JP7003481B2 - Reinforcing rankings for social media accounts and content - Google Patents

Description

Mutual reference to related applications This application is a partial continuation of US Patent Application No. 15 / 043,406 filed February 12, 2016, of US Patent Application No. 15 / 422,383 filed February 1, 2017. Partial continuation This is a partial continuation of US Patent Application No. 15 / 424,730 filed on February 3, 2017. The content of the above application is incorporated herein by reference in its entirety.

Fields The embodiments discussed in this paper relate to the identification and extraction of information.

With the advent of computer networks such as the Internet and the growth of technology, more and more information is becoming available to more and more people. For example, many leading researchers use social media to share information and exchange ideas in a timely manner.

The subject matter claimed in the present application is not limited to embodiments that solve any shortcomings or operate only in an environment as described above. Rather, this background is provided only to illustrate one exemplary technical area in which some of the embodiments described herein may be implemented.

One or more embodiments of the present disclosure include computer-implemented methods of ranking social media accounts and content based on mutually reinforcing relationships between social media accounts and content. You may be. The method may include determining a general type weight for each social media account of multiple social media accounts. The general type weight may be based on the social media account type corresponding to the social media account. The method may further include determining the individual weight for each social media account of the plurality of social media accounts. The method also mutually reinforces between each social media account of the plurality of social media accounts and the content promoted by each social media account of the plurality of social media accounts. It may also include encoding relationships. The mutually reinforcing relationship is between each social media account of the plurality of social media accounts and the content item of the content promoted by each social media account of the plurality of social media accounts. It may be encoded as a promotional link. The method may further include calculating the basic link strength. The base link strength may be calculated for each promotional link, and the base link strength is the general type weight for each social media account of the plurality of social media accounts and the plurality of social media. • It may be based on the individual weights for each social media account in the account. The method may also include calculating the mutually reinforcing rankings of the plurality of social media accounts and content based on the basic link strength.

The objectives and advantages of the embodiments will be realized and achieved at least by the elements, features and combinations specifically pointed out in the claims.

It should be understood that the above general description and the following detailed description are merely examples and descriptive, and do not limit the claimed invention.

An exemplary embodiment will be described and described in more detail and in detail with reference to the accompanying drawings.
FIG. 6 illustrates an exemplary system configured to identify and extract information. It is a diagram of an exemplary flow that may be used for the identification and extraction of information. The first half of the flowchart of an exemplary method of identifying and extracting information. The second half of the flow chart is an exemplary method of identifying and extracting information. It is a flowchart of another exemplary method of information identification and extraction. It is a flowchart of another exemplary method of information identification and extraction. It is another exemplary flow diagram that may be used for the identification and extraction of information. It is a flowchart of an exemplary method of information identification and extraction. It is a flowchart of an exemplary method of identifying a personal academic web page. The first half of the flow chart of another exemplary method that may be used in the identification and extraction of information. It is the second half of the flow chart of another exemplary method that may be used in the identification and extraction of information. A flowchart of an exemplary method that may be used in cross-validating candidates for social media accounts and personal academic web pages. A flowchart of another exemplary method that may be used in cross-validating candidates for social media accounts and personal academic web pages. A flowchart of another exemplary method that may be used in cross-validating candidates for social media accounts and personal academic web pages. A flowchart of another exemplary method that may be used in cross-validating candidates for social media accounts and personal academic web pages. A flowchart of another exemplary method that may be used in cross-validating candidates for social media accounts and personal academic web pages. FIG. 3 illustrates an exemplary schematic representation of the process of generating a candidate set for a social media account. The first half of the flowchart of an exemplary method of identifying and extracting information while using a social media account as a sensor. The second half of the flow chart is an exemplary method of identifying and extracting information while using a social media account as a sensor. It is a flowchart of an exemplary method that can be used in identifying and extracting information while using a social media account as a sensor. It is a flowchart of another exemplary method that can be used in identifying and extracting information while using a social media account as a sensor. It is a diagram of an exemplary flow that can be used for mutually reinforcing rankings of social media accounts and content based on the social media account type. The first half of the diagram of an exemplary flow that can be used for social media account type decisions. The second half of the diagram of the exemplary flow that can be used for social media account type decisions. It is a flowchart of an exemplary method of calculating a mutually reinforcing ranking of social media accounts and content. It is a diagram showing an exemplary bipartite graph that encodes a mutually reinforcing relationship between an account and content. It is a figure which shows the exemplary system which can identify and extract information.

Some embodiments described in this article relate to methods and systems for identifying and extracting information. As a result of the current speed of technology, research and general knowledge generation, previous and current methods of knowledge distribution do not provide sufficient up-to-date knowledge and information about recent developments. Moreover, knowledge is no longer generated by a small number of selected individuals in a selected area. Rather, researchers, professors, experts and others with knowledge of a given topic, referred to as knowledgeable people in this disclosure, are located around the world and constantly generate and share new ideas.

However, as a result of the Internet, this vast amount of newly generated knowledge from around the world is constantly being shared worldwide. In some situations, this vast amount of knowledge is shared through social media. For example, knowledgeable people may share their recent knowledge through blogs, microblogs and other social media.

Knowing that current information is shared on social media does not mean that it is easily accessible or that individuals can actually access it. In some areas, there may be thousands, tens of thousands, or hundreds of thousands of knowledgeable people. There is no database containing the names of knowledgeable people from a particular field. However, even if the database contains a name, the time a person spends identifying whether the knowledgeable person has a social media account would be unthinkably disproportionate. .. Moreover, even if a person can identify whether a knowledgeable person had a social media account, they are always accessing, parsing, and sharing those social media accounts. The time to gain new knowledge will not be realistic.

After all, the rise of computers and the Internet has made large amounts of information available, but there is no practical way for humans to reasonably access it. Some embodiments described in this article have been previously unavailable to people, or to information that was not reasonably available by humans, or even by groups of humans, without technical assistance. Regarding methods and systems for identifying and extracting information that can help access.

The methods and systems for identifying and extracting information described in this disclosure include identifying knowledgeable people by identifying the authors of publications and lectures. Metadata for those multiple authors is extracted from publications and lectures. Author metadata is used to search for social media accounts to determine the social media accounts of those authors. For example, in some embodiments, author metadata may include information about the author's name, author's profile, and co-authors. Information from social media accounts may be compared to author metadata to match authors with social media accounts. In some embodiments, the systems and methods in this disclosure may further consider the topic of information provided on social media accounts. Thus, if an author has a social media account but does not share any knowledge related to the topic published by that author, the social media account may not be considered.

After identifying a social media account, the information on the identified social media account may be collected, organized and presented. For example, the information may be organized on the basis of a topic, thereby presenting current knowledge from people with different knowledge, with current updates, to those who are interested in the selected topic. be able to. In this way, new information from a number of sources that one cannot reasonably identify or manage can be accessed and shared. Thus, the systems and methods in this disclosure provide technical solutions to problems arising from technology that cannot be reasonably implemented by humans.

In addition, even if a social media account can be identified, the automated system or process for identifying a social media account related to a knowledgeable person may be incorrect, or multiple social media accounts. It may not be possible to make a distinction among the potential candidates for. For example, more than 70% of names have multiple Twitter accounts associated with that name. It can be very difficult for a computing system to automatically determine which social media account is associated with a particular knowledgeable person. Also, many knowledgeable people have personal academic web pages. It can also be difficult to identify whether a website is an academic web page of a knowledgeable person.

This disclosure may relate to mutual validation between a knowledgeable person's social media account and a personal academic web page. For example, by using different aspects of social media accounts and personal academic web pages, it is possible to ensure that different consistent features or aspects between the two are related to the same knowledgeable person. .. Consistent with this disclosure, a collection of candidate social media accounts and candidate personal academic web pages may be identified. Each candidate may be parsed or otherwise analyzed to identify various features or aspects of a candidate social media account and / or a candidate personal academic web page. Their various features and / or aspects are cross-validated between the two to ensure that both their personal academic web page and their social media account are correctly associated with a particular author. May be done. According to this disclosure, after social media accounts have been cross-validated with personal academic web pages, the posts of those social media accounts may be organized on a topic basis and thereby selected. A person interested in a topic can present current knowledge from multiple different knowledgeable people with current updates. In this way, new information from a number of sources that one cannot reasonably identify or manage can be accessed and shared. Thus, the systems and methods in this disclosure provide technical solutions to problems arising from technology that cannot be reasonably implemented by humans. In addition, it allows automated processing of tasks that were not previously performed by the computer.

A further difficulty in this space is identifying social media accounts that are knowledgeable about a given topic. It is impractical and virtually impractical to try to identify different accounts where an individual is knowledgeable about a topic that is squeezing thousands or even millions of social media accounts. Moreover, the set of knowledgeable people who can only recognize knowledgeable social media posts on any given topic can be completely different. Similarly, a simple keyword search performed by a computer is a huge number of accounts that may simply refer to a topic or may not actually know the topic being discussed. It can lead to false positives. Moreover, more sophisticated computer-based analysis may not be as effective as relying on the human judgment of a knowledgeable person as to whether another person may be considered knowledgeable on a given topic.

This disclosure may relate to using a social media account as a sensor. Thereby, human judgment can be indirectly used as a basis for determining whether a given social media account can be a knowledgeable account. Specifically, those who are knowledgeable about a given topic are likely to know and recognize which other people are knowledgeable about the same topic. In addition, people who are knowledgeable about a given topic may seek information from others who are also knowledgeable about the topic, for example by reading the publication or following the social media post. Is high. For example, a list of followers and followers may be aggregated starting from one or more seeded social media accounts that are known to be knowledgeable about a topic. .. Optionally, general and / or non-personal social media accounts may be removed from the list. For accounts that are being followed by a seed account that are not already seed accounts, analysis may be performed on that account to determine if it is a knowledgeable account. .. If it is a knowledgeable account (for example, if the account is associated with the author of an academic publication on the topic in question), the account may be added as a seed account. In this way, people who are actually knowledgeable about a topic use it indirectly (through the social media accounts they follow) to identify other accounts that are also knowledgeable. Will be done. Moreover, this is done in a way that computers are used in ways that humans cannot. Thus, the systems and methods in this disclosure provide technical solutions to problems arising from technology that cannot be reasonably implemented by humans. In addition, through the implementation of hybrid systems that leverage human judgment and knowledge, it allows automated processing of tasks that were not previously performed by computers.

As discussed above, researchers, professors, experts and others with knowledge of a given topic are located all over the world and are constantly generating and sharing new ideas. Many of these knowledgeable people view social media such as Twitter as an available resource for learning the latest discipline-specific knowledge. Due to the abundance of information and knowledge shared through social media, it can be difficult for someone like a learner in a particular discipline to identify different accounts that are knowledgeable about a topic.

The present disclosure may relate to mutually reinforcing rankings of social media accounts and social media content based on the social media account type. The premise is that social media users with discipline-specific expertise (ie, knowledgeable on a given topic) are likely to promote high-quality content in that discipline, and high-quality content in a discipline It is promoted by social media users with discipline-specific expertise. Specifically, if content (eg, an article) is published or shared by more quality social media accounts with discipline-specific expertise, that content is of good or high quality content in that discipline. We can conclude that there is. In addition, if a social media account consistently publishes or shares good content (eg, good articles) in a discipline, that social media account is a discipline-specific specialty. You can conclude that it is a good quality social media account with knowledge. Some embodiments of the present disclosure are based on the social media account type and are mutually reinforcing between good quality or high quality content in a discipline and good quality social media accounts with discipline-specific expertise. Provide rankings to do.

Embodiments of the present disclosure will be described with reference to the accompanying drawings.

FIG. 1 is a diagram illustrating an exemplary system 100 configured to identify and extract information, configured according to at least one embodiment described in the present disclosure. The system 100 may include a network 102, an information gathering system 110, a publication system 120, a social media system 130, a device 140 and a web hosting system 150.

The network 102 may be configured to communically combine an information gathering system 110, a publication system 120, a social media system 130, a device 140 and a web hosting system 150. In some embodiments, the network 102 may include any network or network configuration configured to send and receive communications between devices. In some embodiments, the network 102 may include a conventional network, a wired or wireless network, and may have many different configurations. In addition, network 102 is a local area network (LAN), wide area network (WAN) (eg, the Internet) or other interconnected data path through which multiple devices and / or entities can communicate. May include. In some embodiments, the network 102 may include a peer-to-peer network. The network 102 may or may be coupled to parts of the remote communication network to send data in a variety of different communication protocols. In some embodiments, the network 102 may include a Bluetooth® communication network or a cellular communication network for communicating and / or transmitting and receiving data. Such transmissions and receptions include Short Message Service (SMS), Multimedia Messaging Service (MMS), Hypertext Transfer Protocol (HTTP), Direct Data Connection, Wireless Application Protocol (WAP), Email and / or Including those via others. Network 102 includes 3rd Generation (3G), 4th Generation (4G), Long Term Evolution (LTE), Long Term Evolution Advanced (LTE-A), Voice over LTE (“VoLTE”) or any other mobile. It may include a combination of data networks or mobile data networks. Further, the network 102 may include one or more IEEE 802.11 wireless networks.

In some embodiments, any of the information gathering system 110, publication system 120, social media system 130 and web hosting system 150 can be configured with any hardware configuration, eg, networked together and tasked. May include servers and databases that are configured to run. For example, the information gathering system 110, the publication system 120, the social media system 130, and the web hosting system 150 are each a plurality of computing systems, for example, a plurality of servers, which are networked together and disclosed in the present disclosure. It may include those configured to perform and / or control the execution of the operations described in. In some embodiments, any of the information gathering system 110, publication system 120, social media system 130 and web hosting system 150 perform the actions described in this disclosure and / or said. It may include computer-readable instructions that are configured to be executed by one or more devices to control the execution of operations.

The information collection system 110 may include a data storage unit 112. The data storage unit 112 may include a database in the information collection system 110 having a structure based on a data object. For example, the data storage unit 112 may include a plurality of data objects having various fields. In some embodiments, the data storage unit 112 may include an author object 114, a social media account object 116, and a personal web page object 118.

In general, the information gathering system 110 may be configured to acquire author information for publications, such as articles, lectures and other publications from the publication system 120. Using the author information, the information gathering system 110 may determine the social media account associated with the author and pull information from the social media account from the social media system 130. At the same time, the personal academic web page associated with the author can be identified and information from the personal academic web page can be pulled from the web hosting system 150. The information gathering system 110 may organize information from social media accounts and / or personal academic web pages and provide it to device 140. Thereby, the information can be presented on the display 142 of the device 140.

The publication system 120 may include a plurality of systems for hosting articles, publications, journals, lectures and other digital documents. The plurality of systems in the publication system 120 may not all be involved except that they host media that provide information. For example, one system of publication system 120 may include a university website hosting lectures and dissertations by university professors. Another system of publication system 120 may include a website hosting articles published in the journal. In these and other embodiments, the publication system 120 may or may not share a website, server, hosting domain or owner.

In some embodiments, the information gathering system 110 may access one or more of the publication systems 120 to obtain digital documents from the publication system 120. Using those digital documents, the information gathering system 110 may obtain information about the author of the digital document and the topic of the digital document. In some embodiments, for each author of a digital document, the information gathering system 110 may generate an author object 114 in the data storage unit 112. In the generated author object 114, the information gathering system 110 may store information about the author obtained from the digital document. The information may include names, profiles, images, co-authors of digital documents, and affiliations of authors (eg, the university to which the author belongs or the company in which the author is employed). The information gathering system 110 may determine the topic of the digital document. The topic of the digital document may be stored in the author object 114.

In some embodiments, multiple digital documents from publication system 120 may include the same author. In these and other embodiments, the author object 114 for the author may be updated and / or supplemented with information from other digital documents. For example, topics from other digital documents may be stored in the author object 114. In some embodiments, the topic of the entire digital document of an author obtained by the information gathering system 110 may be stored in the author object 114.

After generating the author object 114, the information gathering system 110 may be configured to determine a social media account for each author in the author object 114. The information gathering system 110 may determine the social media account by accessing the social media system 130. Additional or alternative, the information gathering system 110 may be configured to identify a personal scholarly web page for each author in the author object 114. The information gathering system 110 may determine the social media account by accessing the web hosting system 150. In these and other embodiments, the information system 110 may cross-validate a social media account of an author with a personal scholarly web page.

In some embodiments, each social media system 130 may include a system configured to host different social media. For example, one of the social media systems 130 may include a microblogging social media system. Another of the social media systems 130 may include a blog social media system. Another of the social media systems 130 may include social networks or other types of social media systems. Another of the social media systems 130 may include a publication collection social media system.

The information gathering system 110 may require each social media system 130 to search for the name of each author in the author object 114 in their respective social media account. For example, the information gathering system 110 may include thousands, tens of thousands, or hundreds of thousands of author objects 114, where each author object 114 contains the name of one author. In this example, there may be four social media systems 130 with which the authors can share information. The number of social media systems 130 may be more or less than four. In these and other embodiments, the information gathering system 110 requires that each of the four social media systems 130 perform a search using the name of the author associated with each author object 114. You may. Thus, given that there are four social media systems 130 and 100,000 authors, the social media system 110 can request 400,000 searches. The social media system 130 may provide the search results to the information gathering system 110. In these and other embodiments, the search results include the link and / or network address of the owner's social media account with a name that at least partially matches the name of the author of author object 114. You may be.

The information gathering system 110 may request a social media account using the social media account link and / or network address from the search. The information gathering system 110 may also generate a social media account object 116 for each social media account. To generate the social media account object 116, the information gathering system 110 may pull information from the social media account and store the information in the social media account object 116. The social media account object 116 may include information about the person associated with the social media account, such as name, profile data, images and / or social media contacts. The information gathering system 110 may also acquire the topic of the post in the social media account, which may also be stored in the social media account object 116.

In some embodiments, each web hosting system 150 may include a system configured to host various web pages. For example, one of the web hosting systems 150 includes a college or college web hosting system that includes one or more web pages devoted to faculty or others associated with the college or college. May be good. Another of the web hosting system 150 is a company or other me that contains one or more web pages that are devoted to someone who is employed or otherwise associated with a company or private entity. Entity web hosting system may be included. Another of the web hosting system 150 may include a personal web hosting system.

The information gathering system 110 may request a general search engine to perform a search for a web page based on the name of each author in the author object 114. Additional or alternative, the information gathering system 110 requires a common search engine to perform a search for a web page based on the name of each author in the author object 114 and the affiliation of that author. You may. For example, the information gathering system 110 may include thousands, tens of thousands, or hundreds of thousands of author objects 114, where each author object 114 is the name of one author and optionally its author. Including the affiliation of. Therefore, if there are 100,000 authors, the information gathering system 110 may request 200,000 searches (100,000 searches for author names and 100,000 searches for author names and affiliations). ). The web hosting system 150 may provide the search results to the information gathering system 110. In these and other embodiments, the search results may include links for personal academic web page candidates and / or uniform resource location specifiers (URLs).

The information gathering system 110 may request a personal academic web page candidate using the link and / or URL of the personal academic web page candidate. The information gathering system 110 may generate a personal academic web page object 118 for each of the personal academic web page candidates. In order to generate the personal academic web page object 118, the information gathering system 110 may pull information from the personal academic web page candidates and store the information in the personal academic web page object 118. The personal academic web page object 118 may include information about a person associated with a personal academic web page candidate, such as a name, publication, keyword, topic, affiliation, social, image and / or others. In some embodiments, personal academic web page candidates may be parsed or otherwise analyzed for various attributes as described, for example, in Method 900 of FIGS. 9a and 9b.

The information gathering system 110 compares the information from the author object 114 with the information from the social media account object 116 and / or the personal academic web page object 118 and is relevant to the author in the author object 114. You may determine which social media account and / or personal academic web page you are. For example, for a given author object 114, a search on social media system 130 may return 25 accounts. 25 social media account objects 116 are compared to a given author object 114 and personal web page object 118, which of the 25 social media accounts and personal academic web pages It may be determined which of the candidates is associated with the author of a given author object 114. In some embodiments, an author may be associated with a social media account when the author is the owner of the social media account. In some embodiments, the social media account and personal web page associated with the author of author object 114 is such that both the social media account and the personal web page are associated with the author. Mutual verification may be done to confirm at a higher level of confidence that this is possible. Various examples of such mutual verification are described in more detail with respect to FIGS. 7 and 10-14.

After matching the social media account, including by mutual verification between the author from the digital document from the publication system 120 and the personal web page, the information gathering system 110 will match the social media account. You may get information from. In these and other embodiments, the information gathering system 110 may request a social media account and parse the social media account to obtain information from the social media account. The information gathering system 110 may collate information from social media accounts, organize the information on a topic basis, and provide the information to users of the information gathering system 110. For example, the information gathering system 110 may provide the information to the device 140.

