WO2023078414A1

WO2023078414A1 - Related article search method and apparatus, electronic device, and storage medium

Info

Publication number: WO2023078414A1
Application number: PCT/CN2022/129963
Authority: WO
Inventors: 王超超; 王为磊; 屠昶旸; 张济徽
Original assignee: 智慧芽信息科技(苏州)有限公司
Priority date: 2021-11-04
Filing date: 2022-11-04
Publication date: 2023-05-11
Also published as: CN113987128A

Abstract

The present disclosure relates to a related article search method and apparatus, an electronic device, and a storage medium. The method comprises: determining a first article, and determining search information according to the attribute information comprised in the first article; according to the search information of the first article, searching to obtain a first preset number of candidate articles so as to match second name information and second address information in each candidate article according to first name information and first address information comprised in the attribute information of the first article; and finally, determining, according to a matching value of each candidate article and the first article, a second article as an article matching the first article. According to embodiments of the present disclosure, the related candidate articles can be searched according to the attribute information in the first article, and the association with the candidate articles is established according to the name and the address therein so as to obtain the second article having high relevancy, so that the accuracy of the related article search results is improved.

Description

Related article search method, device, electronic device and storage medium

technical field

The present disclosure relates to the field of computer technology, and in particular to a related article search method, device, electronic equipment and storage medium.

Background of the invention

When browsing an article, users usually have a need to browse related articles of the article. The current way to search for related articles based on an article is to search directly based on the author's name. This search method is difficult to search for related articles when the author's name is expressed in different ways, resulting in low accuracy of search results.

Contents of the invention

In view of this, the present disclosure proposes a related article search method, device, electronic device and storage medium, aiming at improving the accuracy of related article search results.

According to a first aspect of the present disclosure, a method for searching related articles is provided, the method comprising:

determining the first article including attribute information, the attribute information including at least first person name information and first address information;

determining search information corresponding to the first article according to the attribute information;

Searching for a first preset number of candidate articles in the article collection according to the search information, each of the candidate articles includes corresponding second name information and second address information;

determining matching values of the first article and each of the candidate articles according to the first name information and first address information and each of the second name information and second address information;

A second article is determined among each of the candidate articles according to the corresponding matching value.

In a possible implementation manner, the first article and each candidate article are determined according to the first name information and first address information and each of the second name information and second address information Matching values for are:

determining a first similarity between each of the candidate articles and the first article according to the first person name information and each of the second person name information;

determining a second degree of similarity between each of the candidate articles and the first article according to the first address information and each of the second address information;

A matching value is determined according to the first similarity and the second similarity corresponding to each candidate article.

In a possible implementation manner, the determining the first similarity between each of the candidate articles and the first article according to the first person name information and each of the second person name information includes:

determining at least one first person's name included in the first person's name information, and at least one second person's name included in each of the second person's name information;

For each of the first person names, determine at least one corresponding synonym information, and a related score corresponding to each of the synonym information;

For each of the second person name information, determine the relationship between each of the second person names included therein and each of the synonym information;

The first similarity is determined according to the sum of correlation scores of synonym information corresponding to each of the second person names.

In a possible implementation manner, for each of the first person names, determining the corresponding at least one synonym information, and the relevant score corresponding to each of the synonym information includes:

determining at least one synonym information corresponding to each of the first person names;

The correlation score corresponding to the synonym information is determined by comparing the difference between each synonym information and the corresponding first person name.

In a possible implementation manner, the determining at least one synonym information corresponding to each of the first person names includes:

Responsive to the first person being an English name, determining an English surname and an English name included in the English name;

The English surname and English name corresponding to each first person's name are respectively input into a plurality of preset name format templates to obtain corresponding synonym information.

In a possible implementation manner, the determining at least one synonym information corresponding to each of the first person names further includes:

In response to the first person name being a Chinese name, performing text conversion on the Chinese name to obtain at least one corresponding synonym information;

Alternatively, determine the Chinese surname and Chinese name included in the Chinese name;

The Chinese surname and Chinese name are converted into English surname and English name by way of pinyin conversion.

In a possible implementation manner, the determining the relevant score by comparing the difference between each synonym information and the corresponding first person name includes:

determining the first score corresponding to each of the first names;

Determining second scores corresponding to multiple preset differences;

In response to at least one difference between the synonym information and the corresponding first person name, determining the difference between the first score corresponding to the first person name and the sum of the second scores corresponding to the differences as the synonym Correlation score corresponding to the information.

In a possible implementation manner, the determining the second similarity between each of the candidate articles and the first article according to the first address information and each of the second address information includes:

Calculate the edit distance between the first address information and each of the second address information to obtain the second similarity between each of the candidate articles and the first article.

In a possible implementation manner, the determining the second article in each of the candidate articles according to the corresponding matching value includes:

A second preset number of candidate articles corresponding to the largest matching value is determined as the second article.

It is determined that the candidate article whose corresponding matching value is greater than a matching threshold is the second article.

