Search

CN-121980020-A - Evaluation candidate retrieval method and device, computer readable medium and electronic equipment

CN121980020ACN 121980020 ACN121980020 ACN 121980020ACN-121980020-A

Abstract

The disclosure provides a method and a device for searching a review candidate, a computer readable medium and electronic equipment, and relates to the technical field of information searching. The method comprises the steps of obtaining a cross subject list set for documents to be reviewed, adding experts with subject marks in a preset expert database comprising all subject marks in the main list into a review candidate set when the main list is a non-empty list, adding experts with subject marks matched with any subject mark in a subsidiary list into the review candidate set when the main list is an empty list, and outputting the review candidate set to a user interface. The method and the device can search the expert which is more suitable for cross subject literature review by setting the cross subject list, and meanwhile, the main list and the auxiliary list can be set to distinguish the cross subject requirements which are required to be met from the cross subject requirements which can be met, so that the cross subject list is flexibly set according to the review requirements, and the problems of mismatching of a reviewer, inaccurate review results and the like are avoided.

Inventors

  • TAN BAOJUN
  • LI GUANGMENG
  • MA WENCHUANG
  • Yin Haicang

Assignees

  • 普科未来(北京)智能科技有限公司

Dates

Publication Date
20260505
Application Date
20260106

Claims (12)

  1. 1. A method of evaluating candidate retrieval comprising: Acquiring a cross discipline list set for documents to be reviewed, wherein the cross discipline list comprises a main list and a secondary list, and at least one list comprises at least 2 discipline marks; When the main list is a non-empty list, adding experts with discipline marks in a preset expert database and all discipline marks in the main list into a review candidate set; When the main list is an empty list, adding an expert with a subject mark matched with any subject mark in the auxiliary list into a review candidate set in the preset expert database; The set of review candidates is output to a user interface.
  2. 2. The method of claim 1, wherein prior to said outputting the set of review candidates to a user interface, the method further comprises: Counting the number of matching of the subject marks corresponding to each expert in the evaluation candidate set and each subject mark in the auxiliary list to obtain the matching number; And eliminating the experts with the matching quantity smaller than a preset matching threshold value from the evaluation candidate set.
  3. 3. The method of claim 1 or 2, wherein prior to said outputting the set of review candidates to a user interface, the method further comprises: Respectively calculating the similarity between the research data of each expert in the evaluation candidate set and the document to be evaluated; And eliminating the expert with the similarity smaller than a preset similarity threshold from the evaluation candidate set.
  4. 4. A method according to claim 3, wherein said separately calculating the similarity between the study data of each expert in the set of evaluation candidates and the document to be evaluated comprises: Extracting professional feature vectors corresponding to each expert based on the research data of each expert; And respectively calculating the similarity between the professional feature vector corresponding to each expert and the document feature vector corresponding to the document to be reviewed.
  5. 5. The method of claim 3, wherein prior to said culling the expert having the similarity less than a preset similarity threshold from the set of review candidates, the method further comprises: Counting the number of matching of the subject marks corresponding to each expert in the evaluation candidate and each subject mark in the auxiliary list to obtain the matching number; And adjusting the similarity based on the matching quantity.
  6. 6. The method of claim 1, wherein prior to said outputting the set of review candidates to a user interface, the method further comprises: based on whether each expert in the evaluation candidate set belongs to the interdisciplinary expert, carrying out descending order sorting to obtain a first sequence; In the experts with the same sequencing result in the first sequence, performing descending sequencing based on the number of subject marks corresponding to each expert and matching the subject marks in the auxiliary list to obtain a second sequence; among the experts with the same sequencing results in the second sequence, sequencing based on the similarity between the research data of each expert and the documents to be reviewed to obtain a third sequence; And outputting the third sequence as a candidate sequence for display on a user interface based on the candidate sequence.
  7. 7. The method of claim 6, wherein the ranking based on similarity between each expert's study data and the document to be reviewed comprises: and sorting according to the descending order of similarity between the research data of each expert and the documents to be reviewed.
  8. 8. The method of claim 6 or 7, wherein the ranking based on similarity between each expert's study data and the document to be reviewed comprises: Acquiring a preset similarity grouping value; Aiming at the experts with the same sequencing result in each group in the second sequence, dividing the experts into at least 2 groups according to the preset similarity grouping value and the similarity corresponding to each expert; The experts within each group are randomly ordered.
  9. 9. The method according to claim 1, wherein the method further comprises: When a target reviewer accepts the review of the document to be reviewed, acquiring key content data corresponding to the document to be reviewed; and updating the data of the target reviewer in the preset expert database based on the key content data.
  10. 10. A review candidate retrieval device, comprising: The system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring a cross discipline list set for a document to be reviewed, the cross discipline list comprises a main list and a secondary list, and at least one list comprises at least 2 discipline marks; the data retrieval module is used for adding the expert with the discipline marks in the preset expert database comprising all discipline marks in the main list into the review candidate set when the main list is a non-empty list; And when the main list is an empty list, adding an expert with a subject mark matched with any subject mark in the auxiliary list into a review candidate set in the preset expert database; And the data output module is used for outputting the evaluation candidate set to a user interface.
  11. 11. A computer readable medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the method according to any one of claims 1 to 9.
  12. 12. An electronic device, comprising: The apparatus of any one of claims 1 to 9, wherein the processor is configured to perform the method of any one of claims 1 to 9 via execution of the executable instructions.

