Evaluation parameter determination method and device, electronic equipment and storage medium

Abstract

The invention provides an evaluation parameter determination method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining a to-be-predicted document; determining feature information of the to-be-predicted document; determining a target influence feature based on the feature information; and inputting the target influence feature into a pre-established neural network model to determine the number of times of citation of the to-be-predicted document. The accuracy of the predicted number of times of citation can be improved.

Description

Technical Field

[0001] This application relates to the field of scientific and technological information technology, and particularly to a method, device, electronic device and storage medium for determining evaluation parameters. Background Art

[0002] With the rapid development of scientific and technological strength, the scientific papers published by Chinese scholars have been in the leading position in the world in terms of both quality and quantity. However, the development speed of scientific and technological journals cannot fully match it, and there is a lack of high-level journals with international influence and popularity.

[0003] The number of citations of a paper is one of the important indicators to measure the quality and dissemination ability of the paper, and it is also an important indicator to evaluate the quality and influence of a journal. Therefore, increasing the number of high-quality papers is the top priority for enhancing the influence of journals and building high-level journals. In-depth analysis of the citation characteristics of highly cited papers and zero-cited papers and evaluation of the citation characteristics of papers have multiple meanings for journal management. First, analyzing the characteristics of highly cited papers helps to predict the research hotspots and development trends of journals and provides guidance for journal manuscript solicitation and selection; second, papers with high citation potential cannot be determined through simple formal review. Accurate prediction through the citation characteristics of papers can provide important reference for selecting papers with high citation potential and avoiding publishing zero-citation papers with poor influence; finally, as a "green leaf" profession, editors' understanding of the characteristics of highly cited and zero-cited papers helps to improve the dissemination potential of manuscripts through editing.

[0004] Over the years, a large number of studies related to the citation characteristics of papers have been carried out at home and abroad. Generally speaking, there are the following two characteristics: 1) Related research mainly focuses on the research of the characteristics of highly cited papers, and relatively little in-depth exploration of the characteristics of zero-cited papers, and the overall understanding of paper citation needs to be comprehensively structured; 2) The analysis of paper citation characteristics presents a combination of qualitative and quantitative analysis, resulting in inaccurate analysis of paper citation characteristics. Summary of the Invention

[0005] In view of the above problems, this application provides a method, device, electronic device and storage medium for determining evaluation parameters, which can improve the accuracy of the predicted number of citations of papers.

[0006] This application provides a method for determining evaluation parameters, including:

[0007] Obtain a document to be predicted;

[0008] Determine the characteristic information of the document to be predicted;

[0009] Determine the target influence characteristics based on the characteristic information;

[0010] Input the target impact feature into a pre-established neural network model to determine the citation count of the document to be predicted.

[0011] In some embodiments, the method further includes:

[0012] Obtain a sample document and the sample citation count of the sample document;

[0013] Determine the sample feature information of the sample document;

[0014] Determine the target sample impact feature based on the sample feature information;

[0015] Generate training data based on the sample citation count corresponding to the target sample impact feature;

[0016] Establish the neural network model based on the training data.

[0017] In some embodiments, the sample document includes: a first sample document and a second sample document. The sample citation count of the first sample document is greater than a first citation count threshold, and the sample citation count of the second sample document is less than a second citation count threshold. The first citation count threshold is greater than the second citation count threshold.

[0018] In some embodiments, determining the target impact feature based on the feature information includes:

[0019] Input the feature information into a pre-established feature correlation model to determine the weight of the feature;

[0020] Determine the target impact feature based on the weight of the feature.

[0021] In some embodiments, the method further includes:

[0022] Establish the feature correlation model based on a machine learning algorithm, where the machine learning algorithm includes: one of a logistic regression algorithm and a decision tree algorithm.

[0023] In some embodiments, the method further includes:

[0024] Input the citation count into a citation feature classification model to determine the evaluation category of the document to be predicted;

[0025] Output the evaluation category.

[0026] In some embodiments, the method further includes:

[0027] Determine a manuscript selection strategy based on the target impact feature and the evaluation category;

[0028] Output the manuscript selection strategy.