In a possible implementation manner, the attribute information further includes article attributes, and determining the search information corresponding to the first article according to the attribute information includes:

Extract feature information from the article attributes, where the feature information includes at least one keyword corresponding to the first article;

The search information corresponding to the first article is determined according to the characteristic information, the first name information and the first address information.

In a possible implementation manner, the first article is a patent document, and the second article is an academic paper.

In a possible implementation manner, the article attribute includes at least one of the abstract of the description, the claims, the description, the patent title, the technical field, the background technology, the content of the invention, and the specific implementation manner, and the first name information Including at least one inventor's name, the first address includes the address of the applicant.

In a possible implementation manner, the second name information includes at least one name of a paper author, and the second address includes an address of an institution to which the paper author belongs.

According to a second aspect of the present disclosure, a related article search device is provided, the device comprising:

The first article determination module is configured to determine a first article including attribute information, the attribute information including at least first name information and first address information;

a search information determination module, configured to determine search information corresponding to the first article according to the attribute information;

An article search module, configured to search for a first preset number of candidate articles in the article collection according to the search information, and each of the candidate articles includes corresponding second name information and second address information;

A data matching module, configured to determine the matching value of the first article and each of the candidate articles according to the first name information and first address information and each of the second name information and second address information;

The second article determining module is configured to determine a second article in each of the candidate articles according to the matching value of each of the candidate articles.

In a possible implementation manner, the data matching module includes:

The first similarity determining submodule is used to determine the first similarity between each of the candidate articles and the first article according to the first person name information and each of the second person name information;

The second similarity determining submodule is used to determine the second similarity between each of the candidate articles and the first article according to the first address information and each of the second address information;

The matching value determination submodule is used to determine the matching value according to the first similarity degree and the second similarity degree corresponding to each of the candidate articles.

In a possible implementation manner, the first similarity determining submodule includes:

a name determination unit, configured to determine at least one first name included in the first name information, and at least one second name included in each of the second name information;

A synonym determining unit, configured to determine at least one corresponding synonym for each of the first person names. word information, and the relevant scores corresponding to each of the synonym information;

A name association unit, configured to determine the relationship between each of the second names and each of the synonym information included in each of the second name information;

The first similarity determination unit is configured to determine the first similarity according to the correlation score sum of the synonym information corresponding to each of the second names.

In a possible implementation manner, the synonym determining unit includes:

a synonym determining subunit, configured to determine at least one synonym information corresponding to each of the first person names;

The relevant score determination subunit is configured to determine the relevant score corresponding to the synonym information by comparing the difference between each synonym information and the corresponding first person name.

In a possible implementation manner, the synonym determining subunit includes:

An English information determining subunit, configured to determine the English surname and English name included in the English name in response to the first person being an English name;

The synonym generation subunit is used to input the English surname and English name corresponding to each first person's name into a plurality of preset name format templates to obtain the corresponding synonym information.

In a possible implementation manner, the synonym determining subunit further includes:

A Chinese information determination subunit, configured to perform text conversion on the Chinese name to obtain at least one corresponding synonym information in response to the first person name being a Chinese name;

The English information conversion subunit is used to convert the Chinese surname and Chinese name into English surname and English name through pinyin conversion.

In a possible implementation manner, the relevant score determination subunit includes:

a first score determination unit, configured to determine the first score corresponding to each of the first names;

The second score determination subunit is used to determine the second scores corresponding to various preset differences;

A correlation score calculation subunit, configured to determine the first score corresponding to the first name and the second score corresponding to each of the differences in response to at least one difference between the synonym information and the corresponding first name. The difference between the sum of the scores is the relevant score corresponding to the synonym information.

In a possible implementation manner, the second similarity determining submodule includes:

The second similarity determination unit is configured to calculate the edit distance between the first address information and each of the second address information, and obtain the second similarity between each of the candidate articles and the first article.

In a possible implementation manner, the second article determination module includes:

The first screening submodule is configured to determine a second preset number of candidate articles with the largest corresponding matching value as the second article.

The second screening submodule is configured to determine that the candidate article whose corresponding matching value is greater than a matching threshold is the second article.

In a possible implementation manner, the attribute information further includes article attributes, and the search information determining module includes:

A feature extraction submodule, configured to extract feature information from the article attributes, where the feature information includes at least one keyword corresponding to the first article;

The search information determination submodule is configured to determine the search information corresponding to the first article according to the feature information, the first name information and the first address information.

According to a third aspect of the present disclosure, an electronic device is provided, including:

processor;

memory for storing processor-executable instructions;

Wherein, the processor is configured to call the instructions stored in the memory to execute the method described in any one of the above.

According to a fourth aspect of the present disclosure, there is provided a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method described in any one of the above items is implemented.

The embodiments of the present disclosure can search for relevant candidate articles through the attribute information in the first article, and establish associations with the candidate articles according to the person's name and address therein to obtain a second article with high correlation, which improves the accuracy of the search results for related articles.

Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings.

Brief description of the drawings

The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the specification, serve to explain the principles of the disclosure.