The device 140 may be associated with a user of the information gathering system 110. In these and other embodiments, the device 140 may include any type of computing system. For example, device 140 may include a desktop computer, tablet computer, mobile phone, smartphone or any other computer system. The device 140 may include an operating system capable of supporting a web browser. Through a web browser, the device 140 may request the information gathering system 110 for a web page containing information collected by the information gathering system 110 from the social media account of the social media system 130. The requested web page may be displayed on the display 142 of the device 140 for presentation to the user of the device 140.

In some embodiments, the information gathering system 110 obtains information from a social media account of a subset of authors on a given topic and presents that information based on said subset of authors. You may. In these and other embodiments, the social media account may be used as a sensor to identify which social media account may be included in its subset. For example, starting with one or more seed social media accounts associated with people who are known to be knowledgeable about a given topic, and being followed by those knowledgeable people. A list of media accounts may be obtained. Social media accounts that are already seed accounts may be removed from the list. Optionally, also remove general social media accounts. In these and other embodiments, the remaining social media accounts in the list are analyzed to determine if they are knowledgeable social media accounts, and if so, seed social media. -May be added as an account. Such processes consistent with the present disclosure are described in more detail in FIGS. 16a-18.

In these and other embodiments, another set of social media accounts, which are learner accounts, may be generated. For example, starting with one or more seed social media accounts related to people who are known to be knowledgeable about a given topic, social media following those knowledgeable people. -A list of accounts may be obtained. Social media accounts that are already seed accounts may be removed from the list. Optionally, also remove general social media accounts. In these and other embodiments, the remaining social media accounts in the list are analyzed to determine if they are interested in the topic, and if so, relevant to those who are trying to learn about that topic. May be added to the second list of social media accounts.

In some embodiments, the first content may be delivered to the seed social media account based on each group of which the account is part, and the second content is said to be the second. It may be served to the social media account on the list. For example, a seed social media account may be associated with a knowledgeable person, and academic publications and book chapters on the topic may be most suitable for a seed social media account. On the other hand, less rigorous material, such as lecture notes or demo videos, may be more suitable for the second set of learning social media accounts.

In some embodiments, the information gathering system 110 may determine a mutually reinforcing ranking of social media accounts and social media content based on the social media account type. The information gathering system 110 may receive an extended seed social media account as input with field-specific knowledge (eg, knowledge on a given topic). Extended seed social media accounts are followed by seed social media accounts associated with people who are known to be knowledgeable about a given topic, as well as those who are knowledgeable. Includes social media accounts that are not already seed social media accounts. Social media accounts that are followed by the knowledgeable person and are no longer seed social media accounts are associated with organizations, publications, vendors including software vendors, conferences, etc. You may. The information gathering system 110 may discriminate between different types of social media accounts from the extended seeded social media accounts of the input with field-specific knowledge. For example, the information gathering system 110 may utilize machine learning tools such as judgment trees to discriminate between different types of social media accounts with discipline-specific knowledge.

In some embodiments, the information gathering system 110 bases the ranking on a mutually reinforcing relationship between the social media account and the social media content promoted by the social media account. May be good. For example, an informative social media account may promote fresh, quality content, and good content may be promoted by a useful information-rich social media account. The information gathering system 110 determines or calculates the strength of the link between the social media account and the social media content promoted by the social media account as the basis for a mutually reinforcing relationship. May be good. For example, for each social media account and the social media content promoted by that social media account, the information gathering system 110 may calculate the link strength (eg, the strength of the promotion). The ranking may be based on the link strength. In some embodiments, the information gathering system 110 utilizes a machine learning tool, such as a judgment tree, to determine the ranking of social media accounts and social media content using said link strength. You may. In some embodiments, the information gathering system 110 considers promotions that include links, but may not consider promotions that do not include links.

In some embodiments, the information gathering system 110 may consider the promotion timeline in determining link strength. For example, a promotion that is earlier in time may be given a higher weight than a promotion that is later in time. That is, the link strength associated with the earlier promotion may be given a higher weight than the link strength associated with the later promotion. As another example, a promotion that is more recent in time may be given a higher weight than a promotion that is older in time. As yet another example, promotion of newer or more recent content may be given higher weight than promotion of older content.

In some embodiments, the information gathering system 110 may consider the type of promotion in determining the link strength. For example, an initial or original promotion may be given a higher weight than a promotion that promotes an initial promotion. In some embodiments, some of the weight from the promotion promoting the initial promotion may be given or transferred to the initial promotion.

Modifications, additions or omissions may be made to system 100 without departing from the scope of the present disclosure. For example, the system 100 may include a plurality of other devices that acquire information from the information gathering system 110. Alternatively or additionally, the system 100 may include one social media system.

FIG. 2 is a diagram of an exemplary flow 200 that can be used to identify and extract information based on at least one embodiment described herein. In some embodiments, the flow 200 may be configured to identify and extract information from a social media account. In particular, the flow 200 may be configured to determine if a social media account is associated with the author of a digital document. In these and other embodiments, some or all of the flow 200 may be an example of the operation of system 100 in FIG.

The flow 200 may start at block 210. Here, the digital document 212 may be acquired. Digital document 212 may be obtained from one or more sources, such as a website or other sources. Digital document 212 may include publications, lectures, dissertations or other documents. In some embodiments, the digital document 212 may include a recent document, eg, a document published within a specific time period, such as the last week, month or months.

At block 220, author profile data and topics of all or part of the digital document 212 may be extracted using methods such as topic model analysis. Author profile data about the author in one or more of the digital documents 212 may be extracted and stored in the author object 222. In some embodiments, the author profile data includes the author's full name, author's affiliation, author's title, co-author, author's documentary image, and description of the author's area of expertise or interest. You may be. The affiliation of the author may be related to the company, university or other entity with which the author is associated. The title of the author may include the grade or status of the author. For example, an author may have a PhD, Research Manager, Senior Researcher, Professor, Lecturer and / or other title. To extract author profile data, digital document 212 may be parsed and searched for keywords related to author profile data.

In some embodiments, topic model analysis may be performed on digital document 212. In some embodiments, the topic model analysis may include several topics that can be discerned, the digital document 212 to determine which of those topics is in the digital document 212. It may be analyzed. In these and other embodiments, the topic model analysis may output the word distribution from digital document 212 for each topic. Alternatively or additionally, the word distribution for each digital document may be determined. Thus, one or more topics may be determined for each digital document 212. In some embodiments, one or more of the digital documents 212 may include a plurality of topics. In some embodiments, the topic for each digital document 212 may be stored in the author object 222.

At block 230, social media may be searched for authors from author object 222. In some embodiments, social media may be searched using the author's full name. The author search may identify a social media account 232 that is owned, operated, or may be related to the author of Digital Document 212.

At block 240, social media profile data may be extracted from the social media account 232. Social media profile data may be similar to author data. For example, social media profile data may contain information about who owns, operates, or is associated with that social media account. Anyone who owns, operates, or is associated with a social media account may be referred to as a social media account owner. Social media profile data may include name, affiliation, location, title, specialty, social media image, description of areas of interest and / or other information about the social media account holder. .. In some embodiments, social media profile data is social media that is not a post to a social media account, such as a biography, profile or other information about the person who owns the social media account. • May be collected by parsing and parsing words from the account.

In some embodiments, some social media accounts connected to the social media account 232 may be identified. Alternatively or additionally, the social media account owners of those social media accounts linked to the social media accounts 232 may be identified. In some embodiments, some social media accounts referred to by social media account 232 may be identified. Alternatively or additionally, the social media account owners of those social media accounts referred to by social media accounts 232 may be identified. Information about those owners connected to and / or mentioned in social media accounts 232 may be part of social media interaction data.

In some embodiments, the area of expertise of the social media account holder for one or more of the social media accounts referred to or connected to the social media account 232 is determined. May be good. In these or other embodiments, the mentioned or connected social media accounts may be accessed. The specialty of the owner of the social media account mentioned or connected may be determined. In some embodiments, the discipline may be determined based on the description in the profile of the social media account holder. Alternatively or additionally, the discipline may be determined based on the topic of postings on social media accounts mentioned or connected.

In some embodiments, the topic of posting on social media account 232 may also be determined. Posts shorter than the threshold number of words may be removed to determine the topic of the post. The threshold number of words may depend on the form of social media. For example, if the social media is a microblog, the threshold may be less than the threshold for the blog.

In addition to postings on social media account 232, content linked by postings on social media account 232 is used to determine the topic (s) of social media account 232. May be good. In these and other embodiments, links within posts of social media account 232 may be accessed to collect content. Specifically, the link in the post of the social media account 232, which is a microblog, may be accessed to collect the content. The collected content and posts may be combined. Topic model analysis may be applied to determine the topic distribution of the aggregated content. The topic model may be used to determine the topic distribution for social media accounts 232. In some embodiments, the authors of the content collected from the links in the posts of social media account 232 may also be collected. Social media profile data, social media interaction data and topics may be stored as social media account objects 242.

In block 250, the social media account object 242 associated with the social media account 232, resulting from a search using the author's name from the author object 222, is compared to the author object 222. Generate different scores. Scores include a name score 252, a profile score 254, a content score 256 and an interaction score 258.

The name score 252 may be determined based on a comparison of the name from the author object 222 with the name from the social media account object 242. The name score 252 may be the first value if their names match exactly. If their names match partially, the name score 252 may be the second value, and if the abbreviations of their names match, the name score 252 may be the third score. .. If there is no match between the names, the name score 252 may be 0. Values for the first, second and third scores may be determined based on ad hoc heuristic rules or statistical machine learning.

The profile score 254 may be determined based on one or more comparisons of the following from the author object 222 and the social media account object 242: title, affiliation, specialty description, image. And position. In these and other embodiments, the position of the author from the author object 222 and the position of the social media account owner from the social media account object 242 may be estimated from their respective affiliations. In these and other embodiments, the titles, affiliations, images, descriptions and locations of the authors and social media account holders may be compared.

In some embodiments, the document image from the author object 222 may be analyzed using a face recognition algorithm. For example, the document image from the author object 222 may be the image of the author. Social media images from the social media account object 242 may also be analyzed using a facial recognition algorithm. For example, the social media image from the social media account object 242 may be the image of the owner of the social media account 232. In some embodiments, the results from the analysis of the document image from the author object 222 may be compared to the results from the analysis of the social media image from the social media account object 242. The comparison may give an indicator of the certainty that those images contain the same person. The measure of certainty that those images contain the same person may be used to generate a profile score 254.

In some embodiments, titles, affiliations, discipline descriptions, analysis and location of document images from the author object 222 may be included in the author profile vector. Similarly, titles, affiliations, specialty descriptions, analysis and location of social media images from the social media account object 242 may be included in the social media account profile vector. Author profile vectors and social media profile vectors may be compared using vector space modeling. The result of vector space modeling may be the profile score 254. In some embodiments, the profile score 254 may be based on another collection of comparisons between titles, affiliations, disciplines and locations. For example, each comparison may be given the same or different weights, and the scores of the comparisons may be added together in a linear combination.

The content score 256 is based on a comparison of the topic of the digital document 212 associated with the author from the author object 222 with the main topic of the social media account from the social media account object 242. It may be decided. In some embodiments, the content score 256 may be increased when the author of the linked content in the post matches the author and / or co-author from the author object 222.

In some embodiments, the topic of the digital document 212 associated with the author is associated with the author to compare the main topic of the social media account from the social media account object. Each digital document 212 may be presented in a bag-of-words vector. The centroid vector of the digital documents 212 associated with the author may be determined using the average of the set vectors of the words for the digital documents 212. In some embodiments, each post from the social media account 232 may also be presented as a set vector of words. The centroid vector of all posts in social media account 232 may be determined using the average of all set vectors of words for those posts. A vector space model may be used to calculate the similarity score S_bow between the center of gravity vector of a post in social media account 232 and the center of gravity vector of digital document 212 in author object 222.

In some embodiments, the topic distribution of the entire author's digital document 232 may be used to form the author's topic vector. The topic distribution of all posts in social media account 232 may be used to form the post topic vector. The vector space model may be used to calculate the similarity score S_topic between the author topic vector and the posted topic vector. The number of times the author from the author object 212 is also the author of the document extracted from the link embedded in the post of the social media account may be N_author. In some embodiments, the content score may be expressed by the following equation: a * S_bow + b * S_topic + c * log (N_author + 1). Here, a, b, and c are numbers, and a + b + c = 1.

The interaction score 258 is based on the correlation between the co-author of Digital Document 212 and the social media account owner of the social media account connected and mentioned in social media account 232. It may be decided. In these and other embodiments, the number of social media account owners and co-authors referred to in social media account 232 is determined and may be referred to as the number of mentioned accounts. The number of social media account owners and co-authors connected to the social media account 232 is determined and may be referred to as the number of connected accounts. In some embodiments, the interaction score 258 may be a linear combination of the number of mentioned accounts and the number of connected accounts. In some embodiments, the number of mentioned accounts and the number of connected accounts may each be weighted differently. Weights for the number of mentioned accounts and the number of connected accounts may be determined based on ad hoc heuristic rules and statistical machine learning.

In some embodiments, the interaction score 258 is the number of mentioned accounts, the number of connected accounts, and the social media account ownership of the connected and mentioned social accounts relative to the specialty of the author. It may be determined based on a person's average specialty score and / or content score.

For example, in some embodiments, the number of connected social media accounts identified as co-authors may be expressed as N_connected. The number of mentioned social media accounts identified as co-authors may be expressed as N_listed. The average discipline score and / or content score between the author and other connected social accounts may be expressed as S_average_connected. The average discipline score and / or content score between the author and other mentioned social accounts may be represented by S_average_mentioned.

In these and other embodiments, the interaction score 258 may be based on the following equation: P1 * log (N_connected + 1) + P2 * log (N_list + 1) + P3 * S_average_connected + P4 * S_average_mentioned. Here, P1, P2, P3, and P4 are numbers, and P1 + P2 + P3 + P4 = 1.

In block 260, whether the social media account owner of social media account 232 is the same as the author from author object 222 has a name score of 252, a profile score of 254, a content score of 256, and mutual. It may be determined using the action score 258. In some embodiments, the determination may be based on a linear combination of a name score 252, a profile score 254, a content score 256 and an interaction score 258. For example, when the linear combination of name score 252, profile score 254, content score 256, and interaction score 258 is above the threshold, the social media account owner of social media account 232 is the author object 222. It may be determined that it is the same as the author from. In some embodiments, the threshold may be determined based on the previous authentication of the matches. For example, a plurality of successive iterations of the flow 200 may be determined for different authors, or a match may be determined outside the flow 200. A threshold score at a particular confidence level may be selected based on those multiple sequential iterations.

In some embodiments, the name score 252, profile score 254, content score 256 and interaction score 258 may each be weighted differently. In these and other embodiments, the weights for different scores may be determined using statistical machine learning or some other algorithm. For example, machine learning algorithms may be trained on the basis of pre-determined matches and mismatches. After training, the machine learning algorithm may receive each of the individual scores as input, weighted to those scores and linearly combined, and the social media account owner of social media account 232. May determine the certainty that is the same as the author from the author object 222. In some embodiments, the machine learning algorithm matches when the certainty that the social media account owner of the social media account 232 is the same as the author from the author object 222 is above the threshold. It may be shown that there is. In some embodiments, the threshold may be user-selected or otherwise determined based on the previous experience or sequential iteration of the flow 200.

The flow 200 may be modified, added or omitted without departing from the scope of the present disclosure. For example, in some embodiments, the flow 200 may include multiple social media accounts 232. In these and other embodiments, a social media account object 242 may be generated for each social media account 232, and the author object 222 may generate a respective social media object 222 to determine a match. It may be compared individually to the account object 242. In some embodiments, if the author is determined to be the owner of a single social media account 232 social media account, the social media accounts resulting from a search for that author. For 232, no other social media account object 242 may be generated.

In some embodiments, the social media account object 242 for each of the different social media accounts 232 may be determined prior to comparison with the author object 222. Alternatively or additionally, a work associated with the author who generated the social media account object 242 of a single social media account 232 and then resulted in the single social media account 232. Comparisons with the author object 222, scores generated, and a match determination may be made before the other social media account object 242 is generated.

In some embodiments, the digital document 212 may include multiple authors. In these and other embodiments, author profile data for each author may be collected and used to generate different author objects 222. A social media search may be performed for each of the different author objects 222. In short, the flow 200 is merely an example of a data flow for identifying and extracting information, and the present disclosure is not limited thereto.

3a and 3b show a flow chart of an exemplary method 300 for identifying and extracting information based on at least one embodiment described herein. In some embodiments, one or more of the actions associated with method 300 may be performed by the information gathering system 110. Alternatively or additionally, the method 300 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 300. Although illustrated as discrete blocks, the steps and behavior associated with one or more of the blocks in Method 300 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

Method 300 may start at block 302. Here, the processing system may be used to obtain multiple digital documents from one or more sources. Digital documents may include recent documents, such as those published within a particular recent time period, such as the last week, month or months. At block 304, the topic of each digital document may be determined using topic model analysis.

At block 306, the author of the digital document may be determined. In some embodiments, author determination may include extracting the names of people indicated as authors in a digital document. In these and other embodiments, a digital document may be parsed and searched for a word indicating that a name is the author of the digital document. In some embodiments, author objects may be obtained from the database for each author. In some embodiments, obtaining an author object may include creating an author object, or searching for and locating an existing author object in a database having the same name.

In block 308, the author may be selected. Block 310 may provide metadata about the selected author. In some embodiments, the metadata may be obtained from digital documents including its author. In some embodiments, the metadata may be the topic of author profile data and various digital documents including the author. Metadata may be stored in the author object associated with that author.

At block 312, social media may be selected. In block 314, the selected social media may be searched using the name of the selected author. The search may return multiple social media accounts that may be related to the author. At block 316, one of those social media accounts may be selected.

At block 318, social media account metadata for the selected social media account may be obtained. In some embodiments, social media account metadata may be obtained from selected social media accounts. In some embodiments, the social media account metadata is the social media account profile data and posting topics (s), linked documents, and links for the selected social media account. It may be another aspect. Social media account metadata may be stored in the author object associated with the selected social media account.

At block 320, scores may be generated based on a comparison between the selected social media account and the selected author. In some embodiments, those scores may be generated based on a comparison of the social media account object and the author object. In some embodiments, the score may include one or more of a name score, a profile score, a content score and an interaction score.

At block 322, it may be determined if there are other social media accounts that have not yet been selected as a result of the social media search in block 314. When there are other unselected social media accounts, method 300 may proceed to block 316, where another of the unselected social media accounts may be selected. If there are no other unselected social media accounts, Method 300 may proceed to block 324.

In block 324, whether the selected author is the social media account owner of the selected social media account is determined using the score generated for each social media account in block 320. May be done. In some embodiments, which of the social media account owners of the selected social media account is the selected author is the score generated for each social media account. It may be determined by comparison. In these and other embodiments, the social media account with the highest score may be determined to be the social media account of the selected author. Alternatively or additionally, a social media account with a score higher than a certain selection threshold may be determined to be the social media account of the selected author. The selection threshold may be based on machine learning, previous experience, although there are other types of analysis. If the selected author is the social media account owner of one of the selected social media accounts, the selected author and the selected social media account. The one of the social media accounts may be associated in a database containing an author object and a social media account object.

At block 326, it may be determined if there are other social media that have not yet been selected in block 312. For example, method 300 may be configured to match the author with a social media account in a plurality of different social media. If there are other unselected social media, method 300 may proceed to block 312 and another of the unselected social media may be selected. If there are no other unselected social media, method 300 may proceed to block 328.

At block 328, it may be determined whether there are other authors from the digital document identified in block 306 that have not yet been selected. If there are other unselected authors, method 300 may proceed to block 308 and another of the unselected authors may be selected. If there are no other unselected authors, method 300 may proceed to block 330.

At block 330, new posts in the social media account associated with the author in the database may be extracted. To extract new posts, the database may contain network addresses for social media accounts. The system will use that network address to navigate to your social media account, postings from a recent time period, or last if there are posts previously extracted from your social media account. Posts may be extracted after the post is extracted.

In block 332, the information extracted from the new post may be organized. In some embodiments, the information may be organized based on the discipline of the author associated with the social media account from which the information was extracted.

At block 334, organized data may be provided based on the discipline of the author associated with those social media accounts. In some embodiments, the information may be provided through a web page.

Those skilled in the art will appreciate that for this process and method and other processes and methods disclosed herein, the functions performed in those processes and methods may be implemented in different order. Moreover, the steps and actions outlined are given merely as examples, and some of the steps and actions are optional or a smaller number of steps and actions without compromising the essence of the disclosed embodiments. It may be combined with an action or expanded into additional stages and actions.