[0029] An embodiment of the present application provides an electronic device, including a memory and a processor. A computer program is stored on the memory. When the computer program is executed by the processor, the method for determining the evaluation parameter described in any one of the above is executed.

[0030] An embodiment of the present application provides a storage medium. The computer program stored on the storage medium can be executed by one or more processors and can be used to implement the method for determining the evaluation parameter described in any one of the above.

[0031] A method, device, electronic device, and storage medium for determining an evaluation parameter provided by the present application can improve the accuracy of the predicted citation times by obtaining a document to be predicted, determining the feature information of the document to be predicted, determining a target influencing feature based on the feature information, and inputting the target influencing feature into a pre-established neural network model to determine the citation times of the document to be predicted. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Hereinafter, the present application will be described in more detail based on embodiments with reference to the drawings.

[0033] Figure 1 It is a schematic flowchart of the implementation of a method for determining an evaluation parameter provided by an embodiment of the present application;

[0034] Figure 2 It is a schematic flowchart of the implementation of another method for determining an evaluation parameter provided by an embodiment of the present application;

[0035] Figure 3 It is a schematic diagram of the composition structure of the electronic device provided by an embodiment of the present application.

[0036] In the drawings, the same components are denoted by the same reference numerals, and the drawings are not drawn to actual scale. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] In order to make the objectives, technical solutions, and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings. The described embodiments should not be construed as limiting the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0038] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict.

[0039] If similar descriptions such as "first / second / third" appear in the application documents, the following description shall be added. In the following description, the terms "first / second / third" involved are only used to distinguish similar objects and do not represent a specific order for the objects. Understandably, "first / second / third" can be interchanged in a specific order or sequence when permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0041] Based on the problems existing in the related art, embodiments of the present application provide a method for determining evaluation parameters. The method is applied to an electronic device, and the electronic device can be a computer, a mobile terminal, etc. The functions implemented by the method for determining evaluation parameters provided by the embodiments of the present application can be realized by a processor of the electronic device calling program code, where the program code can be stored in a computer storage medium.

[0042] Embodiments of the present application provide a method for determining evaluation parameters. Figure 1 It is a schematic flowchart of the implementation of a method for determining evaluation parameters provided by embodiments of the present application, as Figure 1 shown, including:

[0043] Step S101, obtain a document to be predicted.

[0044] In the embodiments of the present application, the document to be predicted can be a paper, the paper can be a journal paper, and the format of the document to be predicted can be PDF format, word format.

[0045] In the embodiments of the present application, the electronic device can open the document to be predicted to obtain the document to be predicted. In some embodiments, the electronic device can load the document to be predicted to obtain the document to be predicted.

[0046] In some embodiments, the electronic device can obtain the document to be predicted through an input device. In some embodiments, the electronic device can obtain the document to be predicted from the network through the Internet.

[0047] In the embodiments of the present application, the document to be predicted is a document for which the number of citations to be determined.

[0048] Step S102, determine the characteristic information of the document to be predicted.

[0049] In the embodiments of the present application, the characteristic information may include: formal characteristics, content characteristics, etc.

[0050] In the embodiments of the present application, the document to be predicted can be input into the feature extraction model to determine the feature information of the document to be predicted.

[0051] In the embodiments of the present application, the feature extraction model can be established through a first sample data set. The first sample data set includes: first sample documents and first sample feature information. The neural network model can be trained with the first sample documents as the input and the first sample feature information as the output to obtain the feature extraction model.

[0052] In some embodiments, after the feature information is determined, the feature information can be processed, including: denoising processing.

[0053] Step S103: Determine the target influencing features based on the feature information.

[0054] In the embodiments of the present application, the target influencing features can be regarded as the feature information that has a greater impact on the prediction of the document to be predicted.

[0055] In the embodiments of the present application, the target influencing features may include one or more of: formal features, content features.

[0056] In some embodiments, step S103 can be implemented through the following steps:

[0057] Step S1031: Input the feature information into a pre-established feature correlation model to determine the weights of the features.