FIG. 1 shows a flowchart of a method for searching related articles according to an embodiment of the present disclosure;

FIG. 2 shows a schematic diagram of a process of determining search information according to an embodiment of the present disclosure;

Fig. 3 shows a schematic diagram of the process of determining candidate articles according to an embodiment of the present disclosure;

Fig. 4 shows a flow chart of determining the matching value of each candidate article according to an embodiment of the present disclosure;

Fig. 5 shows a schematic diagram of a process of determining synonyms information of a first person's name according to an embodiment of the present disclosure;

Fig. 6 shows a schematic diagram of a device for searching related articles according to an embodiment of the present disclosure;

FIG. 7 shows a schematic diagram of an electronic device according to an embodiment of the present disclosure;

Fig. 8 shows a schematic diagram of another electronic device according to an embodiment of the present disclosure.

Modes of Carrying Out the Invention

Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numbers in the figures indicate functionally identical or similar elements. While various aspects of the embodiments are shown in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as superior or better than other embodiments.

In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific implementation manners. It will be understood by those skilled in the art that the present disclosure may be practiced without some of the specific details. In some instances, methods, means, components and circuits that are well known to those skilled in the art have not been described in detail so as to obscure the gist of the present disclosure.

Fig. 1 shows a flowchart of a method for searching related articles according to an embodiment of the present disclosure. In a possible implementation, the method for searching related articles in this embodiment of the present disclosure may be executed by a terminal device or other processing device, where the terminal device may be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal , cellular phones, cordless phones, personal digital assistants (Personal Digital Assistant, PDA), handheld devices, computing devices, vehicle-mounted devices, wearable devices, etc. Other processing devices may be servers, such as a single server or a server cluster composed of multiple servers. In some possible implementation manners, the method for searching related articles may be implemented by a processor invoking computer-readable instructions stored in a memory.

In an exemplary application scenario, by performing the related article search method of the embodiment of the present disclosure on the predetermined patent documents, after searching for multiple related papers, according to the inventor's name and applicant's address in the patent documents , and the name and address of the author in the paper are associated, and the papers that match the patent documents are accurately associated among the multiple papers obtained by the search.

As shown in Figure 1, the related article search method of the embodiment of the present disclosure includes the following steps:

S10. Determine the first article including attribute information.

In a possible implementation manner, the first article is an article of related articles to be retrieved, which includes attribute information. The first article may be different articles in different application scenarios. For example, when searching for papers related to patents, the first article can be patent documents; when searching for patents related to papers, the first article can be academic papers; when searching for relevant column articles related to news information, the first article can be news.

Optionally, the attribute information is the content in the first article used to characterize the attribute characteristics of the first article, including at least first name information and first address information. Wherein, the first name information is used to represent the name of the relevant person of the first article, and the first address information is used to represent the relevant address of the first article. Further, for different types of first articles, the corresponding related persons and related addresses are different. For example, when the first article is an academic paper, the relevant person can be the author of the paper, and the relevant address is the address of the institution to which the author of the paper belongs. When the first article is a patent document, the relevant person may be the inventor of the patent document, and the relevant address may be the address of the applicant of the patent document. Since the author of the article, the inventor of the patent, and the applicant can be one or more persons, that is, the first name information can include at least one first name related to the first article, and the first address information can include the first article Associated at least one address information.

Further, the attribute information may also include other article attributes used to characterize the characteristics of the first article. For example, when the first article is an academic paper, the article attributes may include the title and abstract of the first article. When the first article is a patent document, the article attribute may include at least one of an abstract, a claim, and a description of the first article. Optionally, when the attribute of the article includes a description, it may include part or complete content of the description, and part of the content of the description may include the patent name, technical field, background technology, content of the invention and specific implementation methods. When the first article is a short story, the article attributes may include a title and a preamble.

Step S20, determining search information corresponding to the first article according to the attribute information.

In a possible implementation manner, corresponding search information is determined according to attribute information in the first article, the search information characterizes article features corresponding to the first article, and is used to search for candidate articles related to the first article.

Optionally, the manner of determining the search information may be to extract characteristic information from article attributes, and the characteristic information includes at least one keyword corresponding to the first article. Then, the search information is determined according to the feature information, the first name information and the first address information. For example, at least one keyword is extracted from the article attributes as characteristic information. When the first article is a patent document, the characteristic information includes abstracts from the description, claims, description, patent title, technical field, background technology, content of the invention and specific implementation A plurality of keywords extracted from at least one method. When the first article is an academic paper, the characteristic information includes a plurality of keywords extracted from at least one of the abstract of the paper, the title of the paper, and the text of the paper. Then, the characteristic information, the first person's name information and the first address information are used together as search words to determine the search information including the above search words.

Fig. 2 shows a schematic diagram of a process of determining search information according to an embodiment of the present disclosure. As shown in FIG. 2 , after determining the attribute information 20 including the article attribute 21 , the first name information 23 and the first address information 22 , the corresponding characteristic information 24 is obtained by extracting keywords in the article attribute 21 . The search information 25 is determined according to the first name information 23 , the first address information 22 and the feature information 24 .

Step S30, searching for a first preset number of candidate articles in the article collection according to the search information.