FIG. 4 is a flow chart of an exemplary method 400 for identifying and extracting information, based on at least one embodiment described herein. In some embodiments, one or more of the actions associated with method 400 may be performed by the information gathering system 110. Alternatively or additionally, method 400 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 400. Although illustrated as discrete blocks, the steps and behavior associated with one or more of the blocks in Method 400 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

Method 400 may start with block 402. Here, for each author of a plurality of digital documents, an author object may be generated in the database. Multiple digital documents may be obtained from one or more sources. In some embodiments, the author profile data may include the title of the author, the affiliation of the author, the area of expertise of the author, and the location of the author. In some embodiments, the generation of the author object may include extracting the name, author profile data and co-authors from the digital document.

At block 404, an indication of various social media accounts in a social media may be obtained. The instructions may be based on a search for the name of the author in the author object on the social media.

In block 406, even if a name score is generated based on a comparison of the name from the author object with the social media name from the social media account object generated based on the social media account. good.

At block 408, a profile score may be generated based on a comparison of author profile data from the author object with social media profile data from the social media account object. In some embodiments, the comparison of author profile data with social media profile data uses author profile data to build an author vector and uses social media profile data. It may include constructing a social media vector and calculating the similarity between the author vector and the social media vector. Here, the calculated similarity is the profile score.

In block 410, even if a content score is generated based on a comparison of topics from posts in social media accounts and topics about each of the digital documents associated with the author from the author object. good.

At block 412, interaction scores may be generated based on the social connection in the social media account and the evaluation of the co-authors for each of the digital documents associated with the author from the author object.

At block 414, whether the social media account is associated with the author of the author object may be determined based on the name score, profile score, content score and interaction score. In some embodiments, determining whether the social media account is related to the author of the author object is based on the name score, profile score, content score, and interaction score. It may include assigning weights to each of the name score, profile score, content score and interaction score. The verdict further linearly combines a weighted name score, a weighted profile score, a weighted content score, and a weighted interaction score, and applies the linear combination to a machine learning algorithm to ensure its social. It may include determining if the media account is associated with the author of the author object.

At block 416, data may be extracted from new posts from social media accounts associated with the author of each author object. Block 418 may provide the data organized on the topic of a digital document.

For example, method 400 may further include determining a topic from posts on social media accounts. In some embodiments, topic determination may include removing posts shorter than the threshold number of words and retrieving content from embedded links within the post. Discrimination of topics may further include summarizing the content and discriminating the topic distribution of the summarized content.

In some embodiments, the method 400 may further comprise obtaining the plurality of digital documents from one or more sources and determining the topic of each digital document using topic model analysis. ..

FIG. 5 is a flow chart of an exemplary method 500 for identifying and extracting information, based on at least one embodiment described herein. In some embodiments, one or more of the actions associated with method 500 may be performed by the information gathering system 110. Alternatively or additionally, Method 500 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 500. Although illustrated as discrete blocks, the steps and behavior associated with one or more of the blocks of Method 500 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

Method 500 may start with block 502. Here, for each author of a plurality of digital documents, an author object may be generated in the database. Multiple digital documents may be obtained from one or more sources. In some embodiments, the author profile data may include the title of the author, the affiliation of the author, the area of expertise of the author, and the location of the author. In some embodiments, the generation of the author object may include extracting the name, author profile data and co-authors from the digital document.

At block 504, an indication of social media accounts on a social media may be obtained based on a search for the name of the author in the author object on the social media.

At block 506, whether the social media account is associated with the author of the author object may be determined based on two or more of the following: name score, profile score, content. -Scores and interaction scores.

In some embodiments, determining whether the social media account is associated with the author of the author object is based on name score, profile score, content score and interaction score. Weights are assigned to each of the name score, profile score, content score, and interaction score, and the weighted name score, weighted profile score, weighted content score, and weighted interaction score are linearly combined. May include doing. The determination may also include applying the linear combination to a machine learning algorithm to determine if the social media account is associated with the author of the author object.

In some embodiments, the name score is generated based on a comparison of the name from the author object with the social media name from the social media account object generated based on the social media account. May be done.

In some embodiments, the profile score may also be generated based on a comparison of author profile data from the author object with social media profile data from the social media account object. good. In some embodiments, the comparison of author profile data with social media profile data uses author profile data to build an author vector and uses social media profile data. It may include constructing a social media vector and calculating the similarity between the author vector and the social media vector. In some embodiments, the calculated similarity may be a profile score.

In some embodiments, the content score is generated based on a comparison of topics from posts in social media accounts with topics about each of the digital documents associated with the author from the author object. May be done.

Interaction scores may be generated based on social connections in social media accounts and co-author ratings for each of the digital documents associated with the author from the author object.

For example, Method 500 may further include determining a topic from posts on social media accounts. In some embodiments, topic determination removes posts shorter than the threshold number of words, retrieves content from embedded links within the post, summarizes the content, and determines the topic distribution of the summary content. It may be included.

<Mutual verification of social media accounts and personal academic web pages>
In one or more embodiments, the disclosure may include cross-validation of social media accounts with personal academic web pages. For example, when determining whether a social media account among multiple candidate social media accounts actually belongs to a person, that person's personal academic web page and that person's social media account. However, it may contain common information or other aspects that can mutually verify the two. It can be assured that both are certainly related to the person. An exemplary implementation of the use of such mutual validation is described in more detail in FIGS. 6-15.

FIG. 6 shows a diagram of an exemplary flow 600 that can be used for the identification and extraction of information based on one or more embodiments of the present disclosure. In some embodiments, the flow 600 may be configured to identify and extract information from a social media account. In particular, Flow 600 may be configured to determine if a social media account and / or personal academic web page is associated with the author of the digital document. In these and other embodiments, a portion of the flow 600 may be an example of the operation of system 100 in FIG.

Flow 600 may include blocks 610, 612, 620, 622, 630 and 632, which may be similar to or equivalent to blocks 210, 212, 220, 222, 230 and 232 of FIG. 2, respectively. .. The full description of the corresponding blocks with reference to FIG. 2 is equally applicable to these blocks of FIG.

With reference to block 640, social media profile data may be extracted from the social media account 632. Social media profile data may be similar to author data. For example, social media profile data may include information about who owns, operates, or is associated with a social media account. Anyone who owns, operates, or is associated with a social media account may be referred to as a social media account owner. Social profile data may include name, affiliation, location, title, specialty, social media image, personal web page URL or area of interest description and other information about the social media account holder. good. In some embodiments, social profile data is a social media account that is not a post to a social media account, such as a biography, profile or other information about the person who owns the social media account. Words from may be collected by parsing and parsing.

In some embodiments, some social media accounts connected to the social media account 632 may be identified. Alternatively or additionally, the social media account owners of those social media accounts linked to the social media accounts 632 may be identified. In some embodiments, some social media accounts may be identified that are informed by the social media account 632. Alternatively or additionally, the social media account owner of the social media account followed by the social media account 632 may be identified. In some embodiments, the first social media account that obtains information from the second social media account is such that the first social media account follows the second social media account. The second first social media account may be referred to as being followed by the first social media account.

In some embodiments, the area of expertise of the social media account holder for one or more of the social media accounts referred to or connected to the social media account 632 is determined. May be good. In these or other embodiments, connected social media accounts may be accessed. The specialty of the owner of the connected social media account may be determined. In some embodiments, the discipline may be determined based on the description in the profile of the social media account holder. Alternatively or additionally, the discipline may be determined based on the topic of posting in a connected social media account.

In some embodiments, the topic of posting on the social media account 632 may also be determined. Posts shorter than the threshold number of words may be removed to determine the topic of the post. The threshold number of words may depend on the shape of social media. For example, if the social media is a microblog, the threshold may be less than the threshold for the blog.

In addition to postings on social media account 632, content linked by postings on social media account 632 is used to determine the topic (s) of social media account 632. May be good. In these and other embodiments, links within posts of social media account 632 may be accessed to collect content. Specifically, the link in the post of the social media account 632, which is a microblog, may be accessed to collect the content. The collected content and posts may be combined. Topic model analysis may be applied to determine the topic distribution of the aggregated content. The topic model may be used to determine the topic distribution for social media accounts 632. In some embodiments, the author of the content collected from the link in the post of social media account 632 may also be collected. Social media profile data, social media interaction data and topics may be stored as social media account objects 642.

At block 650, a search may be performed for a personal scholarly web page 652 that may be a candidate for the author's personal scholarly web page. For example, a general search engine may be required to perform a search for a web page based on the name of each author in the author object 622. Additional or alternative, a general search engine may be required to perform a web page search based on the name of each author in the author object 622 and the affiliation of the author in the author object 622. For example, when parsing Digital Document 612, if the author name of Andrew Ng was found along with his affiliation with Stanford University, then "Andrew Ng" and "Stanford University". A search may be performed on a combination of items from (Stanford University). The results of the above two searches may be merged by combining the two lists and removing any duplicates to generate a list of possible personal academic web pages 652. In some embodiments, a limited number of top results, such as the top 10 results from each search, may be included as candidates, and then their list may be merged.

In some embodiments, after merging the results, one or more specific social media or other profile-based pages may be identified. For example, Google Scholar pages, LinkedIn pages, ResearchGate pages and / or other profile-based pages based on templates for others. May be identified. Such identified pages may be removed from the list of potential candidates. In addition or alternatives, such pages may be used as social media accounts in cross-validation or as potential candidates for personal academic web pages. In some embodiments, the merged search results of the web page may be analyzed to identify what result is the personal academic web page 652. For example, the content of a particular web page may be parsed and analyzed to classify the page and determine if it is a personal academic web page 652. An exemplary method 900 for describing such an analysis is described with reference to FIGS. 9a and 9b.

With reference to block 660, the candidate site identified as personal academic web page 652 in block 650 may be used to extract information for generating personal academic web page object 662. For example, various features or aspects of the personal academic web page 652 may be parsed and added as data in the personal academic web page object 662. In some embodiments, some of the data in the personal academic web page object 662 may be similar to or equivalent to that of the author object 622. For example, personal academic web page data may contain information about who owns, operates, or is associated with a web page. Personal academic web page data also includes names, affiliations, locations, titles, disciplines, author photographic images, publications, resumes, classes or classes of persons associated with personal academic web pages. It may include a lecture, a description of the area of interest, a social media account, contact information, a URL and / or other information.

In block 670, the social media account object 642 associated with the social media account 632 resulting from a search using the author's name from the author object 622 uses one or more cross-validation techniques. And may be cross-validated with one or more of the personal academic web page objects 662 associated with the personal academic web page 652. For example, the social media account object 642 and a given web page object 662 have a URL match 671 (the exemplary method is described with reference to FIG. 10), a social media account match 672 (the exemplary method). Is described with reference to FIG. 11), Photo Match 673 (the exemplary method is described with reference to FIG. 12), Keyword Match 674 (the exemplary method is described with reference to FIG. 13) and / or linked. Mutual verification may be performed using the social media keyword match 675 (an exemplary method is described with reference to FIG. 14). In some embodiments, these different cross-validation techniques are sequentially ordered until mutual validation is established, eg ULR match 671, social media account match 672, photo match 673, keyword match 674 and linked social. -May be used in media keyword match 675. In these and other embodiments, a single mutual validation in ensuring that the personal academic web page object 662 and the social media account object 242 are correctly associated with a given author object 222. Techniques may be used, or all cross-validation techniques may be used. Alternatively or additionally, two or more of the above cross-validation techniques may be used in parallel.

With reference to block 680, a match is determined between the author object 622, a given social media account object 642 and a given personal academic web page object 662, based on the cross-validation of block 670. You may. A match in block 680 may indicate that a given social media account object 642 and a given personal academic web page object 662 are correctly associated with the author object 622. For example, if one or more of the above cross-validation techniques ensure that the author is the same person who owns the social media account and the personal academic web page, a match is found. Can be done. In some embodiments, the presence or absence of a match may be determined on the basis of previous mutual verification of the match. For example, a plurality of successive iterations of the flow 600 may be determined for different authors, or a match may be determined outside the flow 600. In some embodiments, if none of the above cross-validation techniques identify the social media account and personal academic web page associated with the author, as described, for example, with respect to Flow 200 in FIG. , Only social media accounts may be compared to author objects.

Flow 600 may be modified, added or omitted without departing from the scope of the present disclosure. For example, in some embodiments, the flow 600 may include a plurality of social media accounts 632 and / or a plurality of personal academic web page objects 662. In these and other embodiments, a social media account object 642 may be generated for each social media account 632, and a personal academic web page object 662 may be generated for each personal academic web page 652. The various combinations may be individually cross-validated to determine a match. For example, a single social media account object 642 may be cross-validated with the personal academic web page object 662 until a match is found, followed by the next social media account object 642. It may be cross-validated with the personal academic web page object 662 and vice versa (eg, the personal academic web page object 662 is cross-validated with various social media account objects 642).

In some embodiments, the social media account object 642 for each of the different social media accounts 632 and / or the personal academic web page object 662 for each of the different personal academic web pages 652 is cross-validated. It may be decided earlier. Alternatively or additionally, a single social media account 632 social media account object 642 and / or a single personal academic web page object 662 may be generated and then cross-validated. , Other social media account objects 642 and / or personal academic web page objects 662 may be done before they are created.

In some embodiments, the digital document 612 may include multiple authors. In these and other embodiments, author profile data for each author may be collected and used to generate different author objects 622. A social media search may be performed for each of the different author objects 622. In short, the flow 600 is merely an example of a data flow for identifying and extracting information, and the present disclosure is not limited thereto.

FIG. 7 shows a flowchart of an exemplary method 700 for identifying and extracting information based on at least one embodiment described herein. In some embodiments, one or more of the actions associated with method 700 may be performed by the information gathering system 110. Alternatively or additionally, the method 700 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 700. Although illustrated as discrete blocks, the stages and behaviors associated with one or more of the blocks in Method 700 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

At block 710, author objects may be created in the database. For example, an information gathering system (such as the information gathering system 110 of FIG. 1) may obtain one or more publications from a publication system (such as the publication system 120 of FIG. 1). Publications may be parsed and analyzed to extract author profile data for the author of the publication and the author. In these and other embodiments, the author profile data may include one or more of the title of the author, the affiliation of the author, the description of the area of expertise of the author, and the position of the author. .. In some embodiments, the generation of the author object may include extracting the name, author profile data, any image of the author, and co-authors from the digital document. Additional or alternative, the author object may also contain topics related to the publication. For example, one or more keywords of a publication may be added to a topic for which the author is knowledgeable about it.

At block 720, for a given author, personal scholarly web page candidates may be obtained that include the possibility of being associated with that author. For example, an information gathering system is one of the web pages in which a common search engine is hosted on a web hosting system (eg, the web hosting system 150 in Figure 1), the author's name and / or its authorship. You may request to perform a search for the author's name and the affiliation of the author. Additional or alternative, another based on one or more items related to the author, such as the author's title (eg, Dean), description of the author's area of expertise and / or other items. Search may be used. Any number of searches may be performed. In some embodiments, the number of searches may be less than five. In some embodiments, the results of those searches may be merged to remove one or more types of web pages from the list, such as Google Scholar pages or LinkedIn pages. The remaining results may be parsed or otherwise analyzed to determine which of those results are personal academic web pages, and the results that are personal academic web pages are candidates for personal academic web pages. May be included as. In these and other embodiments, data is extracted from personal academic web page candidates to generate personal academic web page objects. An exemplary method of obtaining a personal academic web page is shown in FIG. 8, and an exemplary method of determining which of the results is a personal academic web page is shown in FIGS. 9a and 9b.

Block 730 may provide potential social media accounts for a given author, including possible associations with that author. For example, the information gathering system may require that the search be performed among one or more social media systems (eg, social media system 130 in FIG. 1). Such searches may be performed based on the name of the author, and may additionally or alternatively include one or more items related to the author in other ways. In addition, such searches may be performed on multiple social media platforms that span multiple social media systems. The returned results may include potential social media accounts. Social media account objects may be generated for those social media account candidates. This is, for example, by parsing the profile of a candidate social media account and / or otherwise extracting various components of the information as social media account data.

In block 740, one of the personal scholarly web page candidates and one of the social media account candidates may be cross-validated as related to a given author. For example, using one or the other of the cross-validation techniques described in FIGS. 10-14, the information gathering system is such that a given personal academic web page and social media account are given authors. Can be confirmed to be correctly related to. In some embodiments, a series of cross-validation techniques may be used. For example, use the first technique and proceed to the next technique if the first technique does not determine a match between a candidate social media account and a candidate personal academic web page. For example, an information gathering system first uses a URL matching technique, then a social media account matching technique, then a photo matching technique, then a keyword matching technique, and then a linked social media keyword matching technique. In some embodiments, block 740 may proceed through multiple cross-validation techniques and obtain results for each cross-validation technique before making a final decision on cross-validation. In these and other embodiments, block 740 may include each of the cross-validation techniques of FIGS. 10-14.

In some embodiments, block 740 may start with one social media account candidate and cross-validate it against each of the personal academic web page candidates until a match is found. Alternatively, block 740 may start with one personal academic web page candidate and cross-validate it against each of the social media account candidates until a match is found. At the end of block 740, social media accounts and personal scholarly web pages may be associated with a given author.

In some embodiments, a given author may have more than one personal academic web page and / or more than one social media account. For example, for a writer who is a faculty member at a university and a consultant at a company, the author is a university-hosted personal scholarly web page, a company-hosted personal scholarly web page, and an individual-hosted personal scholarship. May have a web page. In addition or alternatives, the author may have a Twitter account, Instagram account and Facebook account. In these and other embodiments, the disclosure may cross-validate two or more personal academic web pages against two or more social media accounts. In these and other embodiments, the one or more processes described in this disclosure will not terminate once one social media account has been cross-validated against one personal academic web page. It may proceed through all social media account candidates and / or all personal academic web page candidates. In these and other embodiments, all social media accounts and personal scholarly web pages that have been reciprocally validated as being related to an author may be associated. In addition or alternatives, a single social media account and / or a single personal scholarly web page may be associated with the author. For example, a preference for a Twitter account may be given over a Facebook account. As another example, university-hosted web pages may be given a preference over personally-hosted web pages.

At block 750, it may be determined if there are additional authors left unanalyzed to associate social media accounts and personal scholarly web pages with further authors. After determining that there are remaining authors, Method 700 may return to block 720 to obtain personal scholarly web page candidates for the next author. After determining that there are no remaining authors, method 700 may proceed to block 760.

At block 760, new social media posts from the social media account associated with the author may be extracted. For example, to extract new posts, the social media object and / or author object may include a network address for the social media account. The information gathering system will use its network address to navigate to your social media account, if there are posts from a recent time period or previously extracted from your social media account. Posts after the last post extraction may be extracted. In these and other embodiments, the information extracted from the new post may be organized. In some embodiments, the information may be organized based on the area of expertise of the author associated with the social media account from which the information was extracted, eg, a topic they are familiar with.

At block 770, organized data may be provided, for example, by topical organization, based on the discipline of the author associated with those social media accounts. In some embodiments, the information may be provided through a web page. Additionally or alternatively, the information may be collected in a collection of social media accounts, such as social media accounts linked to the author, or by a knowledgeable social media account owner. It may be communicated to another set.

FIG. 8 shows a flow chart of an exemplary method 800 for identifying a personal academic web page, based on at least one embodiment described herein. Although one author will be described, Method 800 may be repeated for any number of authors. Method 800 may reflect one embodiment of performing one or more operations of block 720 of FIG. In some embodiments, one or more of the actions associated with method 800 may be performed by the information gathering system 110. Alternatively or additionally, Method 800 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 800. Although illustrated as discrete blocks, the steps and behavior associated with one or more of the blocks of Method 800 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

The dashed arrow leading to block 810 indicates that method 800 may be a continuation of another method, such as continuing from block 710 of method 700 of FIG.

In block 810, even if the first search for possible personal academic web pages is performed based on the name of the author, for example, based on the name of the author in the author object generated in block 710. good. For example, an information gathering system (eg, information gathering system 110) is a web page hosted by one or more web hosting systems (eg, web hosting system 150 in FIG. 1) based on the author's name. You may ask a common search engine to perform a search for. The results may be included in the first list. The number of results included in the first list may be limited or censored based on numerical values or any other criterion.

