KR101425054B1 - System and method for searching professionals - Google Patents

Abstract

A professional search system and method are disclosed. The expert search system according to an embodiment of the present invention includes an expert pool generation module for analyzing the activity details of network users in the network and ranking the experts selected for each field according to the analysis result, An expert search module for searching the expert pool according to the user's query and providing the user with a list of the experts who have been searched for the search result and a feedback module for updating the expert pool using the expert- .

Description

[0001] SYSTEM AND METHOD FOR SEARCHING PROFESSIONALS [0002]

The present invention relates to a technique for easily searching an expert on a network and enabling collaboration with a searched expert.

With the transition from the traditional industrial society to the information society, there is a growing demand for knowledge management in enterprises. In particular, in the past, knowledge management was managed with know-how, but in recent years, importance of know-where has emerged. The knowledge registered in the general knowledge management database is mostly old or non-core information due to the security of knowledge itself and the strengthening of intellectual property rights. However, the needs of the so-called experts, Is increasing day by day. There is a growing demand for generalized problem solving, mentoring, project staffing as well as who is the right professional to get the latest knowledge.

However, in the existing expert group management method, the degree holders and the high rankers were selected as specialists through a certain test and the information about them was provided in a database. In this case, however, it is impossible to apply the collective standard because the demand and the level of the specialist are different according to the individual, the case, or the field, and in particular the cost information of the expert selection process, It was a very difficult problem.

It is an object of the present invention to provide an expert search means capable of analyzing network use histories of respective network users, selecting experts for each specialized field, and supporting collaboration with the selected experts.

The expert search system according to an embodiment of the present invention includes an expert pool generation module for analyzing the activity details of network users in the network and ranking the experts selected for each field according to the analysis result, An expert search module for searching the expert pool according to the user's query and providing the user with a list of the experts who have been searched for the search result and a feedback module for updating the expert pool using the expert- .

Meanwhile, the expert search method according to an embodiment of the present invention may include analyzing activity details in the network of network users in the expert pool generation module, and selecting an expert according to the expert field according to the analysis result, A module for classifying the selected experts in the module to form a pool of experts; an expert search step for searching the expert pool according to a user's query in the expert search module and providing the expert list derived from the search results to the user; And a feedback step of, in the feedback module, updating the expert pool using the expert-specific evaluation result input from the user.

According to the embodiments of the present invention, there is an advantage in that the latest experts can be searched only by activities in the network, such as usual business activities and knowledge activities, without having to perform special tests, interviews, and expert recruitment for selecting experts .

In addition, according to the embodiments of the present invention, expert information is constantly updated according to feedback of users who have been assisted by a searched expert, so that it is possible to provide information of practically useful experts.

1 is a block diagram illustrating an entire network service system 100 including an expert search system according to an embodiment of the present invention.
2 is a block diagram illustrating a detailed configuration of the expert search system 106 according to an embodiment of the present invention.
FIG. 3 is a diagram showing an example of visual analysis of a connection degree of each user through analysis of a social network.
4 is a diagram illustrating a screen for providing an expert recommendation list according to an exemplary embodiment of the present invention.
FIG. 5 is a flowchart illustrating an expert search method 500 according to an embodiment of the present invention.

Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. However, this is merely an example and the present invention is not limited thereto.

In the following description, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear. The following terms are defined in consideration of the functions of the present invention, and may be changed according to the intention or custom of the user, the operator, and the like. Therefore, the definition should be based on the contents throughout this specification.

The technical idea of the present invention is determined by the claims, and the following embodiments are merely a means for effectively explaining the technical idea of the present invention to a person having ordinary skill in the art to which the present invention belongs.

1 is a block diagram illustrating an entire network service system 100 including an expert search system according to an embodiment of the present invention. As shown, the network service system 100 includes a plurality of network service entities 102, a plurality of network user terminals 104, and an expert search system 106, And 108 are connected to each other to exchange data.

The network service entity 102 is an in-network component for providing online users with services such as e-mail service, blog service, social network service (SNS), online bulletin board service, And all kinds of services provided on the Internet.

The network user terminal 104 is a terminal used by network users who want to use a service provided by the network service entity 102. In the embodiment of the present invention, the network user terminal 104 includes all kinds of user equipment that can be connected to a network and receive services. For example, a personal portable terminal such as a desktop or notebook computer, a smart phone, a personal data assistant (PDA), or a tablet computer may be a network user terminal 104 according to the present invention.