In a possible implementation manner, the search information corresponding to step S20 is used to search in a preset article collection including a plurality of articles to obtain a first preset number of candidate articles. Optionally, the search method in this embodiment of the present disclosure may be to search the article collection through an ES (elasticsearch) search engine according to the corresponding search information, and obtain a first preset number of candidate articles. The retrieval process of the ES search engine is to split and store the content in the search information, form a corresponding retrieval index, and perform matching retrieval.

Fig. 3 shows a schematic diagram of a process of determining candidate articles according to an embodiment of the present disclosure. As shown in FIG. 3 , after the first article 30 is determined, the search information 31 is determined according to the attribute information therein. Further, according to the search information 31 , N articles are searched in the preset article collection 32 as candidate articles 33 .

Further, each candidate article retrieved includes corresponding second name information and second address information. Wherein, the second name information and the second address information are respectively used to represent the name and address of the relevant person of the candidate article. Further, for different types of candidate articles, the corresponding relevant persons and relevant addresses are also different. For example, when the candidate article is an academic paper, the relevant person can be the author of the paper, and the relevant address is the address of the institution to which the author of the paper belongs. When the candidate article is a patent document, the relevant person can be the inventor of the patent document, and the relevant address can be the address of the applicant of the patent document. Since the author of the article, the inventor of the patent, and the applicant can be one or more persons, that is, the second name information can include at least one second name related to the candidate article, and the second address information can include at least one person related to the candidate article. Address information.

Step S40: Determine the matching value of the first article and each of the candidate articles according to the first name information and first address information and each of the second name information and second address information.

In a possible implementation manner, the matching values of the first article and each candidate article are obtained by establishing associations between the relevant persons and relevant addresses of the first article and the relevant persons and relevant addresses of the candidate articles. That is to say, the matching value between the corresponding candidate article and the first article can be obtained according to the degree of matching between the first name information and the second name information, and the matching degree between the first address information and the second address information.

Fig. 4 shows a flow chart of determining the matching value of each candidate article according to an embodiment of the present disclosure. As shown in Figure 4, in a possible implementation, the process of determining the matching value of each candidate article includes the following steps:

Step S41 , according to the first name information and each second name information, determine the first similarity between each candidate article and the first article.

In a possible implementation, the first similarity between each candidate article and the first article can be obtained by matching according to the first name information of the person related to the first article and the second name information of the person related to each candidate article . That is to say, the first similarity is used to characterize the matching degree of related persons of corresponding articles, for example, the possibility that two articles are the same author, or the possibility that two articles are used to describe events or information related to the same person.

Optionally, the process of determining the first similarity between each candidate article and the first article may also include: determining at least one first name included in the first name information, and at least one name included in each second name information. second name. For each first person's name, at least one corresponding synonym information and a related score corresponding to each synonym information are determined. For each second person's name information, determine the relationship between each second person's name and each synonym information included therein, and determine the first similarity according to the correlation score sum of the synonym information corresponding to each second person's name.

That is to say, the synonym information of each first name in the first name information is determined, and when the second name in the second name information is the same as a synonym information, its corresponding correlation score is determined. The sum of the correlation scores corresponding to the second names in the second person name information is calculated to obtain the first similarity.

In a possible implementation manner, the process of determining the synonym information of each first person name in the first person name information includes: determining at least one synonym information corresponding to each first person name, and comparing each synonym information with the corresponding first person name The difference in names determines the correlation score.

Optionally, since names of people are expressed in different ways in articles of different text types, the synonym information corresponding to the first person name may be determined according to the text type of the first person name, for example, the same English name may be represented in different formats. In a possible implementation, in response to the first person's English name, the English surname and English name included in it may be determined, and the English surname and English name corresponding to each first person's name are respectively input into a plurality of preset Name format template to get the corresponding synonym information.

That is to say, when the first person is an English name, the English name is divided to obtain an English name and an English surname. At the same time, predetermine the possible expression formats of multiple English names, such as "surname · first name", "first name · surname", "first name, surname" and "first letter of first name · surname", etc., and determine each expression format as the corresponding Name format template. Further, input the English name and English surname obtained by dividing the first person's name into each name format template to obtain corresponding synonym information. Optionally, the synonym information includes exactly the same information as the corresponding first person name.

For example, for the first person name "SORIN FABIEN". The English surname "SORIN" and the English name "FABIEN" are obtained by dividing them into the preset multiple name format templates to obtain the corresponding synonym information. When each name format template is "first name·surname", "first name·surname", "first name, last name" and "first letter of first name·surname", the synonym information output respectively is "FABIEN SORIN", "FABIEN·SORIN ", "FABIEN, SORIN" and "FABIEN, S".

Furthermore, in order to meet the situation that the relevant personnel with Chinese names publish other articles with English names in pinyin format, when the text type of the first person’s name is Chinese, the English name can be obtained by converting it into the corresponding pinyin to further determine the corresponding synonym information. That is to say, in response to the first person being named in Chinese, the Chinese surname and Chinese name included therein are determined, and the Chinese surname and Chinese name are converted into English surname and English name through pinyin conversion.