At block 820, a second search for possible personal academic web pages may be performed based on the author's name and author's affiliation. For example, information gathering systems require common search engines to perform searches for web pages hosted by one or more web hosting systems based on the author's name and affiliation. You may. The results may be included in the second list. The number of results included in the second list may be limited or censored based on numerical values or any other criteria. In some embodiments, the sizes of the first list and the second list may be the same size or different sizes. Additional or alternative, other search items may be used, and / or additional searches may be performed to generate additional lists in addition to the first and second lists. For example, a search may be performed that includes the title and author name of the publication, or that uses any other author data of the author object.

At block 830, the results from the first search and the second search may be merged. For example, the results are in every other way (eg, result 1 from the first list, result 1 from the second list, result 2 from the first list, result 2 from the second list, first. Results from the list of 3 and / or others) or any other combination technique may be combined. In some embodiments, the merged list may be duplicated.

At block 840, one or more social media accounts may be identified as profile pages based on the social media account's profile page template. For example, the above results may be with known templates for one or more social media account profiles for social media accounts such as LinkedIn pages, ResearchGate pages or Google Scalar pages. May be compared. One or more of the above results are analyzed to determine the format, including the location and style of one or more web elements, and compared to the known layout and / or format of the template social media page. May be good. After identifying the page as such a social media page, the social media page may be added to the list of personal academic web page candidates and removed from the merged list of search results. In some embodiments, such social media account pages may be limited to academic or business-based social media accounts.

At block 850, a given result from the list of results may be parsed to identify whether the given result is a personal academic web page. For example, various text or visual elements of a given result may be parsed and analyzed to determine if those text and / or visual elements are consistent with a personal academic web page. .. Based on the given result being a personal academic web page, the given result may be included in the list of personal academic web page candidates. Examples of methods that can be used to parse the results to identify whether the results are personal academic web pages are described with respect to FIGS. 9a and 9b. Another example of a method that can be used to parse a result to identify whether it is a personal academic web page is described for US Patent Application No. 13 / 732,036 (including, eg, FIG. 6). Has been done. The entire US Patent Application No. 13 / 732,036 is incorporated herein by reference.

At block 860, it may be determined whether any further results remain to be parsed and whether or not the results are personal academic web pages should be determined. After determining that there are further results, Method 800 may return to block 850 and the next result may be parsed to determine if the result is a personal academic web page. After determining that there are no remaining results that have not yet been parsed, Method 800 may output the resulting consequential personal scholarly web page candidates.

The dashed arrow at the end of method 800 may indicate that those personal web page candidates may be used by one or more additional processes or blocks, such as block 730 of method 700 of FIG.

In some embodiments, instead of identifying the social media account in block 840, method 800 may proceed directly to parsing the results.

9a and 9b show a flow chart of another exemplary method 900 that can be used in the identification and extraction of information, based on one or more embodiments of the present disclosure. For example, FIGS. 9a and 9b show a flowchart of an exemplary method 900 that parses one or more web pages and determines if the web page is a personal academic web page. Although one web page will be described, Method 900 may be repeated for any number of web pages. Method 900 may reflect one embodiment of performing one or more operations of block 850 of FIG. In some embodiments, one or more of the actions associated with method 900 may be performed by the information gathering system 110. Alternatively or additionally, Method 900 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 900. Although illustrated as discrete blocks, the stages and behaviors associated with one or more of the blocks in Method 900 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

Referring to FIG. 9a, the dashed arrow leading to block 905 indicates that method 900 may be a continuation of another method, such as continuing from block 840 of method 800 of FIG.

At block 905, web page results may be analyzed. Web page analysis may give a keyword score associated with the resulting content. Block 905 may include one or more of blocks 910, 915, 920 and 925 and may include one or more actions that may be included in analyzing web page results.

At block 910, web pages may be fetched. For example, an information gathering system (eg, information gathering system 110 in FIG. 1) may request a web page from a web hosting system (eg, one of the web hosting systems 150 in FIG. 1) through a network. You may communicate.

At block 915, the computer-readable code of the web page may be parsed to identify one or more blocks of information contained in the web page. For example, the code used by a computer to display a web page may be parsed to determine the location of fields that may contain blocks of information. In some embodiments, the web page is a hypertext markup language (HTML), an extensible hypertext markup language (XHTML), an extensible markup language (XML), a cascading style sheet (CSS), It may be presented using any other language or technique used to provide computer-readable code that describes Javascript and / or web pages. In some embodiments, the code may be parsed to identify text blocks with more words than the threshold number. As another example, search for text blocks with titles such as "publications", "interests", "contact information", "summary" and / or others. May be done.

In block 920, keywords may be extracted from the information block identified in block 915. For example, a word in an information block may be compared to one or more topics identified by an information gathering system, or to another list of keywords associated with one or a topic. As another example, certain types of words may be removed from the words in the information block (eg, "a", "the", "interested", "enjoy". ), "University," "department," and / or others), the remaining words may be sorted. Additional or alternative, any other keyword extraction technique may be used.

At block 925, keyword scores may be generated based on the extracted keywords. For example, the keyword score is the number of identified keywords (such as a score that reflects the finding of eight keywords), and the number of keywords for a particular topic among all keywords (for example, 12 for a topic). Keyword frequency (such as a score that reflects that 8 of the keywords were found), keyword frequency (such as a score that reflects that a quarter of the words used in the information block were keywords for a topic), and / Or other may be represented.

At block 930, one or more anchor texts of the result may be parsed. The anchor text may include visible text associated with the hyperlink. For example, anchor text can be highlighted, bolded, underlined, or otherwise formatted to indicate that the text is related to a hyperlink. Anchor text analysis can give an anchor text score based on the anchor text. Block 930 may include one or more of blocks 935, 940 and 945 and may include one or more actions that may be included in parsing the anchor text.

At block 935, one or more anchor texts may be identified within the resulting web page. For example, the results web page may be parsed to identify all hyperlinks in the results. Visible text associated with hyperlinks may be identified as anchor text.

At block 940, the anchor text of the resulting web page may be searched for one or more text elements. For example, anchor text may be searched for the name of the author. As another example, the anchor text may be searched for keywords related to one or more topics and / or the one or more topics. In these and other embodiments, the anchor text may be categorized based on what the anchor text identifies. For example, if the anchor text is a person's name, it may be categorized as a "name."

At block 945, an anchor text score may be generated. In some embodiments, the anchor text score may be based on the name in the anchor text corresponding to the author's name, the keywords in the anchor text, the category to which the anchor text belongs and / or others. .. For example, the anchor text score has one anchor text with the author's name, two anchor texts with keywords within the anchor text, and two additional keywords within the topic-related categories. It may reflect that.

With reference to FIG. 9b, in block 950, the URL of the result may be parsed. The URL may give a URL score based on the URL. Block 950 may include one or more actions that may be included in parsing the URL, including blocks 955, 960 and 965.

At block 955, the resulting URL may be split into fragments. For example, for a URL containing online.stanford.edu / instructors / andrew-ng, this URL may be decomposed into "online", "stanford.edu", "instructors" and "andrew-ng". In these and other embodiments, special characters such as ~,-, * and / or others may be removed from the fragments or used as delimiters between fragments. In some embodiments, URL fragments may be categorized in a manner similar to anchor text. For example, the fragment "andrew-ng" may be categorized as a name category and the fragment "stanford.edu" may be categorized as an affiliation or entity.

At block 960, fragments may be searched for names and / or keywords. For example, a fragment may be searched for all or part of the author's name. Additional or alternative, fragments may be searched for keywords related to a topic or a topic. For example, an author may have one or more topics that the author has published about it, and keywords related to that topic may be searched among the fragments.

At block 965, a URL score may be generated. In some embodiments, the URL score may be based on the name within the fragment corresponding to the author's name, the keywords within the fragment, the category to which the fragment belongs and / or others. For example, the fragment score may reflect that there is one fragment with the author's last name.

At block 970, the resulting web page may be categorized as a personal academic web page or another type of web page based on the keyword score, anchor text score and / or URL score. In some embodiments, the keyword score, anchor text score, and URL score may each contain a number between 0 and 1, and the sum of all potentially possible scores is equal to 1. .. In addition, different scores may be weighted differently. For example, the URL score may have a greater weight than the anchor text score. Each score can have a possible value of 0.3333 if all of those scores are weighted equally. In some embodiments, a machine learning engine may be utilized in the categorization of web pages. For example, one or more known personal academic web pages are positive for a machine learning engine so that the machine learning engine can identify different features and / or commonalities of personal academic web pages. It may be provided as training data. As another example, one or more web pages that are known not to be personal academic web pages may be provided as negative training data for a machine learning engine. In these and other embodiments, the machine learning engine may generate a classification algorithm based on the positive and / or negative training data received.

In some embodiments, the various scores can be an expression of how similar the analyzed aspects of the resulting web page to a typical personal academic web page. For example, most scholarly web pages may contain descriptions of a person's research projects and interests, descriptions of subjects and lectures offered by that person, descriptions of publications by that person and / or others. Keyword scores, anchor text scores and URL scores can collectively and / or individually reflect how likely it is that the resulting web page will contain features of those types.

In some embodiments, rather than using scores, the results are categorized based on one or more of the keywords extracted in block 920, the anchor text identified in block 935, or the fragments of block 955. May be done. Additional or alternative, the categorization may be based on the categorization in which the keyword, anchor text or fragment is categorized.

In some embodiments, the result is one of a plurality of categories such as social media pages, personal academic web pages, project websites, business entity websites, academic department websites and / or others. It may be classified into one category.

At block 975, a determination may be made as to whether the result was categorized as a personal academic web page at block 970. If the results are categorized as personal academic web pages, method 900 may proceed to block 980 and the resulting web pages are added as personal academic web page candidates. If the results are not categorized as a personal academic web page, Method 900 may proceed to the dashed arrow at the end of Method 900.

The dashed arrow at the end of Method 900 may indicate that the personal web page candidate identified in Method 900 may be used by one or more additional processes or blocks, such as Block 860 of Method 800 in FIG. ..

FIG. 10 shows a flowchart of an exemplary method 1000 that can be used in mutual validation of social media accounts and personal academic web page candidates based on one or more embodiments of the present disclosure. Although one social media account candidate will be described, Method 1000 may be repeated for any number of social media account candidates. Method 1000 may reflect one embodiment of performing one or more operations of block 740 of FIG. In some embodiments, one or more of the actions associated with method 1000 may be performed by the information gathering system 110. Alternatively or additionally, Method 1000 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 1000. Although illustrated as discrete blocks, the steps and behaviors associated with one or more of the blocks in Method 1000 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

The dashed arrow leading to block 1010 indicates that method 1000 may be a continuation of another method, such as continuing from block 730 of method 700 of FIG. Additional or alternative, the dashed arrow may be a continuation of one or more of the method 1100 of FIG. 11, the method 1200 of FIG. 12, the method 1300 of FIG. 13 or the method 1400 of FIG.

At block 1010, profiles of potential social media accounts may be fetched. For example, an information gathering system (eg, information gathering system 110 in FIG. 1) contacts a social media system (eg, one or more of the social media systems in FIG. 1) to contact a social media account. You may get the profile of the candidate. In some embodiments, only the profile is fetched and the information gathering system does not need to receive the entire social media account.

At block 1020, URLs in the profile may be identified. For example, the profile of a social media account may be parsed or parsed to determine if the profile contains fields for personal web pages. In some embodiments, the particular social media account may or may not include such a field, or may not include an entry in such a field. When such a field exists and contains an entry, the corresponding entry may be identified as a URL in the profile. In some embodiments, if there is no such field or entry in such a field, method 1000 may exit and proceed to the dashed arrow at the end of method 1000 to another cross-validation technique. ..

At block 1030, the URL of the profile of the candidate social media account may be compared with the URL of the candidate personal academic web page.

At block 1040, it may be determined based on the comparison of block 1030 whether there is a match between the URL of the profile of the candidate social media account and the URL of the candidate personal academic web page. In some embodiments, the determination may be an exact match query. Additional or alternative, the query may require a similarity above the threshold, such as at least 95% or at least 90% match between URLs. If there is a match, method 1000 may proceed to block 1060. If there is no match, method 1000 may proceed to block 1050. In some embodiments, the URL protocol and / or subdomain may be ignored for matching purposes. For example, in such an embodiment, the URLs stanford.edu/instructors/andrew-ng and http://online.stanford.edu/instructors/andrew-ng may be found to match.

At block 1050, a determination may be made as to whether there are additional personal academic web page candidates to compare with the URL of the profile of the social media account candidate. If there are no other personal academic web page candidates to compare, the method may proceed to the dashed arrow at the end of Method 1000. Method 1000 may return to block 1030 if there are more personal academic web page candidates to compare.

At block 1060, it can be confirmed that both the personal scholarly web page and the social media account candidates are related to the author, based on the matches found in block 1040. For example, mutual validation via the URL of a social media account profile and the URL of a personal academic web page ensures that both the social media account candidate and the personal academic web page are correctly associated with the author. Can be enhanced. In some embodiments, block 1060 may proceed to the dashed arrow at the end of Method 1000. Additional or alternative, method 1000 may proceed from block 1060 to block 1050. For example, Method 1000 may return to block 1050 if there are more than one URL in the profile of a candidate social media account.

The dashed arrow at the end of Method 1000 may indicate that mutually validated personal web page candidates and social media account candidates are used by one or more processes or blocks, such as Block 750 of Method 700 in Figure 7. Can show that. Additional or alternative, the dashed arrow may proceed to one or more of the method 1100 of FIG. 11, the method 1200 of FIG. 12, the method 1300 of FIG. 13 or the method 1400 of FIG.

FIG. 11 shows a flowchart of another exemplary method 1100 that can be used in mutual validation of social media accounts and personal academic web page candidates based on one or more embodiments of the present disclosure. .. Although one personal academic web page candidate will be described, Method 1100 may be repeated for any number of personal academic web page candidates. Method 1100 may reflect one embodiment of performing one or more operations of block 740 of FIG. In some embodiments, one or more of the actions associated with method 1100 may be performed by the information gathering system 110. Alternatively or additionally, method 1100 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 1100. Although illustrated as discrete blocks, the steps and behavior associated with one or more of the blocks of Method 1100 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

The dashed arrow leading to block 1110 indicates that method 1100 may be a continuation of another method, such as continuing from block 730 of method 700 of FIG. Additional or alternative, the dashed arrow may be a continuation of one or more of the method 1000 of FIG. 10, the method 1200 of FIG. 12, the method 1300 of FIG. 13 or the method 1400 of FIG.

At block 1110, personal academic web page candidates may be fetched. For example, an information gathering system (eg, information gathering system 110 in FIG. 1) contacts a web hosting system (eg, one of the web hosting systems in FIG. 1) to obtain personal academic web page candidates. May be good.

At block 1120, personal academic web page candidates may be parsed to identify social media accounts listed as personal academic web page candidates. For example, the code used by a computer to display personal academic web page suggestions is parsed to determine the location of a field that contains one or more social media platforms in the field title or body. May be good. In some embodiments, method 1100 may be terminated if there is no such field or body and no social media account identifier is found in the personal academic web page candidate. You may follow the dashed arrow at the end to another cross-validation technique.

At block 1130, the identified social media account may be compared to various social media account candidates. For example, comparison involves comparing the Twitter handle listed on a personal academic web page, the name of a Facebook account, or any other unique identifier of a social media account represented on a personal academic web page. You may be.

In block 1140, a determination is made based on the comparison in block 1130 whether there is a match between the social media account identified in block 1120 and any of the social media account candidates. May be good. In some embodiments, the comparison may be an exact match query. Additional or alternative, the query may require a similarity above the threshold, such as at least 95% match or at least 90% match. If there is a match, method 1100 may proceed to block 1150. If there is no match, method 1100 may proceed to the dashed arrow at the end of block 1100.

In block 1150, both the personal academic web page and the social media account candidates that match the identified personal academic web page are related to the author, based on the match found in block 1140. It can be confirmed that it is. For example, mutual validation through a personal academic web page and an identified social media account can increase the certainty that both the social media account candidate and the personal academic web page are correctly associated with the author.

The dashed arrow at the end of Method 1100 may indicate that mutually validated personal web page candidates and social media account candidates are used by one or more processes or blocks, such as Block 750 of Method 700 in FIG. Can show that. Additional or alternative, the dashed arrow may proceed to one or more of the method 1000 of FIG. 10, the method 1200 of FIG. 12, the method 1300 of FIG. 13 or the method 1400 of FIG.

FIG. 12 shows a flowchart of another exemplary method 1200 that can be used in mutual validation of social media accounts and personal academic web page candidates based on one or more embodiments of the present disclosure. .. Although one personal academic web page candidate will be described, Method 1200 may be repeated for any number of personal academic web page candidates. Method 1200 may reflect one embodiment of performing one or more operations of block 740 of FIG. In some embodiments, one or more of the actions associated with method 1200 may be performed by the information gathering system 110. Alternatively or additionally, the method 1200 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 1200. Although illustrated as discrete blocks, the stages and behavior associated with one or more of the blocks of Method 1200 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

The dashed arrow leading to block 1210 indicates that method 1200 may be a continuation of another method, such as continuing from block 730 of method 700 of FIG. Additional or alternative, the dashed arrow may be a continuation of one or more of the method 1000 of FIG. 10, the method 1100 of FIG. 11, the method 1300 of FIG. 13 or the method 1400 of FIG.

At block 1210, personal academic web page candidates may be fetched. For example, an information gathering system may contact a web hosting system to obtain personal academic web page candidates.

At block 1220, personal academic web page candidates may be parsed to identify and extract one or more photographs of personal academic web page candidates, referred to as first photographs. For example, the code used by the computer to display a personal academic web page candidate may be parsed to determine the location of the image within the personal academic web page. In some embodiments, the extracted photo may be analyzed using image recognition to determine if the photo is a human photo. In some embodiments, if the personal academic web page candidate does not have a photo, method 1200 may be terminated or may proceed to the dashed arrow at the end of method 1200 to another cross-validation technique.

At block 1230, profiles of potential social media accounts may be fetched. For example, an information gathering system may contact the social media system to obtain a profile of potential social media accounts. In some embodiments, only the profile is fetched and the information gathering system does not need to receive the entire social media account.

At block 1240, the profile of a candidate social media account may be parsed to identify and extract one or more photos within the social media account profile, referred to as the second photo. .. For example, social media account profiles often include photos or other images associated with social media accounts as visual identifiers for social media accounts. In some embodiments, method 1200 may be terminated if the social media account candidate profile does not have a photo, or may proceed to the dashed arrow at the end of method 1200 to another cross-validation technique. good.

At block 1250, the first and second photographs may be compared. Any image comparison technique may be used, such as feature comparison techniques, pointwise techniques and / or others. In some embodiments, the first and / or second photographs may be pretreated to align the orientation, scale, cropping and / or other features of the first and second photographs. In some embodiments, the comparison of blocks 1250 may only be performed on human images. Additional or alternative, the comparison of blocks 1250 may be performed for any photo. This is because some researchers may post photos of their research projects or other similar photos on their social media profiles and their personal academic web pages. If there are a plurality of first and / or second photographs, any or all of the first photographs may be compared with any or all of the second photographs.

In some embodiments, the first and / or second photo may be analyzed using a face recognition algorithm. For example, the first photo may contain a photo of the owner of a candidate personal academic web page, and the second photo may contain a photo of the owner of a candidate social media account. In some embodiments, the results from the face recognition analysis of the first photo may be compared to the results from the face recognition analysis of the second photo. The comparison may give an indicator of the certainty that those images contain the same person.

At block 1260, a determination may be made as to whether there is a match between the first and second photographs. In some embodiments, the comparison may be an exact match query. Additional or alternative, the query may require a similarity above the threshold, such as at least 95% or at least 90% match between the first and second photographs. If there is a match, method 1200 may proceed to block 1280. If there is no match, method 1200 may proceed to block 1270.

At block 1270, a determination may be made as to whether there are additional social media account candidates that should be fetched to extract the photos. If there are no other social media account candidates to be fetched to extract the photo, the method may proceed to the dashed arrow at the end of Method 1200. Method 1200 may return to block 1230 if there are additional social media account candidates to be fetched to extract the photos.

At block 1280, it can be confirmed that both the personal scholarly web page candidate and the social media account candidate are related to the author, based on the match found in block 1260. For example, mutual validation through the first photo of a personal academic web page and the second photo of a social media account profile shows that both the social media account candidate and the personal academic web page candidate are correctly associated with the author. It can increase the certainty of being. In some embodiments, block 1280 may proceed to the dashed arrow at the end of method 1200. Additional or alternative, method 1200 may proceed from block 1280 to block 1270. For example, method 1200 may return to block 1270, as the author may have multiple social media accounts.

The dashed arrow at the end of Method 1200 may indicate that mutually validated personal web page candidates and social media account candidates are used by one or more processes or blocks, such as Block 750 of Method 700 in Figure 7. Can show that. Additional or alternative, the dashed arrow may proceed to one or more of the method 1000 of FIG. 10, the method 1100 of FIG. 11, the method 1300 of FIG. 13 or the method 1400 of FIG.

FIG. 13 shows a flow chart of another exemplary method 1300 that may be used in mutual validation of social media accounts and personal academic web page candidates based on one or more embodiments of the present disclosure. .. Although one personal academic web page candidate will be described, Method 1300 may be repeated for any number of personal academic web page candidates. Method 1300 may reflect one embodiment of performing one or more operations of block 740 of FIG. In some embodiments, one or more of the actions associated with method 1300 may be performed by the information gathering system 110. Alternatively or additionally, method 1300 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 1300. Although illustrated as discrete blocks, the steps and behavior associated with one or more of the blocks in Method 1300 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

The dashed arrow leading to block 1310 indicates that method 1300 may be a continuation of another method, such as continuing from block 730 of method 700 of FIG. Additional or alternative, the dashed arrow may be a continuation of one or more of the method 1000 of FIG. 10, the method 1100 of FIG. 11, the method 1200 of FIG. 12 or the method 1400 of FIG.

At block 1310, personal academic web page candidates may be fetched. For example, an information gathering system (eg, information gathering system 110 in FIG. 1) contacts a web hosting system (eg, one of the web hosting systems in FIG. 1) to obtain personal academic web page candidates. May be good.

At block 1320, personal academic web page candidates may be parsed to identify information blocks. For example, the code used by a computer to display a personal academic web page may be parsed to determine the location of fields that may contain blocks of information. In some embodiments, the code may be parsed to identify text blocks with more words than the threshold number. As another example, search for text blocks with titles such as "publications", "interests", "contact information", "summary" and / or others. May be done.

In block 1330, keywords may be extracted from the information block identified in block 1320. For example, a word in an information block may be compared to one or more topics identified by an information gathering system, or to another list of keywords associated with one or a topic. In some embodiments, keywords may be automatically extracted from scholarly publications on a topic. Additional or alternative, any other keyword extraction technique may be used. In some embodiments, the keyword may include occupational terms such as "research physicist" or "post-doctoral candidate".

At block 1340, profiles of potential social media accounts may be fetched. For example, the information gathering system may contact a social media system (eg, the social media system of FIG. 1) to obtain a profile of a candidate social media account. In some embodiments, only the profile is fetched and the information gathering system does not need to receive the entire social media account.

At block 1350, the extracted keywords may be compared to the text in the social media account candidate profile. For example, the keywords extracted in block 1330 may be searched from any text in the social media account profile. In some embodiments, any overlap may be given a score, the score may increase with consecutive matching terms, or may increase with increasing number of matching terms in the same sentence. good.

At block 1360, it may be determined whether the keywords extracted from the personal academic web page candidates exceed the similarity threshold with the text from the profile. For example, a determination may be made as to whether the score associated with the overlap exceeds a threshold indicating a high level of overlap in the keyword. In some embodiments, the threshold may vary based on which keywords are found to appear in both social media account candidates and personal academic web page candidates. For example, more general keywords may have a higher threshold than less common keywords. After determining that the similarity threshold is exceeded, method 1300 may proceed to block 1380. After determining that the similarity threshold is not exceeded, method 1300 may proceed to block 1370.

At block 1370, a determination may be made as to whether there are additional social media account candidates that should be fetched for comparison with the keyword. After determining that there are no other social media account candidates to be fetched, the method may proceed to the dashed arrow at the end of Method 1300. Method 1300 may return to block 1340 after determining that there are additional social media account candidates to be fetched.

At block 1380, it can be confirmed that both the personal academic web page candidate and the social media account candidate are related to the author, based on the determination in block 1360. For example, mutual validation through keywords on personal academic web pages and profile texts on social media account profiles shows that both social media account candidates and personal academic web page candidates are correctly associated with the author. It can increase the certainty. In some embodiments, block 1380 may proceed to the dashed arrow at the end of method 1300. Additional or alternative, method 1300 may proceed from block 1380 to block 1370. For example, method 1300 may return to block 1370, as the author may have multiple social media accounts.

The dashed arrow at the end of Method 1300 may indicate that mutually validated personal web page candidates and social media account candidates are used by one or more processes or blocks, such as Block 750 of Method 700 in FIG. Can show that. Additional or alternative, the dashed arrow may proceed to one or more of the method 1000 of FIG. 10, the method 1100 of FIG. 11, the method 1200 of FIG. 12 or the method 1400 of FIG.

FIG. 14 shows a flow chart of another exemplary method 1400 that can be used in mutual validation of social media accounts and personal academic web page candidates based on one or more embodiments of the present disclosure. .. Although one personal academic web page candidate will be described, Method 1400 may be repeated for any number of personal academic web page candidates. Method 1400 may reflect one embodiment of performing one or more operations of block 740 of FIG. In some embodiments, one or more of the actions associated with method 1400 may be performed by the information gathering system 110. Alternatively or additionally, method 1400 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 1400. Although illustrated as discrete blocks, the steps and behavior associated with one or more of the blocks in Method 1400 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

The dashed arrow leading to block 1410 indicates that method 1400 may be a continuation of another method, such as continuing from block 730 of method 700 of FIG. Additional or alternative, the dashed arrow may be a continuation of one or more of the method 1000 of FIG. 10, the method 1100 of FIG. 11, the method 1200 of FIG. 12 or the method 1300 of FIG.

At block 1410, personal academic web page candidates may be fetched. Block 1410 may be similar to or equivalent to block 1310 in FIG.

At block 1420, personal academic web page candidates may be parsed to identify information blocks. Block 1420 may be similar to or equivalent to block 1320 in FIG.

In block 1430, keywords may be extracted from the information block identified in block 1420. Block 1430 may be similar to or equivalent to block 1330 in FIG.

Block 1440 may fetch profiles of social media accounts linked to certain social media account candidates. For example, a social media account that is getting information from the social media account candidate (eg, following the social media account candidate) and / or the social media account candidate is getting information from it. The information processing system may contact the social media system to identify the social media account it has acquired (eg, followed by the social media account candidate). Social media systems may also be required to send profiles of their following and / or followed social media accounts. In some embodiments, the number of required profiles may be censored numerically, for example 50 profiles or 100 profiles or 200 profiles and / or others.

At block 1450, the extracted keywords may be compared to the text of the social media account profile. In some embodiments, block 1450 may be similar to or equivalent to block 1350 of FIG. 13, but the comparison is to the social media account candidate rather than to the profile of the social media account candidate itself. The difference is that it runs for the profile of the linked social media account.

Block 1460 determines whether keywords extracted from personal academic web page candidates exceed the similarity threshold with the text of one or more of the linked social media account profiles. good. In some embodiments, the determination may be made for each profile or across the text of all profiles. After determining that the similarity threshold is exceeded, method 1400 may proceed to block 1480. After determining that the similarity threshold is not exceeded, method 1400 may proceed to block 1470. In some embodiments, even if there is a minimum number and / or proportion of linked social media account profiles that exceed the similarity threshold before Method 1400 proceeds to block 1480 instead of block 1470. good.

At block 1470, a determination may be made as to whether there are additional social media account candidates with a linked account profile that should be fetched for comparison with the keyword. If there are no other social media account candidates to be fetched, the method may proceed to the dashed arrow at the end of Method 1400. Method 1400 may return to block 1440 if there are additional social media account candidates to be fetched.

At block 1480, it can be confirmed that both the personal academic web page candidate and the social media account candidate are related to the author, based on the determination at block 1460. For example, cross-validation via keywords on personal academic web pages and linked social media account profile texts for social media account candidates is described by both social media account candidates and personal academic web pages. It can increase the certainty that it is correctly related to the author. In some embodiments, block 1480 may proceed to the dashed arrow at the end of method 1400. Additional or alternative, method 1400 may proceed from block 1480 to block 1470. For example, method 1400 may return to block 1470, as the author may have multiple social media accounts.

The dashed arrow at the end of Method 1400 may indicate that mutually validated personal web page candidates and social media account candidates are used by one or more processes or blocks, such as Block 750 of Method 700 in FIG. Can show that. Additional or alternative, the dashed arrow may proceed to one or more of the method 1000 of FIG. 10, the method 1100 of FIG. 11, the method 1200 of FIG. 12 or the method 1300 of FIG.

<Social media account as a sensor>
In one or more embodiments, the disclosure may include using a social media account as a sensor for identifying other knowledgeable social media accounts. For example, social media that is following a social media account and / or is being followed by a social media account in determining whether a social media account is associated with a knowledgeable person. -Accounts may be analyzed. One or more embodiments of the present disclosure may take advantage of the ability of knowledgeable people to recognize others who are knowledgeable about a particular topic and to seek information from those others. For example, a professor who writes about machine learning may follow other people who are knowledgeable about machine learning on social media and be followed by those other people. In addition, an account followed by a knowledgeable person may be more likely to be an account of a person who is knowledgeable about a given topic than an account that is following a knowledgeable person. For example, a graduate student may follow a particular professor who is known to be knowledgeable about a given topic, considering that particular professor is knowledgeable of the insights from that graduate student. Being may not mean. By analyzing and using links in seed social media accounts of people with known knowledge, seed social media accounts can identify social media accounts of other knowledgeable people. Can function as a sensor for. In some embodiments, various sets of candidate social media accounts are generated, then whether the candidate is a knowledgeable account or some other category, such as a learner social media account. It may be analyzed to determine if it can be included in. A knowledgeable social media account may refer to a social media account associated with a knowledgeable person on a given topic. A learner social media account may refer to a social media account associated with a person who is interested in a given topic but may or may not be knowledgeable about the given topic. ..

FIG. 15 shows an exemplary 1500 schematic representation of the generation of a candidate set for social media accounts, based on one or more embodiments of the present disclosure. In some embodiments, the schematic 1500 indicates a process or part of a process that identifies a social media account as a candidate for a knowledgeable social media account and / or a learner social media account. sell. In these and other embodiments, the process or part of a process represented by the schematic representation 1500 may be an example of the operation of system 100 in FIG. For example, in some embodiments, the information gathering system 110 may be configured to generate candidate sets as shown in schematic representation 1500.

As shown in FIG. 15, a set of seed social media accounts 1510 is one or more social media accounts 1512a-1512g (generally with seed social media accounts (s) 1512). May be included). The set of seeded social media accounts 1510 may include seed social media accounts 1512 that are known to be social media accounts that are knowledgeable about a given topic. For example, using the process of this disclosure (as shown in Figure 2 and / or Figure 6), the author of a publication on a given topic has a social media account associated with that author. You may be doing it. The social media account associated with the author can be a social media account of a person who is knowledgeable about the topic of the publication. Such social media accounts may be included as one of the seed social media accounts 1512. In addition or alternatives, the user may submit himself or another social media account as a social media account that should be included as one of the seed social media accounts 1512. Any other method or process may be used to identify the seed social media account 1512, such as peer reviews, peer recommendations, undergraduate identification, organizational identification, and the like.

The arrow attached to the seed social media account 1512 may indicate a social media account linked to the seed social media account 1512. For example, an arrow exiting a given social media account is by the social media account or the given social media account from which the given social media account is informed. Can indicate the social media account being followed. An arrow pointing to a given social media account is the social media account that is getting information from the given social media account or the social media that is following the given social media account. Can indicate a media account. For example, for the seed social media account 1512a, the seed social media account 1512a follows the social media accounts 1522a, 1512b, 1512c and 1512e and is followed by the social media accounts 1512b and 1532e. ing. As another example, for social media account 1522a, social media account 1522a is following social media account 1512c, followed by social media accounts 1512a, 1512b and 1512e.

In some embodiments, a first candidate set 1520 for social media accounts may be generated. For example, the first candidate set 1520 fetches the social media account profile of the seed social media account 1512 and all the social media followed by the seed social media account 1512. They may be created by identifying accounts and these accounts may be added to the first candidate set 1520 as social media accounts 1522a and 1522b (referred to as social media accounts 1522). ..

In some embodiments, one or more social media accounts may be removed from the first candidate set 1520. For example, the first candidate set 1520 may be analyzed to identify any social media accounts already in the seed social media account set 1510. For example, the seed social media account 1512a follows the social media account 1512b, while the social media account 1512b is already in the set of seed social media accounts 1510, and thus social. Media account 1512b may be removed from the first candidate set 1520.

As another example, one or more of the social media accounts 1522 may be analyzed to determine if they are owned by a person, organization, publication, software vendor, conference or otherwise. For example, some meetings may include a Twitter account that generates social media posts that may be related to a given topic but not to someone who is knowledgeable about the given topic. In some embodiments, social media accounts owned by real people are included in the first candidate set 1520.

Another example of a social media account 1522 removed from the first candidate set 1520 may include a generally applicable social media account or a general social media account. For example, a popular movie star or politician may be followed by a large number of knowledgeable people on a topic, which indicates that the movie star or politician is always knowledgeable on the topic. It may not be. One or more embodiments of the present disclosure may eliminate such general social media accounts. An exemplary method of such a technique is shown in FIG.

In some embodiments, the social media account 1522 of the first candidate set 1520 is analyzed to determine if the social media account 1522 is included as the seed social media account 1512. May be good. In some embodiments, such analysis may include removing various social media accounts from the first candidate set 1520, with the remaining social media accounts 1522 being seed social. -May be added to media account 1510. Additional or alternative, additional analysis may be performed on the social media account 1522. In these and other embodiments, by including additional seeded social media accounts 1512, further seeded social media accounts can be used with those newly added seeded social media accounts. The process of identifying is possible.

As an addition or alternative to the first candidate set 1520, in some embodiments, a second candidate set 1530 for social media accounts may be generated. For example, the second candidate set 1530 fetches the social media account profile of the seed social media account 1512 and lists all social media accounts that follow the seed social media account 1512. The social media account being followed may be generated by identification in the second candidate set 1530 as social media accounts 1532a-1532c (referred to as social media accounts 1532). May be added.

In some embodiments, one or more social media accounts may be removed from the second candidate set 1530. For example, the second candidate set 1530 may be analyzed to identify any social media accounts contained in the seed social media account set 1510. For example, the seed social media account 1512a is followed by the social media account 1512b, but the social media account 1512b is already in the set of seed social media accounts 1510, and thus social. Media account 1512b may be removed from the second candidate set 1530. Additional or alternative, the second candidate set 1530 may be analyzed to identify any social media accounts already in the first candidate set 1520. For example, social media account 1522a follows seed social media account 1512c, but is not in the set of seed social media accounts 1510. However, the social media account 1522a is already in the first candidate set 1520, so that the social media account 1522a may be removed from the second candidate set 1530.

Another example of the social media account 1532 removed from the second candidate set 1530 may include a generally applicable social media account or a general social media account. Similar to those mentioned with reference to removing such accounts from the first candidate set 1520. An exemplary method of such a technique is shown in FIG.

In some embodiments, the social media account 1532 of the second candidate set 1530 may be analyzed to include the social media account 1532 in the learner social media account set. It may be determined. In some embodiments, such analysis may include removing various social media accounts from the second candidate set 1530, with the remaining social media accounts 1532 being learner social. -May be added to a set of media accounts. Additional or alternative, further analysis may be performed on the social media account 1532. For example, an analysis may be performed to determine the level of interest of the social media account for a given topic.

In some embodiments, the set of seed social media accounts 1510 and the set of learner social media accounts are of some sort based on which set the social media accounts belong to. Content may be delivered. For example, the set of seed social media accounts 1510 may be provided with new publications, and the set of learner social media accounts may be provided with lecture videos or lesson summaries. In some embodiments, the set of seed social media accounts 1510 may be provided with more advanced content than is provided to the set of learner social media accounts. As such, social media accounts are sensors for identifying and classifying certain social media accounts, indirectly based on the human perception of the knowledge level of the owner of the social media account. Can be used as.

Modifications, additions or omissions may be made to the schematic representation 1500 without departing from the scope of the present disclosure. For example, the schematic representation 1500 may include other sets or groups of social media accounts, such as a set of learner social media accounts. Alternatively or additionally, additional features or details of the analysis described with respect to FIG. 15 may be described with reference to FIGS. 16a-18.

16a and 16b show a flow chart of an exemplary method 1600 of identifying and extracting information while using a social media account as a sensor, based on one or more embodiments of the present disclosure. For example, in some embodiments, one or more of the actions associated with method 1600 may be performed by the information gathering system 110. Alternatively or additionally, Method 1600 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 1600. Although illustrated as discrete blocks, the steps and behavior associated with one or more of the blocks in Method 1600 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

At block 1602, a seed social media account may be acquired. For example, an information gathering system (eg, the information gathering system 110 in FIG. 1) may be given a set of predetermined social media accounts that are knowledgeable about a given topic. Additional or alternative, the information gathering system relates to the author of the publication using one or more of the processes, systems or devices of the present disclosure, such as the flow of FIG. 2 and / or FIG. You may identify one or more social media accounts.

At block 1604, a social media account profile may be fetched for a given seed social media account. For example, the information gathering system may contact a social media system (eg, one or more of the social media systems in FIG. 1) to obtain a profile of potential social media accounts. In some embodiments, only the profile is fetched and the information gathering system does not need to acquire the entire social media account.

In block 1606, the first set of social media accounts may be extracted from the profile as social media accounts followed by seed social media accounts. For example, the portion of the profile that contains a field that identifies the social media account being followed by the seed social media account may be identified, and the social media account listed therein may be social. -It may be extracted as the first set of media accounts.

At block 1608, the first set of social media accounts may be compared to seed social media accounts. For example, such a comparison may identify any social media accounts that are included in both the first set of social media accounts and the seed social media accounts.

In block 1610, a first set of candidates for social media accounts may be constructed based on the comparison of block 1608. For example, the first candidate set for a social media account is in the first set of social media accounts, but not in the seed social media account. It may include an account. In some embodiments, blocks 1608 and 1610 may be performed simultaneously, for example, social media in both the first set of social media accounts and the seed social media account. • By removing the account each time it is identified and the remaining social media accounts in the first set become the first candidate set for social media accounts.

In block 1612, one or more general social media accounts may be removed from the first candidate set of social media accounts. For example, a celebrity social media account may be followed by one or more seed accounts, but the seed social media account may not be knowledgeable on a topic that it is knowledgeable about. .. An example of removing one or more common social media accounts is described with reference to FIG.

In block 1614, the candidate social media accounts of the first candidate set may be analyzed to determine the type of social media account. For example, the analysis may be performed to determine if the candidate social media account is owned by a person or by an organization (eg, journal, conference, software tool, organization, etc.). As another example, the analysis also has an interest score above the threshold for determining if a candidate social media account is a knowledgeable account for a given topic. It may be executed to determine whether or not it is. As another example, the analysis may be performed to determine if the interest level of the candidate social media account is above the threshold. An exemplary method of such analysis is described, for example, in FIG.

At block 1616, a determination may be made as to whether the candidate social media account is a knowledgeable social media account. For example, the determination may be based on the analysis performed in block 1614. After determining that the candidate social media account is a knowledgeable account, method 1600 may proceed to block 1618. After determining that the candidate social media account is not a knowledgeable account, method 1600 may proceed to block 1620.

In block 1618, candidate social media accounts may be added as seed social media accounts.

At block 1620, a determination may be made as to whether there are additional candidate social media accounts within the first set of social media account candidates. Method 1600 may return to block 1614 if there are more candidates. If there are no further candidates, method 1600 may proceed to block 1622.

With reference to FIG. 16b, in block 1622, a second set of social media accounts following the seed social media accounts may be extracted. For example, the portion of the profile that contains a field that identifies the social media account that follows the seed social media account is identified, and the social media account listed there is social. It may be extracted as the second set of media accounts.

At block 1624, a second set of candidates for social media accounts may be constructed. For example, the second set of social media accounts is in the second set of social media accounts extracted in block 1622, but the first set of social media accounts and It may include a social media account that is not included in the seed social media account. In some embodiments, the social media account in the second set of social media accounts is compared to the seed social media account and the first set of social media accounts. Often, overlapping accounts may be removed from the second set of social media accounts and given the second set of candidates for social media accounts.

At block 1626, one or more general social media accounts may be removed from the second set of candidate social media accounts. Block 1626 may be similar to or equivalent to block 1612, but is executed against a second set of candidate social media accounts rather than the first set.

At block 1628, the name associated with the candidate for the second candidate set of social media accounts may be obtained. For example, a social media system may be required to provide a profile for a candidate social media account. As another example, a social media system to provide the name associated with a particular social media account without requesting or receiving additional data about that social media account. May be inquired.

At block 1630, it may be determined whether the name associated with the candidate account is an organization account or a person's name. For example, a text analysis is performed on the name obtained in block 1628 and one or more indicators of the organization, such as the words "journal" "the" "company (inc.)" "Company (co). .) ”,“ Package ”,“ group ”, etc. may be determined. Additional or alternative, the name retrieved in block 1628 identifies a text item typically used as a name such as "John", "Andrew", or "Sarah". May be compared with the name database for. In some embodiments, the information gathering system may maintain a database of known organizations (eg, conferences, journals, universities, software vendors and / or standards-setting bodies) associated with a topic, and may be named. It may be compared to an entry in a database of known organizations. In these and other embodiments, method 1600 may proceed to block 1632 after determining that the name is tissue. Additional or alternative, after determining that the name is an organization, that organization may be added as another entry in said database of known organizations. After determining that the name is a person, method 1600 may proceed to block 1634.

In block 1632, candidate social media accounts may be removed from the second set of candidate social media accounts based on the name being the organization name. After block 1632, method 1600 may proceed to block 1640.

At block 1634, an interest score representing an interest in a given topic of a person may be identified based on the name being the person's name. For example, the interest score may be based on the number of keywords related to a given topic that appear in social media posts for candidate social media accounts. Additional or alternative, the interest score may be based on the percentage of candidate social media accounts that contain a threshold number of keywords related to a given topic. Additional or alternative, interest scores are based on the interaction of candidate social media accounts with one or more social media posts that contain one or more keywords related to a given topic. You may. In some embodiments, the candidate's interest score may be based on any combination of the above or any other method for identifying one or more topics of interest in a social media account. ..

At block 1636, a determination may be made as to whether the interest score is above the threshold. In some embodiments, the threshold level may be based on the popularity of the topic. Additional or alternative, the threshold level may be based on how often keywords related to the topic are used outside the context of the topic. For example, the terms "machine" and "learning" are often used outside the academic context, while "naive Bayes" is rarely used outside the academic context. After determining that the interest score is above the threshold, method 1600 may proceed to block 1638. After determining that the interest score does not exceed the threshold, method 1600 may proceed to block 1640.

At block 1638, candidate social media accounts may be added to a second set of social media accounts based on the determination made in block 1636 that the interest score exceeds the threshold. For example, the second set of social media accounts may be a set of learner social media accounts. The second set of social media accounts is an account that wants to get information about a particular topic, but does not necessarily have the expertise or knowledge recognized by the peers on that topic. You may.

At block 1640, a determination may be made as to whether there are additional candidate social media accounts in the second set of candidate social media accounts that have not yet been analyzed. After determining that there are remaining candidate accounts, Method 1600 may return to block 1628. After determining that there are no more candidate social media accounts, Method 1600 may proceed to block 1642.

At block 1642, a determination may be made as to whether there are additional seeded social media accounts that have not yet been analyzed. After determining that there are more seeded social media accounts, Method 1600 may return to block 1604. If there are no additional seed social media accounts, Method 1600 may proceed to block 1644.

At block 1644, different content may be provided to the seed social media account and the second set of social media accounts. In some embodiments, the different content may be related to the same topic, but may be different for those two groups. For example, a seed social media account (which is known to be knowledgeable about a given topic) is offered primary content such as new publications, discoveries, etc. related to that topic. May be good. The second set of social media accounts (which we know are interested in the topic, but not necessarily knowledgeable about the topic) are lecture notes, lectures related to the topic. Videos, lesson presentations, summaries, etc. may be provided.

In some embodiments, the first and / or second set of candidate social media accounts is before the first and / or second set of candidate social media accounts is analyzed. It may be generated for all seed social media accounts. Such an approach can avoid potentially duplicate analysis of candidate social media accounts. In these and other embodiments, after analyzing those candidates, additional seed accounts, if any, may be processed to generate additional candidate social media accounts. As another example, any of blocks 1622 to 1640 may be omitted, and only the first candidate set may be constructed and analyzed. In addition or alternatives, only the second candidate set may be constructed and analyzed.

FIG. 17 shows a flow chart of an exemplary method 1700 that can be used in identifying and extracting information while using a social media account as a sensor, based on one or more embodiments of the present disclosure. Although one social media account will be described, Method 1700 may be repeated for any number of social media accounts. Method 1700 may reflect one embodiment of performing one or more operations of block 1614 of FIG. In some embodiments, one or more of the actions associated with method 1700 may be performed by the information gathering system 110. Alternatively or additionally, Method 1700 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 1700. Although illustrated as discrete blocks, the stages and behavior associated with one or more of the blocks of Method 1700 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

The dashed arrow leading to block 1705 indicates that method 1700 may be a continuation of another method, such as continuing from block 1612 or 1620 of method 1600 of FIG.

At block 1705, a name may be obtained for a social media account that is a candidate social media account in the set of candidate social media accounts. Block 1705 may be similar to or equivalent to block 1628 of FIG.

In block 1710, it may be determined whether the name is an organization name or a person's name. Block 1710 may be similar to or equivalent to block 1630 in FIG. After determining that the name is an organization name, method 1700 may proceed to block 1740. After determining that the name is a person's name, method 1700 may proceed to block 1715.

In block 1715, based on the name being a person's name, the name may be compared to one or more author names in the publication database. For example, an information gathering system (eg, information system 110 in FIG. 1) may include a database of publications and / or authors of publications, wherein the name is the author of one or more publications. It may be compared to such a database to determine if it appears as.

At block 1720, a determination may be made as to whether there is a match between the person's name and the author of the publication in the database. In some embodiments, the match may include an exact match, an exact surname match, an approximate percentage match (eg 80% match) or some other variant thereof. For example, for the author name Andrew Ng, in various embodiments, any of the following may be considered a match, depending on the match criteria: Andy Ng. ], A. Ng [A. Wu], Drew Ng [Drew Wu], Andi Ng [Andy Wu], Andrew G. Ng [Andrew G. Wu], Dr. Ng [Dr. Wu], Doctor Ng [ Dr. Wu] etc. After determining that the names match, method 1700 may proceed to block 1725. After determining that the names do not match, method 1700 may proceed to block 1730.

In block 1725, candidate accounts may be categorized as knowledgeable accounts based on the fact that the name matches a certain author's name in the database, and method 1700 may proceed to the dashed line at the end of method 1700. ..

At block 1730, interest scores may be identified for the candidate account based on the fact that the name does not match the author in the database. Block 1730 may be similar to or equivalent to block 1634 in FIG. 16b.

At block 1735, a determination may be made as to whether the candidate's interest score exceeds the threshold. In some embodiments, the threshold may be based on the rarity of the topic, the number of publications on a given topic, or any other of a variety of factors. After determining that the interest score is above the threshold, the method may proceed to block 1725. After determining that the interest score does not exceed the threshold, method 1700 may proceed to block 1740.

At block 1740, candidates may be removed from the set of social media accounts. For example, a lower interest score below the threshold may indicate that the account is not knowledgeable about the given topic. Therefore, the account may be removed as a potential candidate for a knowledgeable account. After block 1740, method 1700 may proceed from block 1740 back to the previous method following that method. For example, method 1700 may proceed from block 1745 to block 1620 of FIG.

The dashed arrow at the end of Method 1700 indicates whether the classified social media account candidates are knowledgeable social media accounts. Block 1616 and / of Method 1600 in FIG. Alternatively, it may indicate that it may be used by one or more processes or blocks, such as block 1620. Additional or alternative, the dashed arrow may indicate that the social media account is not knowledgeable and has been removed from the candidate list.

FIG. 18 shows a flow chart of another exemplary method 1800 that can be used in the identification and extraction of information while using a social media account as a sensor, based on one or more embodiments of the present disclosure. .. Although one candidate social media account will be described, Method 1800 will describe any number of social media accounts, for example, to remove all common social media accounts from a collection of candidate social media accounts. It may be repeated for the account. Additional or alternative, method 1800 may be performed on one or both of the first candidate set and the second candidate set of social media accounts. Method 1800 may reflect one embodiment of performing one or more operations of blocks 1612 and / or 1626 of FIG. In some embodiments, one or more of the actions associated with method 1800 may be performed by the information gathering system 110. Alternatively or additionally, Method 1800 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 1800. Although illustrated as discrete blocks, the steps and behavior associated with one or more of the blocks in Method 1800 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

The dashed arrow leading to block 1810 indicates that method 1800 may be a continuation of another method, such as continuing from block 1610 or 1624 of method 1600 of FIG.

At block 1810, candidate social media account profiles may be fetched. Block 1810 may be similar to or equivalent to block 1604, but candidate social media account profiles may be fetched instead of seed social media account profiles.

Block 1820 may count the first number of global followers for candidate social media accounts. For example, a general count of all followers of a candidate social media account may be made. In some embodiments, one or more socials to provide a number of followers for a particular social media account, rather than fetching the profile and counting the number of followers listed in the profile. -The media system may be inquired. For example, if a candidate account has 1.3 million followers, the number of global followers can be 1.3 million. As another example, if the candidate account has 410 followers, the number of global followers can be 410.

At block 1830, a second number of local followers for candidate social media accounts may be counted. For example, a local follower social media account is a candidate social media account from said first set of candidate social media accounts and / or said set of seed social media accounts. It may include those who are following the candidate social media account. In some embodiments, the local follower social media account may further include the second set of candidate social media accounts. For example, there are 50 seed accounts that follow a social media account, and 20 accounts from the first set of candidate social media accounts that follow that social media account. In some cases, the number of local followers may be 70.

At block 1840, topic relevancy scores may be generated. A topic relevance score can indicate how many of the followers of a candidate social media account are knowledgeable or potentially knowledgeable about a given topic. For example, the topic relevance score may be generated as a quotient of local followers divided by global followers. Using the first of the above two examples, the topic relevance score can be determined to be 700 / 1.3 million, or about 5.384 × 10 ^-5 . For the second example, the topic relevance score can be determined to be 70/410, or about 0.1707.

At block 1850, a determination may be made as to whether the relevance score is above the threshold. In some embodiments, the threshold may be topic-based or topic-independent. For example, some topics may be more popular, so there may be more people following the topic. This can increase the relevance score. In some embodiments, the threshold may be between 0.01 and 0.0001 using the numerical example above. However, the threshold can be more generally arbitrary. After determining that the relevance score is above the threshold, method 1800 may proceed to the dashed arrow at the end of method 1800. After determining that the relevance score is below the threshold, method 1800 may proceed to block 1860.

At block 1860, candidate social media accounts may be removed from the set of candidate social media accounts. For example, candidate social media accounts may be categorized as general social media accounts based on their relevance score not above the threshold. Such general social media accounts may be removed from the first and / or second set of candidate social media accounts. In addition or alternatives, such candidate social media accounts may be removed from the set of learner social media accounts and / or seed social media accounts.

The dashed arrow at the end of method 1800 indicates that a shortened set of candidate social media accounts may be used by one or more processes or blocks, such as block 1614 and / or block 1628 of method 1600 of FIG. Can show that.

In one or more embodiments, the present disclosure is based on a social media account type, by modeling a mutually reinforcing relationship between a social media account and social media content. Provides ranking of media accounts and social media content. This disclosure may identify good quality social media accounts with field-specific knowledge and recommend good field-specific content based on mutually reinforcing rankings that take into account social media account types. .. Taking Twitter as an example of social media services, Twitter accounts can be created by individuals, companies, academic institutions, trade conferences, academic conferences, organizations, publications, software vendors, etc. (eg). Can be owned). A Twitter account that repeatedly or consistently tweets or retweets good quality content in a particular area may be considered a good Twitter account with expertise in that particular area. Also, content that is tweeted or retweeted by many good Twitter accounts in a particular area may be considered good content in that particular area. One or more embodiments of the present disclosure have discipline-specific expertise to rank good quality Twitter accounts with discipline-specific expertise and quality discipline-specific content based on the Twitter type. Take advantage of the relationship between good Twitter accounts and good discipline-specific content. In the description below, Twitter accounts are used as exemplary social media accounts, and tweets and retweets are used as exemplary social media posts or promotions. Despite these examples referring to Twitter, one of ordinary skill in the art will appreciate that the various embodiments described in this article are applicable to any of a number of social media services. ..

FIG. 19 is an exemplary flow of 1900 that can be used with respect to the mutually reinforcing ranking of social media accounts and content based on the social media account type, based on one or more embodiments of the present disclosure. It is a figure. In some embodiments, Flow 1900 illustrates a process or part of a process that determines the mutually reinforcing ranking of social media accounts and social media content based on the social media account type. You may. In these and other embodiments, some or all of the flow 1900 may be an example of the operation of system 100 in FIG. For example, in some embodiments, the information gathering system 110 is configured to generate mutually reinforcing rankings of social media accounts and content based on the social media account type shown in Flow 1900. May be good.

Flow 1900 may start at block 1910 and an extended account may be obtained as a sensor. The account may be a social media account and the extended account may be an extended seed social media account with discipline-specific knowledge. An extended seed social media account with discipline-specific knowledge is a seed social media account associated with people who are known to be knowledgeable about a given topic (eg, Figure 15). Seed social media account 1510) and social media accounts followed by the knowledgeable person that are not already seed social media accounts (eg Figure 15). The first candidate set of 1520) and may be included. In some embodiments, an extended seed social media account with discipline-specific expertise identifies or identifies different types of social media accounts for identifying or discovering discipline-specific content. It may be used as a sensor to do so. Mutual reinforcement methods may be applied to identify useful information-rich social media accounts based on social media account types and to endorse discipline-specific content within social media.

Block 1920 may extract and summarize recent shared and / or commented content generated from extended social media accounts. In some embodiments, social media posts or promotions that include links to content may be considered, and social media posts or promotions that do not include links to content may be discarded (eg, social). Not considered when generating mutually reinforcing rankings for media accounts and content). Links contained within social media posts from extended social media accounts may be accessed and content extracted. The extracted content may be grouped together. The example of Twitter as a social media service may consider tweets or retweets from an extended Twitter account (eg, a Twitter account with discipline-specific knowledge) that includes a link. Tweets or retweets that do not contain may be discarded. For each tweet, the link within the tweet may be followed to the target web page, and the content from the target web page may be extracted. Content extracted from tweets may be combined. Therefore, a tweet or retweet containing a link (eg, tweeting or retweet) is considered to be good content if it is tweeted or retweeted (eg, voted) by more people (eg, article, publication, etc.). It may be considered as a kind of vote (for example, a vote) in the sense that it is possible. Conversely, content that is tweeted or retweeted by a smaller number of people does not have to be considered good content.

In some embodiments, for each extended social media account of the expanded social media account, the most recent specific number of posts (eg, the most recent 1000 posts, the most recent 1100 posts). Content generated, shared and / or commented from (etc.) may be extracted and combined. In the Twitter example, content from the most recent specific number of tweets or retweets may be extracted and combined for each extended Twitter account. That is, the link contained in the most recent specific number of tweets or retweets may be traced to the corresponding target web page, and the content from the target web page may be extracted and summarized. Content generated, shared and / or commented from posts made within a specific time period or time point for each expanded social media account in the expanded social media account (eg, the last week). Posts within, posts within the last two weeks, posts within the last month, etc.) may be extracted and summarized.

In block 1930, discrimination may be made for different types of social media accounts contained in extended social media accounts with discipline-specific knowledge. Seed social media accounts (eg, seed social media account 1510 in Figure 15) associated with people who are known to be knowledgeable about a given topic are social media created by individuals.・ It may be an account. For example, the author of a publication on a given topic or discipline may have a social media account associated with that author. The social media account associated with the author can be a social media account of someone who is knowledgeable about the topic or discipline of the publication. Such social media accounts may be considered personal social media accounts (eg, personal social media account types). Social media accounts followed by knowledgeable people that are no longer seed social media accounts (eg, first candidate set 1520 in Figure 15) are individuals, companies, It may be a social media account generated by an academic institution, trade conference, academic conference, organization, publication, software vendor, etc. A determination may be made about the type of social media account followed by a knowledgeable person that is not already a seed social media account. For example, for each social media account that is included in a social media account that is followed by a knowledgeable person and is not already a seed social media account, that particular social media. Whether the media account is owned by an individual, company, academic institution, trade conference, academic conference, organization, publication, software vendor or others (eg personal social media account type, corporate social) -Analysis may be performed to determine media account type, academic institution social media account type, trade conference social media account type, etc.). Illustrative techniques for identifying different types of social media accounts contained in extended social media accounts with discipline-specific knowledge are shown in FIGS. 20a and 20b.

Block 1940 may generate mutually reinforcing rankings for social media accounts and social media content based on the social media account type. For example, mutually reinforcing methods are applied to identify extended social media accounts with discipline-specific knowledge based on mutually reinforcing rankings (for example, useful information-rich social media accounts). Identify) and recommend content generated, shared and / or commented from an extended social media account with discipline-specific knowledge. In particular, mutually reinforcing rankings may be based on the social media account type of extended social media accounts with discipline-specific knowledge. Such a process consistent with the present disclosure will be described in more detail with respect to FIG.

20a and 20b show diagrams of an exemplary flow 2000 that can be used for social media account type discrimination based on one or more embodiments of the present disclosure. In some embodiments, Flow 2000 may indicate a process or part of a process for determining the social media account type for a social media account. That is, Flow 2000 may indicate a process or part of a process for identifying what type of social media account the social media account is. In these and other embodiments, some or all of Flow 2000 may be an example of the operation of system 100 in FIG. For example, in some embodiments, for each social media account contained in an extended seed social media account with discipline-specific knowledge, as the information gathering system 110 is shown in Flow 2000, social. • It may be configured to determine the type of media account.

Flow 2000 may start at block 2010 and an account profile corresponding to social media account 2002 may be acquired. The social media account 2002 may be a social media account included in an extended seed social media account with discipline-specific knowledge, and the social media account 2002 is social according to Flow 2000. • May be acquired or searched to determine the social media account type that corresponds to the media account 2002. In some embodiments, the social media account 2002 is a social media account that is included in an extended seed social media account with discipline-specific knowledge and is followed by a knowledgeable person. It may be one of those that are not already seed social media accounts (eg, first candidate set 1520 in FIG. 15). In this case, a seed social media account (for example,) that is included in an extended seed social media account with discipline-specific knowledge and is associated with people who are known to be knowledgeable about a given topic. The seed social media account 1510) in FIG. 15 may be a social media account created by an individual and is considered to be a personal social media account (eg, a personal social media account type). May be good.

The account profile may contain information about the entity that owns, operates or is associated with the social media account 2002. The entity that owns, operates, or is associated with a social media account may be referred to as the social media account owner. The account profile may include a name, photo, description, link URL and other information about the social media account owner. For example, the account profile may be a web page.

In block 2020, the name associated with the social media account 2002 may be extracted from the acquired account profile. The name may be a string or character string contained in the account profile web page. For example, an account profile web page may be parsed and / or searched for a character string that can indicate a name. The extracted name may be the name of the social media account owner (eg, the owner of the social media account 2002). For example, the name may be an individual's name, a journal's name, a company's name, a meeting's name, and so on.

In block 2022, the extracted names may be inspected to generate name features 2024. Name feature 2024 may be a vector of numerical features or signals representing the extracted name. That is, the name feature 2024 may be a numerical representation of the extracted name. In some embodiments, the extracted names are in one or more databases with known names, such as author name databases, generic name databases, conference name databases, company name databases, name keyword databases, and so on. It may be inspected. The author name database may contain the names of authors of published articles or publications in specific disciplines or topics such as computer science, electrical engineering, machine learning, and the like. A database of common names may include common names for people such as "Dave", "Diana", "Susan", and so on. The company name database may include the names of companies, companies, and the like. The name keyword database contains individual keywords accumulated from existing names of various social media account types such as "machines", "research", "conference", etc. You may go out. If a match is found between the extracted name and the name in one of the databases, the name feature 2024 may be set to indicate or represent that particular type of name. For example, if the extracted name matches the name of an author in the author database, the name feature 2024 may be set to indicate that the extracted name is the name of the author. In another example, if the extracted name matches a generic name in a generic name database, the name feature 2024 is set to indicate that the extracted name is a generic name. You may. In yet another example, if the extracted name contains or contains a particular keyword in the name keyword database, the name feature 2024 is set to indicate that the extracted name contains a particular keyword. May be done. If a match is found between the extracted name and the name in one of the databases, the name feature 2024 may be set to indicate that the extracted name is not found in any name database.

At block 2030, photos related to social media account 2002 may be extracted from the acquired account profile. The photo may be an image contained in an account profile web page. The account profile web page may be parsed to identify and extract one or more photos in the account profile. For example, social media account profiles often include photos or other images associated with the social media account as a visual identification of the social media account.