The expert search system 106 is a system for providing the network users with a means for searching for experts necessary for each individual or each case and for performing cooperation with the searched experts. The expert search system 106 analyzes the activity of network users in the network 108 (i.e., the network service entity 102 utilization history of network users via the network user terminal 104) . For example, if a particular network user is frequently posting blog posts, primarily in connection with network security, chatting with other users in the SNS, or sending or receiving emails frequently, The user can be selected as an expert in the field of network security by analyzing the network usage history of the user. In addition, the expert search system 106 may rank the selected experts according to the degree of activity in the network, construct the ranked expert information as a specialist pool in the form of a database, and provide the information to the user. The expert information can be continuously updated by reflecting the expert evaluation (feedback) of the users according to the user information.

2 is a block diagram illustrating a detailed configuration of the expert search system 106 according to an embodiment of the present invention. As shown, the expert search system 106 according to an embodiment of the present invention includes an expert pool generation module 200, an expert search module 202, and a feedback module 204.

The expert pool generation module 200 analyzes the activities of the network users in the network 108 and sets up expert pools by ranking the experts selected according to the expertise according to the analysis result.

The expert pool generation module 200 may extract an effective tag for each network user from the network activity details of the network users, and may select a specialty field of each network user using the valid tag. The activities in the network include, for example, registering, inquiring or verifying knowledge in the mail reception / transmission history of each network user, in-house knowledge management system (meaning a system for collecting and managing information or information necessary for the company) A history of blog posts, a history of social network services, or personal profile information registered by the network users (the project history, the department history, the awards, and the writing history , Lecture history, major and interest fields, etc.).

The valid tag selection process will be described in more detail as follows. The expert pool generation module 200 collects the documents posted in the network, for example, the posts posted by each network user, the emails transmitted, and the like, and extracts keywords from the activity history through morphological analysis on the activity details . An algorithm for extracting a keyword through morphological analysis from a document is well known in the art, and a detailed description thereof will be omitted here.

When the keyword is extracted, the expert pool generation module 200 selects a keyword that satisfies a predetermined criterion among the extracted keywords as an effective tag. The effective tag selection criterion can be defined as follows.

First, the expert pool generation module 200 may extract a keyword indicating a frequency of a predetermined value or more among the keywords included in the document registered in the network 108 by the specific network user, as an effective tag of the corresponding network user. For example, in the case of a keyword that appears in a document at a frequency of 5% or more, the keyword may be the valid tag. Keywords frequently appearing in a document are likely to be close to the subject of the document or a term in a field that the author of the document is familiar with.

Alternatively, the specific network user can extract the keywords retrieved from the keywords used to search for contents in the network more than a predetermined number of times by using the effective tags of the corresponding network users. For example, a keyword that is retrieved more than 20 times by a specific network user may be an effective tag of the corresponding network user. This is because, in general, when you search for specific keywords frequently, you are likely to be engaged in or are more interested in the subject associated with the keyword.

In addition, the expert pool generation module 200 may select a tag or the like that is directly defined by the creator of each document as an effective tag. Since the tags defined in the document are given to allow the user to best express the topic of the document, it is possible to accurately measure the interests of the relevant network user.

In this manner, effective tag extraction criteria in the expert pool generation module 200 are listed, but this is merely exemplary and the present invention is not limited thereto. That is, the expert pool generation module 200 can set an appropriate effective tag extraction criterion according to the characteristics of the network and users, and the scope of rights of the present invention is not limited to a specific effective tag extraction criterion.

When the effective tags for each network user are extracted through the above-described process, the expert pool generation module 200 calculates the frequency of the extracted effective tags and selects the special fields for each network user. That is, the expert pool generation module 200 may select a special field to which the valid tag having the extracted valid tag number equal to or greater than a predetermined value (for example, 20 or more) belongs to the special field of the corresponding network user . For example, when a plurality of valid tags such as "money "," budget ", "investment ", and the like are extracted from the posts registered by a specific network user, the expert pool generation module 200 generates keywords The field of specialization, ie finance / accounting, belonging to the network user can be selected as a specialization.

If the valid tag is a tag defined directly from the network user, the expert pool generation module 200 transmits an effective tag having a frequency of a defined tag equal to or more than a preset value (for example, 10 times) Can be a professional field. That is, the expert pool generation module 200 may set a frequency reference value for selecting a specialty field according to whether the valid tag is extracted from a document or directly from a network user. If it is defined directly by a network user, it can more accurately identify the expertise of the network user than by morphological analysis. In addition, the expert pool generation module 200 may select a special field registered by the network user in the profile of the network user as a special field of the network user.

On the other hand, the expert pool generation module 200 can select experts for each specialty by using Social Network Analysis. In other words, through the analysis of the social network, a hub that plays a key role in the field of specialization can be found. The network users located in this hub are likely to be experts or knowledge brokers, so when analyzing them through social network analysis, they will be able to know the so-called know-where. do.

Specifically, the expert pool generation module 200 collects social networking activities (mail reception / transmission, messenger usage history, posting registration / inquiry details, etc.) of network users for keywords defined for specific professional fields, The analysis is conducted using a social network analysis tool to score the connectivity of each user with other users, that is, the degree of communication with other users related to the keyword. At this time, if the value of the degree of connection is high, it is highly likely to be an expert who acts as a hub of the specialized field. Therefore, the expert pool generation module 200 may determine the connection degree with other network users as a result of the social networking activity analysis A network user having a set value or more is selected as an expert in a special field to which the specific keyword belongs.

FIG. 3 shows an example of visual analysis of the connectivity of each user through the analysis of the social network. In the illustrated embodiment, it can be seen that users who are displayed in a circular form have a relatively high degree of connection with other users, and such users are highly likely to be experts in this field. In the case of a specific social network analysis methodology, any of the algorithms known in the art may be used, and the present invention is not limited to a specific social network analysis algorithm.

After analyzing the network activities of each network user and analyzing the results of the social network analysis, the expert pool generation module 200 calculates the expert's index of each network user in each special field using the calculated results do. The expert index can be obtained by summing the values calculated by applying the predetermined weights to the previously calculated values using a predetermined index calculation formula. The expert pool generation module 200 may construct the expert's exponentiation formula so as to give more weight to recent network activity details. In addition, the expert pool generation module 200 may form the expert index calculation equation so that the feedback result of the feedback module 204, which will be described later, is also reflected in the expert index calculation.

When the expert indexes for each expert field of each network user are calculated through the above-described equations or the like, the expert pool generating module 200 ranks the selected experts using the calculated indexes, .

The expert pool can, for example, classify the selected experts into a taxonomy form, that is, a top-down tree form, and store them in the expert pool. In this case, the taxonomy may be configured to support multiple classification schemes. For example, if an expert named "Hong Gil Dong" is a dispute and litigation expert in the field of life insurance, its information can be classified and stored as follows.

For example,

Industry - Finance> Insurance> Life Insurance

Job role - Legal affairs management> Dispute / litigation expert

Alternatively, the expert pool generation module 200 may match and store the keywords belonging to the expert field of the selected expert. At this time, the keyword may be, for example, an effective tag extracted in the analysis process. For example, it can be configured as follows.

For example,

Related Tags: Insurance, Life Insurance, Finance, Dispute, Litigation, Settlement, Adjustment, etc.

Next, the expert search module 202 searches the expert pool generated according to the user's query, and provides the user with a list of the experts who have obtained the search results. In this case, the user means a user in the network who needs the help of a specialist. The user may use the expert search system 106 to search for a specialist in his / her field of expertise, listen to advice from a searched expert, or collaborate with an expert.

For example, a user who wishes to obtain expert assistance can search for keywords in the field in which he or she wants help, or sequentially search the tree form to find an expert in his / her field. In this case, the expert search module 202 may sort the inputted keyword or expert according to the expert field according to the expert index, and recommend the user to the user.

Meanwhile, the expert search module 202 may provide the information of the intermediary between the searched expert and the user together with the expert. For example, if there is a user who has an acquaintance relationship with a searched expert among a user who has an acquaintance in the social network service (SNS) and a user who wants to obtain expert assistance, It can be recommended as an intermediary for. The relay person may be one person, several persons, or may be connected to a specialist through various stages of relay depending on the situation. FIG. 4 exemplifies the expert recommendation list providing screen. In the case of the expert recommended for the third time in the drawing, it can be seen that two relay persons are output together.

Through the expert search module 202, the user can easily search for a specialist in a particular field of expertise, and can receive the necessary assistance through collaboration with the searched expert.

Next, the feedback module 204 receives the evaluation result of the selected expert from the user, and updates the expert pool using the input result of the expert-specific evaluation.