Description

Evaluation candidate retrieval method and device, computer readable medium and electronic equipment Technical Field The present disclosure relates to the field of information retrieval technology, and in particular, to a method for retrieving a review candidate, a device for retrieving a review candidate, a computer-readable medium, and an electronic apparatus. Background With the deep implementation of the national innovation driving development strategy, the technological innovation and the industrial transformation accelerate the evolution, and the subject cross-fusion becomes a main source of the technological development at the front. To cope with this trend, the education department formally sets up cross discipline categories aimed at systematically culturing high-level compound talents with a multidisciplinary knowledge background. In this context, the proliferation of interdisciplinary literature produced by universities, scientific research institutions and industry has presented unprecedented challenges to the literature review and evaluation mechanisms. Disclosure of Invention The invention aims to provide a review candidate retrieval method, a review candidate retrieval device, a computer readable medium and electronic equipment, and further solves the problems that the conventional peer review is only in accordance with a single subject to cause mismatching of a review person and inaccurate review results. According to the first aspect of the disclosure, a search method for a review candidate is provided, which comprises the steps of obtaining a cross subject list set for a document to be reviewed, wherein the cross subject list comprises a main list and a secondary list, at least one list comprises at least 2 subject marks, when the main list is a non-empty list, the subjects with the subject marks in a preset subject library comprising all subject marks in the main list are added into a review candidate set, when the main list is an empty list, the subjects with the subject marks matched with any subject mark in the secondary list in the preset subject library are added into the review candidate set, and the review candidate set is output to a user interface. According to a second aspect of the disclosure, a review candidate retrieval device is provided, and the review candidate retrieval device comprises a data acquisition module, a data output module and a data output module, wherein the data acquisition module is used for acquiring a cross subject list set for a document to be reviewed, the cross subject list comprises a main list and a subsidiary list, at least one of the main list and the subsidiary list comprises at least 2 subject marks, the data retrieval module is used for adding an expert with the subject marks in a preset expert database comprising all subject marks in the main list into a review candidate set when the main list is a non-empty list, and adding an expert with the subject marks matched with any subject mark in the subsidiary list into the review candidate set when the main list is an empty list, and the data output module is used for outputting the review candidate set to a user interface. According to a third aspect of the present disclosure, there is provided a computer readable medium having stored thereon a computer program which, when executed by a processor, implements the method described above. According to a fourth aspect of the present disclosure, there is provided an electronic device characterized by comprising a processor, and a memory for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the above-described method. According to the review candidate retrieval method provided by the embodiment of the disclosure, through setting the cross discipline list, the expert which is more suitable for cross discipline documents to be reviewed can be retrieved according to at least 2 discipline marks in the discipline list, meanwhile, through the design of the main list and the auxiliary list, the cross discipline requirements which must be met and the cross discipline requirements which can be met can be distinguished, so that the review candidate retrieval method is flexibly set according to the review requirements, and the problems that the conventional peer review is not matched with the reviewer caused by retrieving a target reviewer according to a single discipline, the review result is not accurate and the like are avoided. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. Drawings The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordi