15所述的计算机可读存储介质,其中,所述根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献中每篇医疗文献的第一评分时,具体实现:
    根据所述多篇医疗文献对应的有向图,确定所述多篇医疗文献对应的转移矩阵;
    根据所述多篇医疗文献对应的转移矩阵以及所述多篇医疗文献的数量,确定所述多篇医疗文献中每篇医疗文献的第一评分。
  18. 根据权利要求15-17中任一项所述的计算机可读存储介质,其中,所述根据所述多篇医疗文献对应的有向图以及所述每篇医疗文献的第一评分,确定所述每篇医疗文献在所述预设时间节点下的目标评分时,具体实现:
    对所述多篇医疗文献的第一评分进行归一化,得到所述每篇医疗文献对应的第二评分;
    根据所述有向图以及所述每篇医疗文献对应的第二评分,得到医疗文献i对应的目标评分,所述医疗文献i为所述多篇医疗文献中的任意一篇医疗文献。
  19. 根据权利要求18所述的计算机可读存储介质,其中,所述根据所述有向图以及所述每篇医疗文献对应的第二评分,得到医疗文献i对应的目标评分时,具体实现:
    根据所述有向图以及每篇医疗文献的第二评分,确定所述多篇医疗文献中除所述医疗文献i之外的其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分;
    将所述其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分以及所述医疗文献i的第二评分进行求和,得到所述医疗文献i对应的目标评分。
  20. 根据权利要求19所述的计算机可读存储介质,其中,所述根据所述有向图以及每篇医疗文献的第二评分,确定所述多篇医疗文献中除所述医疗文献i之外的其他医疗文献中每篇医疗文献对所述医疗文献i的第三评分时,具体实现:
    根据所述有向图,确定所述其他医疗文献中引用了所述医疗文献i的医疗文献以及未引用所述医疗文献i的医疗文献(即有向图中的孤立节点),其中,所述引用了所述医疗文献i的医疗文献包括直接引用所述医疗文献i和间接引用所述医疗文献i;
    根据医疗文献j的第二评分和发表时间、所述医疗文献i的第二评分以及所述预设时间节点,确定所述医疗文献j对该医疗文献i的第三评分,其中,所述医疗文献j为所述引用了所述医疗文献i中的任意一篇医疗文献,并确定所述未引用医疗文献i的医疗文献对所述医疗文献i的第三评分为0。
PCT/CN2020/131808 2020-10-23 2020-11-26 医疗文献排序方法、装置、电子设备及存储介质 WO2021179687A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011153172.4A CN112286988B (zh) 2020-10-23 2020-10-23 医疗文献排序方法、装置、电子设备及存储介质
CN202011153172.4 2020-10-23

Publications (1)

Publication Number Publication Date
WO2021179687A1 true WO2021179687A1 (zh) 2021-09-16

Family

ID=74424919

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/131808 WO2021179687A1 (zh) 2020-10-23 2020-11-26 医疗文献排序方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN112286988B (zh)
WO (1) WO2021179687A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114510584A (zh) * 2022-04-19 2022-05-17 北京智谱华章科技有限公司 文献识别方法、装置、电子设备以及计算机可读存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101887460A (zh) * 2010-07-14 2010-11-17 北京大学 一种文献质量评估方法及应用
CN105589948A (zh) * 2015-12-18 2016-05-18 重庆邮电大学 一种文献引用网络可视化及文献推荐方法及系统
CN105740452A (zh) * 2016-02-03 2016-07-06 北京工业大学 基于PageRank和时间衰减的科技文献重要度评价方法
CN105740386A (zh) * 2016-01-27 2016-07-06 北京航空航天大学 基于排序集成的论文搜索方法及装置
CN107391659A (zh) * 2017-07-18 2017-11-24 北京工业大学 一种基于信誉度的引文网络学术影响力评价排序方法
US20180211173A1 (en) * 2017-01-24 2018-07-26 International Business Machines Corporation System for evaluating journal articles

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011159646A1 (en) * 2010-06-14 2011-12-22 Topsy Labs, Inc. A system and method for determining quality of cited objects in search results based on the influence of citing subjects
CN109118029B (zh) * 2017-06-22 2022-02-18 腾讯科技(深圳)有限公司 对象排序处理方法、装置、计算机设备和存储介质
US10713310B2 (en) * 2017-11-15 2020-07-14 SAP SE Walldorf Internet of things search and discovery using graph engine
CN109376218B (zh) * 2018-09-14 2020-12-11 大连理工大学 一种基于级联的论文影响力评估方法
CN111198897B (zh) * 2018-11-19 2023-06-13 中国农业大学 科研热点主题分析方法、装置与电子设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101887460A (zh) * 2010-07-14 2010-11-17 北京大学 一种文献质量评估方法及应用
CN105589948A (zh) * 2015-12-18 2016-05-18 重庆邮电大学 一种文献引用网络可视化及文献推荐方法及系统
CN105740386A (zh) * 2016-01-27 2016-07-06 北京航空航天大学 基于排序集成的论文搜索方法及装置
CN105740452A (zh) * 2016-02-03 2016-07-06 北京工业大学 基于PageRank和时间衰减的科技文献重要度评价方法
US20180211173A1 (en) * 2017-01-24 2018-07-26 International Business Machines Corporation System for evaluating journal articles
CN107391659A (zh) * 2017-07-18 2017-11-24 北京工业大学 一种基于信誉度的引文网络学术影响力评价排序方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114510584A (zh) * 2022-04-19 2022-05-17 北京智谱华章科技有限公司 文献识别方法、装置、电子设备以及计算机可读存储介质

Also Published As

Publication number Publication date
CN112286988B (zh) 2023-07-25
CN112286988A (zh) 2021-01-29

Similar Documents

Publication Publication Date Title
WO2022126971A1 (zh) 基于密度的文本聚类方法、装置、设备及存储介质
TWI677828B (zh) 基於資料源的業務客製裝置、方法及電腦可讀儲存介質
WO2021143267A1 (zh) 基于图像检测的细粒度分类模型处理方法、及其相关设备
US11288573B2 (en) Method and system for training and neural network models for large number of discrete features for information rertieval
WO2022142027A1 (zh) 基于知识图谱的模糊匹配方法、装置、计算机设备和存储介质
CN107305637B (zh) 基于K-Means算法的数据聚类方法和装置
US11645695B2 (en) Computing personalized recommendations by modeling interactions as a bipartite graph
WO2021189920A1 (zh) 医疗文献簇的主题确定方法、装置、电子设备及存储介质
CN108009437B (zh) 数据发布方法和装置及终端
CN110442733A (zh) 一种主题生成方法、装置和设备及介质
CN113722438A (zh) 基于句向量模型的句向量生成方法、装置及计算机设备
WO2021184547A1 (zh) 对话机器人意图语料生成方法、装置、介质及电子设备
CN112307190A (zh) 医学文献排序方法、装置、电子设备及存储介质
WO2021179687A1 (zh) 医疗文献排序方法、装置、电子设备及存储介质
CN108763961A (zh) 一种基于大数据的隐私数据分级方法和装置
CN112966054A (zh) 基于企业图谱节点间关系的族群划分方法和计算机设备
CN110335061B (zh) 交易模式画像建立方法、装置、介质及电子设备
CN111641517A (zh) 同质网络的社群划分方法、装置、计算机设备和存储介质
WO2024109859A1 (zh) 一种肿瘤基因突变分类方法、装置、电子设备及存储介质
Sun Personalized music recommendation algorithm based on spark platform
WO2021179688A1 (zh) 医学文献检索方法、装置、电子设备及存储介质
KR102012564B1 (ko) 주식 정보 제공 방법
CN113961720A (zh) 预测实体关系的方法和关系预测模型的训练方法、装置
CN108319606A (zh) 专业数据库的构建方法和装置
CN110442674A (zh) 标签传播的聚类方法、终端设备、存储介质及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20924856

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20924856

Country of ref document: EP

Kind code of ref document: A1