At block 2032, the extracted photographs may be inspected to produce photographic features 2034. The photographic feature 2034 may be a vector of numerical features or signals representing the extracted photo. In some embodiments, the extracted photo may be inspected to determine if the photo is a person's face or contains a person's face. For example, the extracted photo may be analyzed using a facial recognition algorithm to determine if the photo is a person's face or contains a person's face. If the photo is a person's face or contains a person's face, the photographic feature 2024 may be set to indicate or represent that the photo is a person's face or contains a person's face. Conversely, if the photo is not a person's face or does not contain a person's face, the photographic feature 2024 may be set to indicate or represent that the photo is not a person's face or does not contain a person's face.

At block 2040, descriptions related to social media account 2002 may be extracted from the acquired account profile. The description may be a text string or content contained in the account profile web page, or may describe the owner of the social media account (eg, the owner of the social media account 2002). For example, an account profile web page may be parsed and / or searched for text strings or content that may indicate a description. In the example of a personal social media account, the description may describe the social media account owner (eg, that person) as a "Ph.D. student in machine learning at Stanford University." In the example of a social media account related to a conference, the description describes the social media account owner (eg, the conference) as "for machine learning researchers held June 19-24, 2016 in New York City. It may be described as "the best international conference".

In block 2042, the extracted description may be inspected to produce descriptive feature 2044. The description feature 2044 may be a vector of numerical features or signals representing the extracted description. In some embodiments, the extracted description is a descriptive keyword database to determine if the extracted description contains or contains one or more individual keywords in the descriptive keyword database. Is matched against. The descriptive keyword database may contain individual keywords accumulated from existing descriptions of various social media account types. If the extracted description contains or includes one or more individual keywords in the descriptive keyword database, the descriptive feature 2044 indicates that the extracted description contains the one or more individual keywords. It may be set. Conversely, if the extracted description does not contain a keyword in the descriptive keyword database, the descriptive feature 2044 may be set to indicate that the extracted description does not contain the keyword.

At block 2050, the link URL associated with the social media account 2002 may be extracted from the acquired account profile. For example, an account profile web page may be parsed and / or parsed to determine if the account profile contains a link URL. If the account profile contains a link URL, the link URL may be extracted from the account profile web page.

In block 2052, the extracted link URL may be inspected to generate the profile URL feature 2054. The profile URL feature 2054 may be a vector of numerical features or signals representing the extracted link URL. In some embodiments, the extracted link URL may be accessed to acquire or download the content pointed to by the link URL (eg, an HTML page). Downloaded content (eg HTML pages) may be parsed to generate a keyword feature vector. The keyword feature vector may be included in the profile URL feature 2054 or may be part of the profile URL feature 2054. In some embodiments, the downloaded HTML page may be parsed to identify one or more blocks of information contained within the HTML page. For example, the code used by the computer to display the downloaded HTML page may be parsed to determine the location of fields that may contain blocks of information (eg text blocks). Keywords may be extracted from the identified information block. In the example of a social media account associated with an individual (personal social media account), examples of keywords are "Candidate", "Publications", "Teaching", "Teaching". It may include "Student" and so on. In the example of a social media account associated with a company, examples of keywords could include "About Us," "Careers," "Join Us," and so on. In the example of a social media account associated with a meeting, examples of keywords are "Registration", "Call for Papers", "Editors", "Authors", "Authors". It can include "Reviewers" and so on. The extracted keywords may be matched against the keyword database for a match. The keyword database may contain individual keywords accumulated from existing web pages of various social media account types. The keyword feature vector may be set to indicate any match between the extracted keywords and the individual keywords.

In some embodiments, the extracted link URL may be split into tokens, which may be parsed to generate a URL feature vector. The URL feature vector may be included in the profile URL feature 2054 or may be part of the profile URL feature. The tokens may be matched against the key URL token database for a match. The key URL token database may contain individual URL tokens accumulated from existing link URLs of various social media account types. Examples of key URL tokens may include ".com", ".org", ".net", ".edu", ".gov", and the like. The URL feature vector may be set to indicate a match between the token and the individual URL tokens in the key URL token database.

At block 2060, recent social media content associated with the social media account 2002 may be retrieved. For example, recent social media posts from social media accounts 2002 may be retrieved. In some embodiments, the number of social media posts retrieved may be a particular number of the most recent social media posts. In some embodiments, the number of social media posts retrieved is a social media post made during or over a particular time period or time point (eg, a post within the last week). , Posts within the last two weeks, posts within the last month, etc.).

At block 2070, the text of the acquired recent social media content may be extracted. At block 2072, the extracted social media text may be inspected to generate the content text feature 2074. Certain types of social media accounts may be more prone to self-promotion and promotion of their content. For example, a social media account associated with a meeting may be more likely to self-promote than a social media account associated with an individual. Thus, the extracted social media text may be inspected and the content text feature 2074 may be a vector of numerical features or signals representing the degree of self-promotion. In some embodiments, the extracted social media text may be inspected to determine if the social media text has or is found with the social media account name. If the social media account name is found in the social media text, a determination is made about the percentage of social media content items that include the social media account name (eg, percentage of social media posts). You may. Content text features 2074 may be set to indicate the percentage of social media content that includes the social media account name. Additional or alternative, the extracted social media text may be inspected to determine if the social media text has or is found to have a hashtag. If a hashtag is found in social media text, the hashtag statistics or statistics associated with the hashtag may be determined and the content text feature 2074 may be set to indicate the hashtag feature. ..

At block 2080, the link URL may be extracted from the recent acquired social media content. At block 2082, link URLs from social media content may be inspected to generate content URL features 2084. As discussed above, certain types of social media accounts may be more prone to self-promotion and promotion of their content. For example, the link URL extracted from the content may be inspected and the content URL feature 2084 may be a numerical feature or a vector of signals representing the degree of self-promotion. In some embodiments, the link URL extracted from the content is inspected and the extracted link URL links to the same domain of the social media account (eg, social media account 2002). It may be determined whether or not. For example, the link URLs extracted from the content are inspected to see if any of the link URLs extracted from the content link to the same domain of the link URL in the account profile (see, for example, block 2050 above). May be determined. The content URL feature 2084 may be set to indicate the percentage of link URLs extracted from the content that link to the same domain of the social media account.

In block 2090, numerical features or signals representing social media account 2002 (eg, name feature 2024, photo feature 2034, description feature 2044, profile URL feature 2054, content text feature 2074, and content URL feature 2084) are It may be entered into a machine learning tool to determine the social media account type 2092 of the social media account. The entered numerical feature or signal indicates whether a particular feature (eg, a side) is present or absent, eg, within a web page. A social media account that is followed by a knowledgeable person and is already a seed social media account, which is included in an extended seed social media account with discipline-specific knowledge. The social media account type for each social media account out of none (eg, first candidate set 1520 in FIG. 15) may be determined according to Flow 2000.

FIG. 21 shows a flow chart of exemplary method 2100 for calculating mutually reinforcing rankings of social media accounts and content based on one or more embodiments of the present disclosure. In some embodiments, method 2100 may be performed by the information gathering system 110. Alternatively or additionally, method 2100 may be performed by any suitable system, device or device. For example, processor 2310 in system 2300 of FIG. 23 may perform one or more of the operations related to method 2100. Although shown as discrete blocks, the stages and behaviors associated with one or more of the blocks in Method 2100 may be divided into additional blocks or fewer blocks, depending on the desired implementation. May be combined or eliminated.

Method 2100 may begin at block 2102, and for each social media account, a general type weight (gtw) may be determined based on the social media account type. The gtw may be determined for each social media account among the extended seed social media accounts with discipline-specific knowledge. In some embodiments, gtw may be arbitrarily assigned to each social media account, for example based on user preferences. For example, one consideration or factor in assigning gtw may be to assign higher gtw to social media accounts that are less likely to promote their own content. That is, more trust may be given to social media accounts that are less likely to promote their own content. Based on this consideration, social media accounts that are less likely to promote their own content, such as social media accounts related to individuals, conferences, journals, news outlets, curations, software tools, etc. May be assigned a high gtw. Conversely, social media accounts that are more likely to promote their own content, such as social media accounts related to businesses, academic institutions, etc., may be assigned a lower gtw. The result is that content promoted by a social media account with a high or higher gtw is more important or appreciated than content promoted by a social media account with a lower or lower gtw. It may be that.

In block 2104, an individual weight (iw) is determined for each social media account based on its account credit (eg, the credit associated with each social media account). May be good. The iw may be determined for each social media account among the extended seeded social media accounts with discipline-specific knowledge. In some embodiments, the iw assigned to a social media account may be based on factors such as the number of re-posts, the number of likes, the number of bookmarks, the number of views, and so on. These and other factors used in determining iw may be determined based on ad hoc heuristic rules or statistical machine learning. For example, it may be assumed that some social media accounts are more popular and others are less popular. More popular social media accounts may be assigned higher or higher iw, and less popular social media accounts may be assigned lower or lower iw. In some embodiments, each factor may be assigned its own weight, and the iw assigned to the social media account may be a linear combination of the respective weights assigned to each factor.

In block 2106, general type weights may be determined for each content type based on user preference. General type weights may be arbitrarily assigned to each type of social media content, for example based on user preferences. Types of social media content may include articles, papers, slides (eg presentations), videos, photographs, audio, and the like. General type weights assigned to different types of social media content can indicate preferences (eg, user preferences) for different types of content.

Block 2108 may encode a mutually reinforcing relationship between the social media account and the content. Reinforcing relationships may be encoded as links or promotional links between social media accounts and the content promoted by those social media accounts. For example, the content may be recent content generated, shared and / or commented from a social media account as discussed above with reference to block 1920 in FIG. In some embodiments, the mutually reinforcing relationships may be encoded by constructing the bipartite graph shown in FIG.

FIG. 22 is a diagram illustrating an exemplary bipartite graph encoding a mutually reinforcing relationship between an account and content, based on one or more embodiments of the present disclosure. More specifically, exemplary, mutually reinforcing relationships between social media accounts U and content C are shown. For a social media account u, a set of all content items promoted by u (eg, posted) may be defined as C_u, and for a content item c, c will someday be promoted (eg, posted). ) A collection of all social media accounts may be defined as U_c.

As shown, this bipartite graph contains two social media accounts u1 and u2 and five content items c1, c2, c3, c4, c5. The social media account u1 has promoted the content items c1, c2, c3, c4 indicated by promotional links 2202, 2204, 2206, 2208, respectively. The social media account u2 has promoted the content items c3, c4, c5 indicated by promotional links 2210, 2212, 2214, respectively. Each promotion link may represent a promotion (eg, a post) from a connected social media account. That is, each promotional link can represent a mutually reinforcing relationship between a connected social media account and a content item.

For simplicity, only two social media accounts and five content items are shown in FIG. 22 and are used in this example, but those skilled in the art have different numbers of social media accounts and content items. You will understand that it is okay. For example, there may be hundreds, thousands, tens of thousands, or hundreds of thousands of social media accounts and / or content items.

With reference to FIG. 21 again, in block 2110, the basic link strength between the social media account and the content may be calculated. Each promotion link may have its own promotion or voting strength, or may be associated with it. A promotion or voting strength can be an indicator of the strength or weight of the promotion. That is, promotion or voting strength may be an indicator of the strength or weight of a mutually reinforcing relationship between a connected social media account and content. For example, in some embodiments, the basic link strength is that good content in one area is promoted by many good (eg, knowledgeable) social media accounts in that area, and good in a particular area. Social media accounts may be determined on the premise of promoting quality content in the field. Therefore, the basic link strength between a social media account and the content items promoted by that social media account is assigned to the gtw assigned to that social media account, to that social media account. It may be calculated based on the general type weight assigned to the content type of the iw and / or its content item.

In some embodiments, the basic link strength may take into account timeliness factors such as timeliness or freshness of the promotion. For example, if the social media account u promotes the content item c and the promotion link is defined as (u, c), the basic link strength is s (u, c) = t (u, c). * May be defined as a (u). Where t (u, c) is promotion timely and a (u) is u's account score. The account score a (u) of u may depend on the general type weight gtw (u) assigned to u and the individual weight iw (u) assigned to u. For example, the account score a (u) may be defined as gtw (u) * iw (u). The timeliness of the promotion t (u, c) may be defined using a monotonic decreasing function so that the earlier the promotion, the higher the weight. For example, the timeliness of a promotion may be defined as t (u, c) = exp (−β * k (u, c)). Here, β is a scaling constant, and k (u, c) is a time stamp function indicating that (u, c) is the kth promotion of c. Thus, a promotion that is faster in time (eg, a post) can be given or assigned a higher basic link strength than a promotion that is slower in time. In some embodiments, the more recent promotion in time may be given or assigned a higher basic link strength than the older promotion in time. In some embodiments, promotion of newer or more recent content may be given or assigned higher basic link strength than promotion of older content.

At block 2112, the adjusted link strength between the social media account and the content may be calculated. In some embodiments, the basic link strength may be adjusted based on content type preferences (eg, user preferences) associated with the promoted content. For example, the preference factor f_p may be assigned to each of the different types of content, and the adjusted link strength may be defined as s (u, c) _new = s (u, c) * f_p. .. Additional or alternative, the base link strength may be adjusted based on the link or promotion type (eg, link type or promotion type). For example, the basic link strength calculated for an initial or original promotion (eg, a promotion that creates or promotes a new content item) is adjusted, and the resulting adjusted link strength is that initial. Alternatively, the original promotion may be re-promoted or made to be higher than the adjusted link strength of the desired promotion. Similarly, the base link strength calculated for a promotion that promotes or prefers an initial or original promotion is adjusted so that the resulting adjusted link strength is that of the initial or original promotion. It may be set to be lower than the adjusted link strength. In some embodiments, some or some of the link strength from the promotion or preferred promotion (eg, retweet in the case of Twitter) that promotes the initial or original promotion is given to the initial or original promotion. , Or may be relocated. For example, suppose a social media account u repromotes or prefers content item c originally generated or promoted by another social media account u'. The adjusted link strength for u may be defined as s (u, c) _new = (1-f_t) * s (u, c), and the adjusted link strength for u'is s ( It may be defined as u', c) _new ＝ s (u', c) ＋ (f_t * s (u, c)). Here, f_t is a transfer factor. In this case, s (u, c) may transfer part of its link strength to s (u', c) by the transfer factor f_t. In some embodiments, the transfer factor f_t may be assigned to ad hoc. For example, f_t may be assigned 0.1 for a 10% transfer or discount factor for repromotion, f_t may be assigned 0.2 for a 10% transfer or discount factor for repromotion, and so on. Similarly, f_t may be assigned 0.1 to indicate a 10% transfer or transfer factor for the initial or original promotion, and f_t may indicate a 10% transfer or transfer factor for the initial or original promotion 0.2. May be assigned, and so on.

At block 2114, a mutually reinforcing ranking of social media accounts and content may be calculated. The mutually reinforcing content between the social media account and the content was calculated in the basic link strength between the social media account and the content (eg calculated in block 2110) and / or (eg in block 2112). ) It may be calculated based on the adjusted link strength between the social media account and the content. For example, mutually reinforcing learning ranking techniques may be used to calculate mutually reinforcing rankings for social media accounts and content.

Those skilled in the art will appreciate that for this process and method and other processes and methods disclosed herein, the functions performed in those processes and methods may be implemented in different order. Moreover, the steps and actions outlined are given merely as examples, and some of the steps and actions are optional or a smaller number of steps and actions without compromising the essence of the disclosed embodiments. It may be combined with an action or expanded into additional stages and actions.

FIG. 23 shows an exemplary system 2300 based on at least one embodiment described herein. The system 2300 may include any suitable system, device or device configured to identify and extract information. The system 2300 may include a processor 2310, a storage device 2320, a data storage unit 2330 and a communication device 2340. All of these may be communicatively combined. The data storage unit 2330 may include various types of data such as author objects and social media account objects.

In general, the processor 2310 may include any suitable dedicated or general purpose computer, computing entity or processing device, including various computer hardware or software modules, on any applicable computer readable storage medium. It may be configured to execute the stored instructions. For example, the processor 2310 interprets and / or executes and / or data a microprocessor, a microcontroller, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a program instruction. It may include any other digital or analog circuit configured to process.

Although shown as a single processor in FIG. 23, the processor 2310 may be any number of network locations or physics configured to perform any number of operations described herein individually or collectively. It may include any number of processors distributed across target locations. In some embodiments, the processor 2310 interprets and / or executes program instructions and / or processes data stored in memory 2320, data storage 2330 or memory 2320 and data storage 2330. You may. In some embodiments, the processor 2310 may fetch a program instruction from the data storage unit 2330 and load the program instruction into the memory 2320.

After the program instructions are loaded into the memory 2320, the processor 2310 will use the program instructions, eg, FIGS. 2, 6, 19, 20, 3, 3, 4, 5, 7, 7, 9, 9, respectively. 10, FIG. 11, FIG. 12, FIG. 13, FIG. 14, FIG. 16, FIG. 17, FIGS. 18 and 21 flows 200, 600, 1900 and / or 2000 and / or method 300, 400, 500, 700, 800, 900, 1000, 1100, 1200, 1300, 1400, 1600, 1700, 1800 and / or 2100 may be executed. For example, processor 2310 may use information from the publication system and social media system to generate author objects and social media account objects, respectively. Processor 2310 may compare information from the author object and the social media account object to identify the social media account associated with the author from the author object.

The memory 2320 and the data storage unit 2330 may include one or more computer-readable storage media that carry or store computer-executable instructions or data structures. Such computer-readable storage media may include any available medium accessible by a general purpose or special purpose computer such as processor 2310.

As an example, but not limited to, such computer-readable storage media include random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and compact disk read. Dedicated memory (CD-ROM) or other optical disk storage, magnetic disk storage or other magnetic storage device, flash memory device (eg semiconductor memory device) or computer-executable instruction or desired program in the form of a data structure. It may include non-temporary computer-readable storage media, including any other storage medium that can be used to carry or store the code and that can be accessed by a general purpose or special purpose computer. Combinations of the above may also be included within the scope of computer readable storage media. Computer-executable instructions may include, for example, instructions and data configured to cause the processor 2310 to perform an operation or group of operations.

The communication unit 2340 may include any component, device, system or combination thereof configured to transmit or receive information over the network. In some embodiments, the communication unit 2340 may communicate with other locations, other devices at the same location, or even other components within the same system. For example, the communication unit 2340 may include a modem, network card (wireless or wired), infrared communication device, optical communication device, wireless communication device (eg antenna) and / or chipset (eg bluetooth device, 802.6 device (eg urban network)). (MAN)), Wi-Fi equipment, WiMAX equipment, cellular communication equipment and / or others) and the like. Communication unit 2340 may allow data to be exchanged with the network and / or any other device or system described in this disclosure. For example, communication unit 2340 may allow system 2300 to communicate with other systems such as publication system 120, social media system 130, device 140 and web hosting system 150 of FIG.

Modifications, additions or omissions may be made to System 2300 without departing from the scope of the present disclosure. For example, the data storage unit 2330 may be a plurality of different storage media located at a plurality of positions and accessed by the processor 2310 through the network.

As mentioned above, the embodiments described herein are of special purpose or general purpose computers (eg, processor 2310 in FIG. 23), including various computer hardware or software modules, as discussed in more detail below. May include use. Further, as indicated above, the embodiments described herein use a computer-readable medium carrying or storing computer executable instructions or data structures (eg, memory 2320 or data storage 2330 in FIG. 23). It may be implemented.

As used in the present disclosure, the term "module" or "component" refers to general-purpose hardware (eg, computer-readable) of a particular hardware implementation and / or computing system that is configured to perform the actions of that module or component. It can refer to a software object or software routine stored and / or executed in a medium, processor and / or other). In some embodiments, the various components, modules, engines and services described herein may be implemented as objects or processes running on a computing system (eg, as separate threads). Some of the systems and methods described in this article are generally described as being implemented in software (stored and / or executed in general purpose hardware), but are separate hardware implementations or software. A combination of hardware implementations is also possible and is considered. In the present disclosure, a "computing entity" can be any computing system as defined earlier in this article or any module or combination of modules running on a computing system.

The terms used in this article and in particular in the annexed claims (eg, the body of the annexed claims) are generally intended as "open" terms (eg, the term "contains" is interpreted as "contains, but not limited to". The term "have" should be interpreted as "having at least ..." and the term "include" should be interpreted as "include but not limited to").

Further, if a particular number of claims are intended to be introduced, such intent is expressly stated in the claims. Without such a statement, there is no such intention. For example, to aid understanding, the accompanying claims below may include the use of the introductory phrases "at least one" and "one or more" to introduce the claims statement. However, even when the same claim contains indefinite articles such as the introductory phrase "one or more" or "at least one" and "a" or "an", the use of such clauses is an indefinite article. The introduction of a claim statement by "a" or "an" limits any particular claim containing such introduced claim statement to embodiments that include only one such statement. Should not be construed as implying (eg, "a" and / or "an" should be construed to mean "at least one" or "one or more". ). The same is true for the use of definite articles that introduce claims.