[0058] In the embodiments of the present application, the feature correlation model can be established based on a machine learning algorithm, where the machine learning algorithm includes: one of a logistic regression algorithm and a decision tree algorithm. In some embodiments, the logistic regression algorithm can be a principal factor regression algorithm.

[0059] In the embodiments of the present application, the weights of the features can be represented by numerical values. The larger the numerical value, the greater the weight. In some embodiments, the weights can also be represented by important, secondary, negligible, etc.

[0060] Exemplarily, by inputting the feature information into a pre-established feature correlation model, information such as whether the feature is an important feature, a secondary feature, or a negligible feature can be determined.

[0061] Step S1032: Determine the target influencing features based on the weights of the influencing factors.

[0062] In the embodiments of the present application, a weight threshold for feature selection can be set, and then the target influencing features can be determined based on the weight threshold.

[0063] In the embodiments of the present application, the target influencing feature may be a preferred feature, a feature with a relatively high relevance to the document, etc.

[0064] Step S104: Input the target influencing feature into a pre-established neural network model to determine the citation times of the document to be predicted.

[0065] In the embodiments of the present application, the input of the neural network model is the target influencing feature, and the output of the neural network is the citation times.

[0066] A method for determining an evaluation parameter provided by the present application includes obtaining a document to be predicted; determining the feature information of the document to be predicted; determining a target influencing feature based on the feature information; inputting the target influencing feature into a pre-established neural network model to determine the citation times of the document to be predicted. By using a neural network model for prediction, the accuracy of the predicted citation times can be improved.

[0067] In some embodiments, before step S104, the method further includes:

[0068] Step S1: Obtain a sample document and the sample citation times of the sample document.

[0069] In the embodiments of the present application, the sample document can be obtained from databases such as CNKI, Ei, and the official website of the journal. The sample document can be a sample paper. The sample document can be a document in recent years. The sample document can be a journal.

[0070] In the embodiments of the present application, the sample citation times may include: 0 times and above.

[0071] Step S2: Determine the sample feature information of the sample document.

[0072] In the embodiments of the present application, the sample feature information may include: formal features, content features, etc.

[0073] In the embodiments of the present application, the document to be predicted can be input into a feature extraction model to determine the sample feature information of the sample document.

[0074] In the embodiments of the present application, a feature extraction model can be established through a first sample data set. The first sample data set includes: a first sample document and sample feature information. A neural network model can be trained with the first sample document as the input and the sample feature information as the output to obtain the feature extraction model.

[0075] Step S3: Determine the target sample influencing feature based on the sample feature information.

[0076] In the embodiments of the present application, the target sample influence feature can be regarded as the feature information that has a greater influence on the prediction of the sample document.

[0077] In the embodiments of the present application, the target influence feature may include one or more of a formal feature and a content feature.

[0078] Step S4: Generate training data based on the number of times the sample corresponding to the target sample influence feature is cited.

[0079] In the embodiments of the present application, the training data may include a training set and a test set.

[0080] Step S5: Establish the neural network model based on the training data.

[0081] In the embodiments of the present application, the data can be trained based on the training set, and the trained neural network can be tested using the test set.

[0082] In some embodiments, the sample document includes a first sample document and a second sample document. The number of times the first sample document is cited is greater than a first citation threshold, and the number of times the second sample document is cited is less than a second citation threshold. The first citation threshold is greater than the second citation threshold.

[0083] In the embodiments of the present application, the first sample document can be regarded as a document with a high citation count, and the second sample document can be a document with zero citations.

[0084] In some embodiments, after step S104, the method further includes:

[0085] Step S105: Input the number of times cited into a citation feature classification model to determine the evaluation category of the document to be predicted.

[0086] In the embodiments of the present application, the evaluation category may include highly cited, zero cited, moderately cited, etc.

[0087] Step S106: Output the evaluation category.

[0088] In the embodiments of the present application, the electronic device can be communicatively connected to a display device, and the evaluation category can be displayed through the display device.