For example, for the first person name "Zhang San". The Chinese surname "Zhang" and the Chinese name "San" are divided into the corresponding English surname "Zhang" and English name "San". Further input the English surname "Zhang" and the English name "San" into a plurality of preset name format templates respectively to obtain corresponding synonym information.

Optionally, at least one corresponding synonym information may also be obtained through text conversion in response to the first person's name in Chinese. For example, convert the first person's name from traditional to traditional, or from traditional to simplified. For example, when the first person's name is "Zhang San" in simplified characters, it can be converted into traditional characters to obtain the synonym information "Zhang San".

In a possible implementation, after determining the synonym information, determining the relevant score according to the difference between each synonym information and the corresponding first person name may include: determining the first score corresponding to each first person name, determining a variety of The preset difference corresponds to the second score, and in response to at least one difference between the synonym information and the corresponding first name, determine the sum of the first score corresponding to the first name and the second score corresponding to each difference The difference is the correlation score.

Among them, the first score is the score when the synonym information is completely consistent with the first person's name, and the second score is used to represent the loss when the first person's name and the synonym information have corresponding differences. The first score and the second score are calculated, and are used to represent the synonym information and the first name correlation score. Optionally, the difference can be determined according to each name format template, for example, it can include different capitalization, abbreviated surnames, removing prefixes, removing suffixes, removing ., removing , and reserved names, etc. That is to say, if there is at least one difference between the synonym information and the corresponding person name, determine the second sum of scores corresponding to each difference, and calculate the difference between the first score and the second sum of scores to obtain the relevant score.

For example, the first score can be set to 1, the second score corresponding to the difference between initials and surnames is 0.3, the second score corresponding to the difference in upper and lower case is 0.2, and the second score corresponding to the difference of increasing · The value is 0.1. When the first person's name is "SORIN FABIEN", the synonym information 1 is "Sorin Fabien", the synonym information 2 is "S·FABIEN", and the synonym information 3 is "Sorin·Fabien", the first person's name and synonym information 1 The correlation score is 0.8, the correlation score with synonym information 2 is 0.6, and the correlation score with synonym information 3 is 0.7.

Further, after determining the synonym information corresponding to each second name included in the second name information, the sum of the correlation scores of each synonym is calculated to obtain the first similarity between the corresponding candidate article and the first article.

Fig. 5 shows a schematic diagram of determining the synonym information of the first person's name according to an embodiment of the present disclosure. As shown in FIG. 5 , for each first name 50 in the first name information, its corresponding character type 51 is determined first. When the character type 51 corresponding to the first person's name 50 is English, divide the first person's name 50 to obtain the English name and English surname 52, and determine a plurality of corresponding synonyms according to the English name and English surname 52 and a plurality of preset name format templates 54 Information 55. When the character type 51 corresponding to the first person's name 50 is Chinese, the first person's name 50 is divided to obtain the Chinese name and Chinese surname 53, and the Chinese name and Chinese surname 53 are converted into corresponding English names and English surnames 52, and then according to the English name and English surname 52 and a plurality of preset name format templates 54 determine a plurality of corresponding synonym information 55 .

In a possible implementation, when the text type of the first person's name 50 is Chinese, the characters of the Chinese surname and Chinese name 53 included in the first person's name 50 can be determined directly through a text conversion method such as conversion between simplified and traditional characters. In another Chinese writing method, the corresponding synonym information 55 is obtained.

Step S42, according to the first address information and each of the second address information, determine the second similarity between each of the candidate articles and the first article.

In a possible implementation manner, the second degree of similarity between each candidate article and the first article is used to characterize the degree of relevance of the corresponding relevant addresses. Optionally, the second similarity may be determined by calculating the edit distance between the first address information and each second address information to obtain the second similarity between each candidate article and the first article. That is to say, the edit distance between each candidate article and the first article is used as the corresponding second similarity.

Further, when the first address information includes multiple first addresses and the second address information includes multiple second addresses, respectively calculate the edit distance of each first address and each second address, and calculate the weighted sum to obtain The corresponding second similarity.

Step S43 , determining a matching value according to the first similarity degree and the second similarity degree corresponding to each of the candidate articles.

In a possible implementation manner, according to the first similarity degree and the second similarity degree corresponding to each candidate article, a matching value used to characterize the matching degree between the candidate article and the first article may be determined. Optionally, the matching value may be calculated by calculating a weighted sum of the first similarity and the second similarity.

Step S50, determining a second article among each of the candidate articles according to the corresponding matching value.

In a possible implementation manner, after the matching values corresponding to each candidate article are determined, the second article is determined among each candidate article according to the corresponding matching value. Optionally, the determining method may be to determine a second preset number of candidate articles corresponding to the largest matching value as the second article. Alternatively, a candidate article whose corresponding matching value is greater than a matching threshold is determined as the second article.

Optionally, when the application scenario of the embodiment of the present disclosure is searching for academic papers related to patent documents, the finally determined second article is an academic paper.