Further, even if a particular number of claims to be introduced is explicitly stated, one of ordinary skill in the art should be construed to mean such statement at least the stated number. You will recognize that (for example, the statement "two statements" without other modifiers means at least two statements or more than one statement). Moreover, in cases where idioms similar to "at least one of A, B and C, etc." or "one or more of A, B, C, etc." are used, such a syntax is generally A. Only, B only, C only, both A and B, both A and C, both B and C or all of A, B and C, etc. are intended to be included.

In addition, any distant phrase presenting two or more alternative terms, whether in the specification, claims or drawings, comprises one of the terms, comprises any of the terms, or said. It should be understood that we are considering the possibility of including both terms. For example, the phrase "A or B" should be understood to include the possibility of "A" or "B" or "A and B".

All examples and conditional language contained herein are intended for educational purposes to assist the reader in understanding the concepts contributed by the present invention and the inventor to the development of the art. It shall be construed without limitation to specific examples and conditions. Although the embodiments of the present disclosure have been described in detail, it should be understood that various changes, alternatives and changes can be made to this without departing from the spirit and scope of the present disclosure.

The following additional notes will be further disclosed with respect to the embodiments including the above embodiments.
(Appendix 1)
A computer-implemented way to rank social media accounts and content based on the mutually reinforcing relationships between social media accounts and content:
At the stage of determining the general type weight for each social media account of a plurality of social media accounts, the general type weight is based on the social media account type corresponding to the social media account. With stages;
At the stage of determining the individual weight for each social media account of the multiple social media accounts;
At the stage of encoding the mutually reinforcing relationship between each social media account of the plurality of social media accounts and the content promoted by each social media account of the plurality of social media accounts. The mutually reinforcing relationship is the content item of the content promoted by each social media account of the plurality of social media accounts and each social media account of the plurality of social media accounts. Encoded as a promotional link between and with the stage;
At the stage of calculating the basic link strength, the basic link strength is calculated for each promotion link, and the basic link strength is the general type for each social media account of multiple social media accounts. Stages based on the weights and the individual weights for each social media account of the plurality of social media accounts;
Including the step of calculating the mutually reinforcing ranking of the plurality of social media accounts and contents based on the basic link strength.
Method.
(Appendix 2)
The method described in Appendix 1 is based on the timeliness of promotion as the basic link strength.
(Appendix 3)
The method according to Appendix 2, wherein the promotion timeliness includes a monotonically decreasing function.
(Appendix 4)
At the stage of calculating the adjusted link strength, the adjusted link strength for each promotion link is the adjustment of the basic link strength calculated for that promotion link.
Further including the step of calculating the mutually reinforcing ranking of the plurality of social media accounts and content based on the adjusted link strength.
The method described in Appendix 1.
(Appendix 5)
The method of Appendix 4, wherein the adjusted link strength is based on a preference factor.
(Appendix 6)
The method according to Appendix 4, wherein the adjusted link strength is based on the type of promotion.
(Appendix 7)
The method according to Appendix 4, wherein the adjusted link strength is based on a transfer factor.
(Appendix 8)
A non-temporary computer-readable medium containing instructions that are configured to perform and / or control the execution when executed by one or more processors, said operation:
At the stage of determining the general type weight for each social media account of a plurality of social media accounts, the general type weight is based on the social media account type corresponding to the social media account. With stages;
At the stage of determining the individual weight for each social media account of the multiple social media accounts;
At the stage of encoding the mutually reinforcing relationship between each social media account of the plurality of social media accounts and the content promoted by each social media account of the plurality of social media accounts. The mutually reinforcing relationship is the content item of the content promoted by each social media account of the plurality of social media accounts and each social media account of the plurality of social media accounts. Encoded as a promotional link between and with the stage;
At the stage of calculating the basic link strength, the basic link strength is calculated for each promotion link, and the basic link strength is the general type for each social media account of multiple social media accounts. Stages based on the weights and the individual weights for each social media account of the plurality of social media accounts;
Including the step of calculating the mutually reinforcing ranking of the plurality of social media accounts and contents based on the basic link strength.
Computer readable medium.
(Appendix 9)
The computer-readable medium according to Appendix 8, wherein the basic link strength is further based on promotion timeliness.
(Appendix 10)
The computer-readable medium according to Appendix 9, wherein the promotion timeliness includes a monotonically decreasing function.
(Appendix 11)
The above operation is further:
Adjust the basic link strength;
Further comprising calculating said mutually reinforcing rankings of said multiple social media accounts and content based on adjusted base link strength.
The computer-readable medium described in Appendix 8.
(Appendix 12)
The computer-readable medium according to Appendix 11, wherein the adjustment of the basic link strength is based on a preference factor.
(Appendix 13)
The computer-readable medium according to Appendix 11, wherein the adjustment of the basic link strength is based on the type of promotion.
(Appendix 14)
The computer-readable medium according to Appendix 11, wherein the adjustment of the basic link strength is based on a transfer factor.
(Appendix 15)
One or more social media servers; and one or more processors and configured to perform and / or control the execution of operations when executed by the one or more processors. A system with a computing device that includes a non-temporary computer-readable medium containing instructions.
The operation is:
At the stage of determining the general type weight for each social media account of a plurality of social media accounts, the general type weight is based on the social media account type corresponding to the social media account. With stages;
The stage of determining the individual weight for each social media account of the multiple social media accounts;
At the stage of encoding the mutually reinforcing relationship between each social media account of the plurality of social media accounts and the content promoted by each social media account of the plurality of social media accounts. The mutually reinforcing relationship is the content item of the content promoted by each social media account of the plurality of social media accounts and each social media account of the plurality of social media accounts. Encoded as a promotional link between and with the stage;
At the stage of calculating the basic link strength, the basic link strength is calculated for each promotion link, and the basic link strength is the general type for each social media account of multiple social media accounts. Stages based on the weights and the individual weights for each social media account of the plurality of social media accounts;
Including the step of calculating the mutually reinforcing ranking of the plurality of social media accounts and contents based on the basic link strength.
system.
(Appendix 16)
The system according to Appendix 15, wherein the basic link strength is further based on promotion timeliness, including a monotonically decreasing function.
(Appendix 17)
The above operation is further:
Adjust the basic link strength;
Further comprising calculating said mutually reinforcing rankings of said multiple social media accounts and content based on adjusted base link strength.
The system according to Appendix 15.
(Appendix 18)
The system according to Appendix 17, wherein the adjustment of the basic link strength is based on a preference factor.
(Appendix 19)
The system according to Appendix 17, wherein the adjustment of the basic link strength is based on the type of promotion.
(Appendix 20)
The system according to Appendix 17, wherein the adjustment of the basic link strength is based on a transfer factor.

110 Information gathering system 112 Data storage 114 Author object 116 Social media account object 118 Personal web page object 140 Device 142 Display 150 Web hosting system 120 Publication system 130 Social media system

210 Get Digital Documents 212 Digital Documents 220 Extract Author Profile Data and Topics 222 Author Objects 230 Search Social Media 232 Social Media Account 240 Extract Social Media Profile Data and Topics 242 Social Media · Account Object 250 Compare social media objects with author objects to generate scores 252 Name Score 254 Profile Score 256 Content Score 258 Interaction Score 260 Determine Match

302 Get Digital Documents 304 Determine Topics 306 Identify Authors 308 Select Authors 310 Get Author Metadata 312 Select Social Media 314 Search Social Media 316 Select Social Media Account 318 Social Media Get Media Account Metadata 320 Generate Score 322 Other Social Media Accounts?
324 Determine if the author is the owner of a social media account based on the score 326 Other social media?
328 Other authors?
330 Extract new posts 332 Organize information 334 Provide organized information

402 Generate author objects in the database for each author of multiple digital documents 404 Finding the author's name in the author object in the social media with instructions for various social media accounts on that social media. Obtained Based on 406 Generates a name score based on a comparison of the name from the author object with the social media name from the social media account object generated based on the social media account 408 Author Generate profile scores based on comparison of author profile data from objects with social media profile data from social media account objects 410 Topics from posts on social media accounts Generate content scores based on comparisons with topics about each of the digital documents associated with the author from the author object 412 Social connections in social media accounts and associations with authors from the author object Generate interaction scores based on co-author ratings for each of the digital documents 414 Name score, profile score, whether the social media account is related to the author of the author object. 416 Extract data from new posts from social media accounts associated with the author of each author object 418 Provide the data in a topic-based organization of digital documents.

502 Generate author objects in the database for each author of multiple digital documents 504 Directing various social media accounts on some social media to search for the name of the author in the author object on the social media. Obtained Based on 506 Determines if the social media account is related to the author of the author object based on two or more of the name score, profile score, content score, and interaction score.

610 Get Digital Documents 612 Digital Documents 620 Extract Author Profile Data and Topics 622 Author Objects 630 Search Social Media 632 Social Media Account 640 Extract Social Media Profile Data and Photos 642 Social Media -Account Object 650 Search Personal Academic Web Page 652 Personal Academic Web Page 660 Extract Data and Photos of Personal Academic Web Page 662 Personal Academic Web Page Object 670 Mutual Verification of Social Media Objects and Personal Academic Web Page 671 URL Match 672 Social Media Account Match 673 Photo Match 674 Keyword Match 675 Linked Social Media Keyword Match 680 Determine Match

710 Generate author object in database 720 Get personal academic web page candidates for authors 730 Get social media account candidates for the author 740 One personal academic web page candidate and one social media account, Mutual verification as related to that author 750 Further authors?
760 Extracting social media posts from various authors' social media accounts 770 Providing the above data in a topic-based organization

810 Perform a first search for personal academic web pages based on the name of the author 820 Perform a second search for personal academic web pages based on the name of the author and the affiliation of the author 830 First search and first Merge Results from Two Searches 840 Identify Individual Profile Pages Based on Templates 850 Parse Results and Identify Results as Personal Academic Web Pages 860 Further Results?

905 Analyze web page results 910 Get web pages 915 Analyze web page code to identify information blocks 920 Extract keywords from information blocks 925 Generate keyword scores based on extracted keywords 930 Analyze Anchor Text 935 Identify Anchor Text in Result Web Page 940 Search Anchor Text in Result Web Page 945 Based on the anchor text and the name in the anchor text that matches the author. Generate anchor text score 950 Analyze the resulting URL 955 Divide the URL into fragments 960 Search the fragment for a name or keyword 965 Generate a URL score based on the name and keyword in the fragment 970 Keyword score, Categorize the results based on anchor text score and URL score 975 Is the result a personal academic web page?
980 Add results to candidate personal academic web pages

1010 Get profile of candidate social media account 1020 Identify URL in profile 1030 Compare URL of candidate personal academic web page with URL in profile 1040 Match?
1050 Is there another personal academic web page candidate?
1060 Confirmed that both the personal academic web page candidate and the social media account candidate are related to the author.

1110 Get personal academic web page candidates 1120 Parse personal academic web page candidates to identify social media accounts 1130 Compare identified social media accounts with social media account candidates 1140 Match?
1150 Confirmed that both the candidate for personal academic web page and the candidate for social media account are related to the author.

1210 Get personal academic web page candidates 1220 Parse personal academic web page candidates and extract the first photo 1230 Get the profile of social media account candidates 1240 Parse the profile and extract the second photo 1250 With the first photo Compare the second photo 1260 Match?
1270 Are there more candidates for social media accounts?
Confirmed that both 1280 personal academic web page candidates and social media account candidates are related to the author.

1310 Get personal academic web page candidates 1320 Parse the code of personal academic web page candidates to identify information blocks 1330 Extract keywords from information blocks 1340 Get profiles of social media account candidates 1350 Extract extracted keywords in profile Compare with text 1360 Do those words exceed the similarity threshold?
1370 Are There More Social Media Account Candidates?
1380 Confirmed that both personal academic web page candidates and social media account candidates are related to the author

1410 Get Personal Academic Web Page Candidates 1420 Parse Personal Academic Web Page Candidate Codes to Identify Information Blocks 1430 Extract Keywords from Information Blocks 1440 Of Social Media Accounts Linked to Some Social Media Account Candidates Get Profile 1450 Compare extracted keywords with text in profile of linked social media account 1460 Do those words exceed the similarity threshold?
1470 Are there more candidates for social media accounts?
1480 Confirmed that both personal academic web page candidates and social media account candidates are related to the author

1520 First candidate set 1510 Seed 1530 Second candidate set

1602 Get a Seed Social Media Account 1604 Get a Social Media Account Profile for a Seed Social Media Account 1606 First of the Social Media Accounts Followed by a Seed Social Media Account 1608 Compare the social media accounts of the first set with the seed social media accounts 1610 The seed social media of the first set of social media accounts. Build a first candidate set for social media accounts that are not in your account 1612 Remove general social media accounts 1614 Analyze the candidate social media accounts for the first candidate set to socialize Determining the type of media account 1616 Candidate social media accounts are knowledgeable social media accounts?
1618 Add Candidate Social Media Account as Seed Social Media Account 1620 Further First Candidate Social Media Account?
1622 Extract a second set of social media accounts that follow a seed social media account 1624 A seed social media account that is in the second set of social media accounts Build a second set of candidates for social media accounts that are not in 1626 Remove general social media accounts 1628 Get names associated with candidate accounts 1630 Determine if name or person name 1632 As candidate 1634 Identifies Interest Score 1636 Is Interest Score Above Threshold?
1638 Add Candidate Social Media Accounts to the Second Set of Social Media Accounts 1640 Are there additional second candidate social media accounts?
1642 Further Seed Social Media Accounts?
1644 Serving different content to seed social media accounts and the second set of social media accounts mentioned above

1705 Get the name of a social media account 1710 Determine if it is an organization or a person name 1715 Compare with the author database of publications 1720 Match?
1725 Category as knowledgeable account 1730 Identified interest score 1735 Does the score exceed the threshold?
Removed as a 1740 candidate

1810 Get Candidate Social Media Account Profile 1820 Count the first number of global followers for Candidate Social Media Accounts 1830 With Seed Social Media Accounts and the first set of Social Media Accounts Count the second number of local followers for a candidate social media account, including those who are following the candidate social media account 1840 Generate a topic relevance score 1850 Is the relevance score above the threshold? ??
Removed 1860 Candidate Social Media Accounts as Candidate, Learner Accounts and / or Seed Accounts

1910 Acquire extended account as a sensor 1920 Extract recent content generated, shared and / or commented from social media accounts, comprehensive 1930 Identify various social media account types 1940 Social media account types Based on, mutually reinforcing rankings of social media accounts and content

2002 Social Media Account 2010 Get Account Profile 2020 Extract Names in Account Profile 2022 Inspect Names in Account Profile 2020 Name Features 2030 Extract Photos in Account Profile 2032 Extract Photos in Account Profile Inspection 2034 Photo Feature 2040 Extract description in account profile 2042 Examine description in account profile 2044 Description feature 2050 Extract link URL in account profile 2052 Inspect link URL in account profile 2054 Profile URL Feature 2060 Get Recent Social Media Content 2070 Extract Text Content 2072 Examine Text in Content 2074 Content Text Feature 2080 Extract Link URL 2072 Examine Link URL in Content 2074 Content URL Feature 2090 Machine Learning Tool 2092 Social・ Media account type

2102 Determine general type weight (gtw) based on account type for each account 2104 Determine individual weight (iw) based on account credit for each account 2106 Determine general type weight based on user preference for each content type 2108 Encode the mutually reinforcing relationship between the account and the content 2110 Calculate the basic link strength between the account and the content 2112 Calculate the adjusted link strength between the account and the content 2114 Reinforce each other between the account and the content Calculate ranking

2300 System 2310 Processor 2320 Memory 2330 Data storage 2340 Communication unit

Claims (20)

A computer-implemented way to rank social media accounts and content based on the mutually reinforcing relationships between social media accounts and content:
At the stage of determining a general type weight for each social media account of multiple social media accounts of an entity related to a particular field of knowledge, the general type weight corresponds to that social media account. Stages based on social media account type;
At the stage of determining the individual weight for each social media account of the multiple social media accounts;
At the stage of encoding the mutually reinforcing relationship between each social media account of the plurality of social media accounts and the content promoted by each social media account of the plurality of social media accounts. The mutually reinforcing relationship is the content item of the content promoted by each social media account of the plurality of social media accounts and each social media account of the plurality of social media accounts. Encoded as a promotional link between and with the stage;
At the stage of calculating the basic link strength, the basic link strength is calculated for each promotion link, and the basic link strength is the general type for each social media account of multiple social media accounts. Stages based on the weights and the individual weights for each social media account of the plurality of social media accounts;
Including the step of calculating the ranking of the content based on the basic link strength.
Method. The method according to claim 1, wherein the basic link strength is further based on promotion timeliness. The method of claim 2, wherein the promotion timeliness comprises a monotonically decreasing function. At the stage of calculating the adjusted link strength, the adjusted link strength for each promotion link is the adjustment of the basic link strength calculated for that promotion link.
Further including the step of calculating the mutually reinforcing ranking of the plurality of social media accounts and content based on the adjusted link strength.
The method according to claim 1. 4. The method of claim 4, wherein the adjusted link strength is based on a preference factor. 4. The method of claim 4, wherein the adjusted link strength is based on the type of promotion. 4. The method of claim 4, wherein the adjusted link strength is based on a transfer factor. A non-temporary computer-readable medium containing instructions that are configured to perform and / or control the execution when executed by one or more processors, said operation:
At the stage of determining a general type weight for each social media account of multiple social media accounts of an entity related to a particular field of knowledge, the general type weight corresponds to that social media account. Stages based on social media account type;
At the stage of determining the individual weight for each social media account of the multiple social media accounts;
At the stage of encoding the mutually reinforcing relationship between each social media account of the plurality of social media accounts and the content promoted by each social media account of the plurality of social media accounts. The mutually reinforcing relationship is the content item of the content promoted by each social media account of the plurality of social media accounts and each social media account of the plurality of social media accounts. Encoded as a promotional link between and with the stage;
At the stage of calculating the basic link strength, the basic link strength is calculated for each promotion link, and the basic link strength is the general type for each social media account of multiple social media accounts. Stages based on the weights and the individual weights for each social media account of the plurality of social media accounts;
Including the step of calculating the ranking of the content based on the basic link strength.
Computer readable medium. The computer-readable medium of claim 8, wherein the basic link strength is further based on promotion timeliness. The computer-readable medium of claim 9, wherein the promotion timeliness comprises a monotonically decreasing function. The above operation is further:
Adjust the basic link strength;
Further comprising calculating said mutually reinforcing rankings of said multiple social media accounts and content based on adjusted base link strength.
The computer-readable medium according to claim 8. The computer-readable medium of claim 11, wherein the adjustment of the basic link strength is based on a preference factor. The computer-readable medium of claim 11, wherein the adjustment of the basic link strength is based on the type of promotion. The computer-readable medium of claim 11, wherein the adjustment of the basic link strength is based on a transfer factor. One or more social media servers; and one or more processors and configured to perform and / or control the execution of operations when executed by the one or more processors. A system with a computing device that includes a non-temporary computer-readable medium containing instructions.
The operation is:
At the stage of determining a general type weight for each social media account of multiple social media accounts of an entity related to a particular field of knowledge, the general type weight corresponds to that social media account. Stages based on social media account type;
At the stage of determining the individual weight for each social media account of the multiple social media accounts;
At the stage of encoding the mutually reinforcing relationship between each social media account of the plurality of social media accounts and the content promoted by each social media account of the plurality of social media accounts. The mutually reinforcing relationship is the content item of the content promoted by each social media account of the plurality of social media accounts and each social media account of the plurality of social media accounts. Encoded as a promotional link between and with the stage;
At the stage of calculating the basic link strength, the basic link strength is calculated for each promotion link, and the basic link strength is the general type for each social media account of multiple social media accounts. Stages based on the weights and the individual weights for each social media account of the plurality of social media accounts;
Including the step of calculating the ranking of the content based on the basic link strength.
system. 15. The system of claim 15, wherein the basic link strength is further based on promotion timeliness, including a monotonically decreasing function. The above operation is further:
Adjust the basic link strength;
Further comprising calculating said mutually reinforcing rankings of said multiple social media accounts and content based on adjusted base link strength.
The system according to claim 15. 17. The system of claim 17, wherein the adjustment of the basic link strength is based on a preference factor. 17. The system of claim 17, wherein the adjustment of the basic link strength is based on the type of promotion. 17. The system of claim 17, wherein the adjustment of the basic link strength is based on a transfer factor.

Images