[0089] In the embodiments of the present application, users can analyze the features of highly cited papers based on the evaluation category, which helps to predict the research hotspots and development trends of journals and provides guidance for journal manuscript solicitation and selection.

[0090] In some embodiments, after step S105, the method further includes:

[0091] Step S107: Determine a manuscript selection strategy based on the target impact feature and the evaluation category.

[0092] In the embodiments of the present application, a correspondence relationship can be established between the impact feature, the evaluation category, and the manuscript selection strategy. After determining the target impact feature and the evaluation category, the manuscript selection strategy can be output based on this correspondence relationship.

[0093] In the embodiments of the present application, the manuscript selection strategy may include: not selecting, suggesting selection, etc.

[0094] Step S108: Output the manuscript selection strategy.

[0095] In the embodiments of the present application, the electronic device can output the manuscript selection strategy through a display device, thereby facilitating the user to select manuscripts.

[0096] Based on the foregoing embodiments, the embodiments of the present application further provide a method for determining evaluation parameters. Taking the periodicals in the oil and gas field as an example, taking the "Three High" papers (highly cited papers, highly downloaded papers, and high PCSI papers) and zero-cited papers in the CNKI Essential Database in the past 5 years as the research objects, an AI algorithm is used to construct a prediction model. Figure 2 It is a schematic flowchart of a method for determining evaluation parameters provided by the embodiments of the present application. As Figure 2 shown, it includes:

[0097] 1. Data collection of influencing factors for "Three High" papers and zero-cited papers, including:

[0098] (1) Induction of characteristic data of "Three High" papers and zero-cited papers.

[0099] Clarify the definitions of "Three High" papers and zero-cited papers, and summarize the influencing factors of the paper citation characteristics in terms of form and content as the basis for data mining.

[0100] (2) Data mining of influencing factors.

[0101] Based on databases such as CNKI, Ei, and the journal official website, select some periodicals in the oil and gas field, and take all the "Three High" papers and zero-cited papers published in the past 5 years as the objects to mine the influencing factor data.

[0102] 2. Research on methods for evaluating and predicting paper citation characteristics, including:

[0103] (1) Intelligent evaluation and optimization of influencing factors.

[0104] Based on the data mining results, optimize the artificial intelligence algorithm, conduct an intelligent evaluation of the correlation between the mined data and the paper citation characteristics, and classify the influencing factors into main factors, secondary factors, and negligible factors.

[0105] (2) Evaluation and prediction model construction of paper citation features.

[0106] Using the optimized parameters as input parameters, the number of citations of the paper as the output parameter, and the data of papers published in journals included in Ei as the learning samples, a machine learning prediction model is constructed. And a paper citation feature classification model is constructed based on the predicted citation frequency of the paper to evaluate the paper citation features (highly cited, zero cited, moderately cited) and predict their possible citation features.

[0107] 3. Research on manuscript selection and editing strategies based on paper citation evaluation, including:

[0108] (1) Feasibility analysis of citation feature judgment method.

[0109] Using the papers published in "Petroleum Drilling Techniques", judge their citation feature categories, and compare the judgment results with the actual citation frequency to verify the feasibility of the citation feature judgment method.

[0110] (2) Manuscript selection strategy and paper editing suggestions (qualitative research analysis is involved).

[0111] Based on the paper citation evaluation method and the key factors determining the citation characteristics of papers, a targeted manuscript selection strategy for improving the dissemination ability of papers is formed, and editing suggestions for improving the dissemination ability of manuscripts are put forward.

[0112] In the embodiments of this application, by forming an AI evaluation model based on paper citation features, the citation features of subsequent submitted manuscripts are predicted, and the key influencing factors affecting the paper citation features are clarified, providing a reference for improving the dissemination ability of papers published in journals.

[0113] In the embodiments of this application, based on databases such as CNKI, Ei, and the journal official website, some journals in the oil and gas field are selected, and the characteristic data of all "three highs" papers and zero-cited papers published in the past 5 years are mined. The subsequent operation steps are as follows: (1) Using machine learning algorithms such as logistic regression and decision tree to establish a correlation model of paper citation features, obtaining main factors, secondary factors and irrelevant factors; (2) Using the optimized parameters as input parameters, the number of citations of the paper as the output parameter, and the data of papers published in journals included in Ei as the learning samples, a machine learning prediction model is constructed. And a paper citation feature classification model is constructed based on the predicted citation frequency of the paper to evaluate the paper citation features (highly cited, zero cited, moderately cited) and predict their possible citation features; (3) In the verification stage, using the papers published in "Petroleum Drilling Techniques", judge their citation feature categories, and compare the judgment results with the actual citation frequency to verify the feasibility of the citation feature judgment method. (4) Based on the paper citation evaluation method and the key factors determining the citation characteristics of papers, a targeted manuscript selection strategy for improving the dissemination ability of papers is formed, and editing suggestions for improving the dissemination ability of manuscripts are put forward.

[0114] Based on the foregoing embodiments, an apparatus for determining evaluation parameters is provided in an embodiment of the present application. Each module included in the apparatus, as well as each unit included in each module, may be implemented by a processor in a computer device; of course, it may also be implemented by specific logic circuits; in the process of implementation, the processor may be a central processing unit (CPU), a microprocessor unit (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0115] An embodiment of the present application provides an apparatus for determining evaluation parameters, and the apparatus for determining evaluation parameters includes:

[0116] An acquisition module, configured to acquire a document to be predicted;

[0117] A first determination module, configured to determine feature information of the document to be predicted;

[0118] A second determination module, configured to determine a target impact feature based on the feature information;

[0119] A third determination module, configured to input the target impact feature into a pre-established neural network model to determine the number of citations of the document to be predicted.

[0120] In some embodiments, the apparatus for determining evaluation parameters is further configured to:

[0121] Acquire a sample document and the sample number of citations of the sample document;

[0122] Determine sample feature information of the sample document;

[0123] Determine a target sample impact feature based on the sample feature information;

[0124] Generate training data based on the sample number of citations corresponding to the target sample impact feature;

[0125] Establish the neural network model based on the training data.

[0126] In some embodiments, the sample document includes: a first sample document and a second sample document. The sample number of citations of the first sample document is greater than a first citation number threshold, and the sample number of citations of the second sample document is less than a second citation number threshold, and the first citation number threshold is greater than the second citation number threshold.

[0127] In some embodiments, determining the target influencing feature based on the feature information includes:

[0128] Inputting the feature information into a pre-established feature correlation model to determine the weight of the feature;

[0129] Determining the target influencing feature based on the weight of the feature.

[0130] In some embodiments, the device for determining the evaluation parameter is further configured to:

[0131] Establish the feature correlation model based on a machine learning algorithm, where the machine learning algorithm includes one of a logistic regression algorithm and a decision tree algorithm.

[0132] In some embodiments, the device for determining the evaluation parameter is further configured to:

[0133] Inputting the number of citations into a citation feature classification model to determine the evaluation category of the document to be predicted;

[0134] Outputting the evaluation category.

[0135] In some embodiments, the device for determining the evaluation parameter is further configured to:

[0136] Determining a manuscript selection strategy based on the target influencing feature and the evaluation category;

[0137] Outputting the manuscript selection strategy.

[0138] An embodiment of the present application provides an electronic device; Figure 3 As shown in the composition structure diagram of the electronic device provided by the embodiment of the present application, Figure 3 As shown, the electronic device 700 includes: a processor 701, at least one communication bus 702, a user interface 703, at least one external communication interface 704, and a memory 705. Among them, the communication bus 702 is configured to realize the connection and communication between these components. Among them, the user interface 703 may include a display screen, and the external communication interface 704 may include a standard wired interface and a wireless interface. The processor 701 is configured to execute a program of the method for determining the evaluation parameter stored in the memory to implement the steps in the method for determining the evaluation parameter provided in the above embodiments.

[0139] In the embodiments of the present application, if the method for determining the above evaluation parameters is implemented in the form of software function modules and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), magnetic disks, or optical discs that can store program codes. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0140] Correspondingly, the embodiments of the present application provide a storage medium on which a computer program is stored, characterized in that when the computer program is executed by a processor, it implements the steps in the method for determining the evaluation parameters provided in the above embodiments.