The embodiments of the present disclosure can search for relevant candidate articles through the attribute information in the first article, and establish associations with the candidate articles according to the person's name and address therein to obtain a second article with high correlation, which improves the accuracy of the search results for related articles. Among them, by dividing names into synonym information in different manifestations, the problem of missing relevant articles in the search process due to different manifestations of corresponding names is avoided.

Although the relevant article search method is described above using FIG. 1 as an example, those skilled in the art can understand that the present disclosure should not be limited thereto. In fact, users can flexibly set the related article search method in the embodiment of the present disclosure according to personal preferences and/or actual application scenarios, as long as they can search for related articles based on names and addresses and improve the accuracy of search results.

Fig. 6 shows a schematic diagram of an apparatus for searching related articles according to an embodiment of the present disclosure. As shown in Figure 6, the related article search device 600 includes:

The first article determining module 60 is configured to determine a first article including attribute information, the attribute information including at least first name information and first address information;

A search information determination module 61, configured to determine search information corresponding to the first article according to the attribute information;

An article search module 62, configured to search for a first preset number of candidate articles in the article collection according to the search information, and each of the candidate articles includes corresponding second name information and second address information;

A data matching module 63, configured to determine the matching value of the first article and each of the candidate articles according to the first name information and first address information and each of the second name information and second address information;

The second article determining module 64 is configured to determine a second article in each of the candidate articles according to the corresponding matching value.

In a possible implementation manner, the data matching module includes:

In a possible implementation manner, the first similarity determination submodule includes:

A synonym determining unit, configured to determine at least one corresponding synonym information for each of the first person names, and a related score corresponding to each of the synonym information;

In a possible implementation manner, the synonym determining unit includes:

The relevant score determination subunit is configured to determine the relevant score by comparing the difference between each synonym information and the corresponding first person name.

In a possible implementation manner, the synonym determining subunit includes:

An English information determining subunit, configured to determine the English surname and English name included in the first person name in response to the first person name in English;

The synonym generating subunit is used to input the English surname and English name corresponding to each first person's name into a plurality of preset name format templates to obtain corresponding synonym information.

Alternatively, identify the Chinese surname and Chinese name included therein;

A correlation score calculation subunit, configured to determine the sum of the first score corresponding to the first name and the second score corresponding to each of the differences in response to at least one difference between the synonym information and the corresponding first name. The difference is the correlation score.

The second similarity determining unit is configured to calculate an edit distance between the first address information and each of the second address information to obtain a second similarity between each of the candidate articles and the first article.

The first screening submodule is configured to determine a second preset number of candidate articles corresponding to the largest matching value as the second article.

The second screening submodule is configured to determine that candidate articles whose corresponding matching values are greater than the matching threshold are the second articles.

The search information determining submodule is configured to determine search information according to the feature information, first name information and first address information.

FIG. 7 shows a schematic diagram of an electronic device 700 according to an embodiment of the present disclosure. For example, the electronic device 700 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, and the like.

Referring to FIG. 7, electronic device 700 may include one or more of the following components: processing component 702, memory 704, power supply component 706, multimedia component 708, audio component 710, input/output (I/O) interface 712, sensor component 714, and communication component 716 .

The processing component 702 generally controls the overall operations of the electronic device 700, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 702 may include one or more processors 720 to execute instructions to complete all or part of the steps of the above method. Additionally, processing component 702 may include one or more modules that facilitate interaction between processing component 702 and other components. For example, processing component 702 may include a multimedia module to facilitate interaction between multimedia component 708 and processing component 702 .

The memory 704 is configured to store various types of data to support operations at the electronic device 700 . Examples of such data include instructions for any application or method operating on the electronic device 700, contact data, phonebook data, messages, pictures, videos, and the like. The memory 704 can be realized by any type of volatile or non-volatile storage device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic or Optical Disk.

The power supply component 706 provides power to various components of the electronic device 700 . Power components 706 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for electronic device 700 .

The multimedia component 708 includes a screen providing an output interface between the electronic device 700 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may not only sense a boundary of a touch or swipe action, but also detect duration and pressure associated with the touch or swipe action. In some embodiments, the multimedia component 708 includes a front camera and/or a rear camera. When the electronic device 700 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive part of the multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capability.

The audio component 710 is configured to output and/or input audio signals. For example, the audio component 710 includes a microphone (MIC), which is configured to receive external audio signals when the electronic device 700 is in operation modes, such as call mode, recording mode and voice recognition mode. Received audio signals may be further stored in memory 704 or sent via communication component 716 . In some embodiments, the audio component 710 also includes a speaker for outputting audio signals.

The I/O interface 712 provides an interface between the processing component 702 and a peripheral interface module, which may be a keyboard, a click wheel, a button, and the like. These buttons may include, but are not limited to: a home button, volume buttons, start button, and lock button.

Sensor assembly 714 includes one or more sensors for providing status assessments of various aspects of electronic device 700 . For example, the sensor component 714 can detect the open/closed state of the electronic device 700, the relative positioning of components, such as the display and the keypad of the electronic device 700, the sensor component 714 can also detect the electronic device 700 or one of the electronic device 700 The position of components changes, the presence or absence of user contact with the electronic device 700 , the orientation or acceleration/deceleration of the electronic device 700 and the temperature change of the electronic device 700 . Sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. Sensor assembly 714 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor component 714 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.

The communication component 716 is configured to facilitate wired or wireless communication between the electronic device 700 and other devices. The electronic device 700 can access a wireless network based on communication standards, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 716 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 716 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) technology, Infrared Data Communication (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

In an exemplary embodiment, electronic device 700 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable A programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic component implementation for performing the methods described above.

In an exemplary embodiment, there is also provided a non-volatile computer-readable storage medium, such as the memory 704 including computer program instructions, which can be executed by the processor 720 of the electronic device 700 to implement the above method.

FIG. 8 shows a schematic diagram of another electronic device 800 according to an embodiment of the present disclosure. For example, the electronic device 800 may be provided as a server. Referring to FIG. 8 , electronic device 800 includes processing component 822 , which further includes one or more processors, and a memory resource represented by memory 832 for storing instructions executable by processing component 822 , such as application programs. The application program stored in memory 832 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 822 is configured to execute instructions to perform the above method.

Electronic device 800 may also include a power supply component 826 configured to perform power management of electronic device 800, a wired or wireless network interface 850 configured to connect electronic device 800 to a network, and an input-output (I/O) interface 858 . The electronic device 800 can operate based on an operating system stored in the memory 832, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

In an exemplary embodiment, there is also provided a non-volatile computer-readable storage medium, such as a memory 832 including computer program instructions, which can be executed by the processing component 822 of the electronic device 800 to implement the above method.

The present disclosure can be a system, method and/or computer program product. A computer program product may include a computer readable storage medium having computer readable program instructions thereon for causing a processor to implement various aspects of the present disclosure.

A computer readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. A computer readable storage medium may be, for example, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory), static random access memory (SRAM), compact disc read only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanically encoded device, such as a printer with instructions stored thereon A hole card or a raised structure in a groove, and any suitable combination of the above. As used herein, computer-readable storage media are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., pulses of light through fiber optic cables), or transmitted electrical signals.

Computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or downloaded to an external computer or external storage device over a network, such as the Internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers. A network adapter card or a network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .

Computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or Source or object code written in any combination, including object-oriented programming languages—such as Smalltalk, C++, etc., and conventional procedural programming languages—such as the “C” language or similar programming languages. Computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement. In cases involving a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as via the Internet using an Internet service provider). connect). In some embodiments, an electronic circuit, such as a programmable logic circuit, field programmable gate array (FPGA), or programmable logic array (PLA), can be customized by utilizing state information of computer-readable program instructions, which can Various aspects of the present disclosure are implemented by executing computer readable program instructions.

Aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It should be understood that each block of the flowcharts and/or block diagrams, and combinations of blocks in the flowcharts and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine such that when executed by the processor of the computer or other programmable data processing apparatus , producing an apparatus for realizing the functions/actions specified in one or more blocks in the flowchart and/or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause computers, programmable data processing devices and/or other devices to work in a specific way, so that the computer-readable medium storing instructions includes An article of manufacture comprising instructions for implementing various aspects of the functions/acts specified in one or more blocks in flowcharts and/or block diagrams.

It is also possible to load computer-readable program instructions into a computer, other programmable data processing device, or other equipment, so that a series of operational steps are performed on the computer, other programmable data processing device, or other equipment to produce a computer-implemented process , so that instructions executed on computers, other programmable data processing devices, or other devices implement the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, a portion of a program segment, or an instruction that includes one or more Executable instructions. In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified function or action , or may be implemented by a combination of dedicated hardware and computer instructions.

Having described various embodiments of the present disclosure above, the foregoing description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and alterations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principle of each embodiment, practical application or technical improvement in the market, or to enable other ordinary skilled in the art to understand each embodiment disclosed herein.

Claims

A search method for related articles, including:

determining the first article including attribute information, the attribute information including at least first person name information and first address information;

determining search information corresponding to the first article according to the attribute information;

Searching for a first preset number of candidate articles in the article collection according to the search information, each of the candidate articles includes corresponding second name information and second address information;

determining matching values of the first article and each of the candidate articles according to the first name information and first address information and each of the second name information and second address information;

A second article is determined among each of the candidate articles according to the corresponding matching value.
The method according to claim 1, wherein, according to the first name information and first address information and each of the second name information and second address information, determining the first article and each of the Matching values for candidate articles include:

determining a first similarity between each of the candidate articles and the first article according to the first person name information and each of the second person name information;

determining a second degree of similarity between each of the candidate articles and the first article according to the first address information and each of the second address information;

A matching value is determined according to the first similarity and the second similarity corresponding to each candidate article.
The method according to claim 2, wherein, according to the first person name information and each of the second person name information, determining the first similarity between each of the candidate articles and the first article comprises:

determining at least one first person's name included in the first person's name information, and at least one second person's name included in each of the second person's name information;

For each of the first person names, determine at least one corresponding synonym information, and a related score corresponding to each of the synonym information;

For each of the second person name information, determine the relationship between each of the second person names included therein and each of the synonym information;

The first similarity is determined according to the sum of correlation scores of synonym information corresponding to each of the second person names.
The method according to claim 3, wherein, for each of the first person names, determining the corresponding at least one synonym information, and the relevant scores corresponding to each of the synonym information include:

determining at least one synonym information corresponding to each of the first person names;

The correlation score corresponding to the synonym information is determined by comparing the difference between each synonym information and the corresponding first person name.
The method according to claim 4, wherein said determining at least one synonym information corresponding to each of said first person names comprises:

Responsive to the first person being an English name, determining an English surname and an English name included in the English name;

The English surname and English name corresponding to each first person's name are respectively input into a plurality of preset name format templates to obtain the corresponding synonym information.
The method according to claim 5, wherein said determining at least one synonym information corresponding to each said first person name further comprises:

In response to the first person name being a Chinese name, performing text conversion on the Chinese name to obtain at least one corresponding synonym information;

Alternatively, determine the Chinese surname and Chinese name included in the Chinese name;

The Chinese surname and Chinese name are converted into English surname and English name by way of pinyin conversion.
The method according to any one of claims 4 to 6, wherein said determining the relevant score by comparing the difference between each said synonym information and the corresponding first person name comprises:

determining the first score corresponding to each of the first names;

Determining second scores corresponding to multiple preset differences;

In response to at least one difference between the synonym information and the corresponding first person name, determining that the difference between the first score corresponding to the first person name and the sum of the second scores corresponding to each of the differences is the The correlation score corresponding to the synonym information.
The method according to any one of claims 2 to 6, wherein, according to the first address information and each of the second address information, the second similarity between each of the candidate articles and the first article is determined include:

Calculate the edit distance between the first address information and each of the second address information to obtain the second similarity between each of the candidate articles and the first article.
The method according to any one of claims 1 to 8, wherein said determining the second article in each of the candidate articles according to the corresponding matching value comprises:

A second preset number of candidate articles corresponding to the largest matching value is determined as the second article.
The method according to any one of claims 1 to 9, wherein said determining the second article in each of said candidate articles according to the corresponding matching value comprises:

It is determined that the candidate article whose corresponding matching value is greater than a matching threshold is the second article.
The method according to claim 10, wherein the attribute information also includes article attributes, and determining the search information corresponding to the first article according to the attribute information includes:

Extract feature information from the article attributes, where the feature information includes at least one keyword corresponding to the first article;

The search information corresponding to the first article is determined according to the characteristic information, the first name information and the first address information.
The method according to claim 11, wherein the first article is a patent document, and the second article is an academic paper.
The method according to claim 11 or 12, wherein the article attributes include at least one of specification abstract, claims, specification, patent title, technical field, background technology, content of the invention, and specific implementation, and the first The name information includes at least one inventor name, and the first address includes the address of the applicant.
The method according to claim 13, wherein the second name information includes the name of at least one author of the thesis, and the second address includes the address of the institution to which the author of the thesis belongs.
A device for searching related articles, comprising:

The first article determination module is configured to determine a first article including attribute information, the attribute information including at least first name information and first address information;

a search information determination module, configured to determine search information corresponding to the first article according to the attribute information;

An article search module, configured to search for a first preset number of candidate articles in the article collection according to the search information, and each of the candidate articles includes corresponding second name information and second address information;

A data matching module, configured to determine the matching value of the first article and each of the candidate articles according to the first name information and first address information and each of the second name information and second address information;

The second article determining module is configured to determine a second article in each of the candidate articles according to the matching value of each of the candidate articles.
The related article search device according to claim 15, wherein said data matching module comprises:

The first similarity determining submodule is used to determine the first similarity between each of the candidate articles and the first article according to the first name information and each of the second name information;

A second similarity determining submodule, configured to determine a second similarity between each of the candidate articles and the first article according to the first address information and each of the second address information;

A matching value determination submodule is configured to determine a matching value according to the first similarity and the second similarity corresponding to each of the candidate articles.
The related article search device according to claim 16, wherein said first similarity determining submodule comprises:

a name determination unit, configured to determine at least one first name included in the first name information, and at least one second name included in each of the second name information;

A synonym determining unit, configured to determine at least one corresponding synonym information for each of the first person names, and a related score corresponding to each of the synonym information;

A name association unit, configured to determine the relationship between each of the second names and each of the synonym information included in each of the second name information;

The first similarity determination unit is configured to determine the first similarity according to the sum of correlation scores of the synonym information corresponding to each of the second names.
The related article search device according to claim 16 or 17, wherein the second similarity determining submodule comprises:

The second similarity determining unit is configured to calculate an edit distance between the first address information and each of the second address information to obtain a second similarity between each of the candidate articles and the first article.
An electronic device comprising:

processor;

memory for storing processor-executable instructions;

Wherein, the processor is configured to invoke instructions stored in the memory to execute the method according to any one of claims 1-14.
A computer-readable storage medium on which computer program instructions are stored, wherein the computer program instructions implement the method according to any one of claims 1 to 14 when executed by a processor.