[0141] The descriptions of the above embodiments of the electronic device and the storage medium are similar to the descriptions of the above method embodiments and have similar beneficial effects to those of the method embodiments. For the technical details not disclosed in the embodiments of the computer device and the storage medium of the present application, please refer to the descriptions of the method embodiments of the present application for understanding.

[0142] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures, or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the "in one embodiment" or "in an embodiment" that appears throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in the various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not mean the order of execution is prior or posterior, and the execution order of each process should be determined by its function and internal logic and should not constitute any limitation to the implementation process of the embodiments of the present application. The serial numbers of the embodiments of the present application above are only for description and do not represent the superiority or inferiority of the embodiments.

[0143] It should be noted that in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, article or device comprising such element.

[0144] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. Additionally, the couplings, direct couplings, or communication connections between the various components shown or discussed can be through some interfaces, and the indirect couplings or communication connections of devices or units can be electrical, mechanical, or in other forms.

[0145] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0146] Furthermore, in each embodiment of this application, the various functional units can all be integrated in one processing unit, or each unit can be separately a unit by itself, or two or more units can be integrated in one unit; the above-mentioned integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0147] Those of ordinary skill in the art can understand that all or part of the steps to implement the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the aforementioned storage medium includes: various media such as removable storage devices, read-only memories (ROMs), magnetic disks, or optical discs that can store program codes.

[0148] Alternatively, if the above integrated units of the present application are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present application essentially or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a controller to execute all or part of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes such as removable storage devices, ROMs, magnetic disks, or optical discs.

[0149] As described above, the above are only the implementation manners of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for determining evaluation parameters, characterized in that, Including: Obtain the document to be predicted; Determine the feature information of the document to be predicted; Determine the target impact feature based on the feature information; Input the target impact feature into a pre-established neural network model to determine the citation times of the document to be predicted.

2. The method according to claim 1, wherein The method further includes: Obtain the sample document and the sample citation times of the sample document; Determine the sample feature information of the sample document; Determine the target sample impact feature based on the sample feature information; Generate training data based on the sample citation times corresponding to the target sample impact feature; Establish the neural network model based on the training data.

3. The method according to claim 2, characterized in that The sample document includes: a first sample document and a second sample document. The sample citation times of the first sample document are greater than a first citation times threshold, and the sample citation times of the second sample document are less than a second citation times threshold. The first citation times threshold is greater than the second citation times threshold.

4. The method according to claim 1, characterized in that Determining the target impact feature based on the feature information includes: Input the feature information into a pre-established feature correlation model to determine the weight of the feature; Determine the target impact feature based on the weight of the feature.

5. The method according to claim 4, characterized in that, The method further includes: Establish the feature correlation model based on a machine learning algorithm, where the machine learning algorithm includes: one of a logistic regression algorithm and a decision tree algorithm.

6. The method according to claim 1, wherein The method further includes: Input the citation times into a citation feature classification model to determine the evaluation category of the document to be predicted; Output the evaluation category.

7. The method according to claim 6, characterized in that The method further includes: Determine a manuscript selection strategy based on the target impact feature and the evaluation category; Output the manuscript selection strategy.

8. An apparatus for determining an evaluation parameter, characterized in that, Including: An acquisition module for obtaining the document to be predicted; A first determination module for determining the feature information of the document to be predicted; A second determination module for determining the target impact feature based on the feature information; A third determination module for inputting the target impact feature into a pre-established neural network model to determine the citation times of the document to be predicted.

9. An electronic device, characterized in that, Including a memory and a processor. A computer program is stored on the memory. When the computer program is executed by the processor, it executes the method for determining the evaluation parameter according to any one of claims 1 to 7.

10. A storage medium, characterized in that, The computer program stored in the storage medium can be executed by one or more processors and can be used to implement the method for determining the evaluation parameter according to any one of claims 1 to 7.

Images