A user who has been assisted by an expert can evaluate the selected expert in various ways. For example, the user may score the aid of the selected expert if it is considered useful, register it in the feedback module 204, or recommend the expert through a "recommend" function. In addition, if it is judged that the expert needs to be assisted in the future, the expert can be registered (tagged) in his / her "favorite book" list, and various items such as the speed and accuracy of the answer The experts can be evaluated through

The feedback module 204 receives the evaluation information such as the number of recommendations of each expert registered by each user, the number of favorite tagged times, the satisfaction degree of answers and the quickness of response, and reflects the evaluation information to each expert's expert index )do. Although the above-mentioned method of reflecting the expert index may be varied, it is general that the expert index is increased when there is positive feedback, and is decreased when it is the opposite.

By continuously reflecting the results of the assistance of the experts on the expert index in this way, according to the present invention, more accurate expert information can be provided to the users.

FIG. 5 is a flowchart illustrating an expert search method 500 according to an embodiment of the present invention.

First, the expert pool generation module 200 analyzes network activity details of the network users, and selects an expert according to an expert field according to the analysis result (502).

In operation 502, it is possible to extract an effective tag for each network user from the activity details of the network users in the network, and select an expert field of each network user using the valid tag. In addition, the step 502 analyzes the social networking activities of the network users according to specific keywords, and transmits the network user having a connection degree with other network users as a result of the social networking activity analysis to a specialist . ≪ / RTI > Details related to the network activity analysis and the social networking activity analysis have been described in detail above, and a repeated description will be omitted here.

Next, the expert pool generation module 200 ranks the experts selected to construct a special pool (504). Specifically, the expert pool generation module 200 calculates an expert index of a selected expert in each special field using the network activity details of the network users and the social networking analysis result, Are stored and managed in the expert pool database.

Next, in the expert search module 202, the expert pool is searched according to the user's query, and the expert list derived from the search result is provided to the user (506). At this time, the expert search module 202 arranges the experts derived from the expert pool according to the calculated expert index, and provides the sorted results to the user. Also, when there is another user in the network having a common relationship with the user who is searched for, the other user can be provided to the user together with the expert search result as a relay of the expert.

Finally, the expert module updates the expert pool using the expert-specific evaluation result input from the user in the feedback module 204 (508). That is, in this step, expert-specific evaluation information including at least one of a recommendation number of experts, a favorite tagged count, an answer satisfaction and an answer speed is received from the user, Recalculate the expert index.

On the other hand, an embodiment of the present invention may include a computer-readable recording medium including a program for performing the methods described herein on a computer. The computer-readable recording medium may include a program command, a local data file, a local data structure, or the like, alone or in combination. The media may be those specially designed and constructed for the present invention or may be known and available to those of ordinary skill in the computer software arts. Examples of computer readable media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floppy disks, and magnetic media such as ROMs, And hardware devices specifically configured to store and execute program instructions. Examples of program instructions may include machine language code such as those generated by a compiler, as well as high-level language code that may be executed by a computer using an interpreter or the like.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is clearly understood that the same is by way of illustration and example only and is not to be construed as limiting the scope of the present invention. I will understand.

Therefore, the scope of the present invention should not be limited to the above-described embodiments, but should be determined by equivalents to the appended claims, as well as the appended claims.

100: Network service system
102: network service entity
104: network user terminal
106: Expert Search System
200: Expert pool creation module
202: Expert Search Module
204: Feedback module

Claims (25)

An expert pool generation module for analyzing the network activity details of the network users and ranking the experts selected according to the expertise according to the analysis result to construct an expert pool;
An expert search module for searching the expert pool according to a user's query for searching for an expert and providing the user with a list of experts who are searched; And
And a feedback module for updating the expert pool using the expert-specific evaluation result input from the user,
The expert pool generation module extracts an effective tag for each network user from the activity details of the network users in the network, selects a specialty field of each network user using the effective tag,
Wherein the expert pool generation module analyzes a social networking activity of the network users according to a specific keyword and analyzes the social networking activity of the network users as a result of the analysis of the social networking activity, Expert search system, selected by experts.
delete The method according to claim 1,
The activity details in the network include one of mail reception / transmission history of each network user, post registration / inquiry history in a bulletin board, blog post registration / inquiry history, social network service utilization history, and personal profile information registered by the network users Gt; a < / RTI > expert search system.
The method according to claim 1,
Wherein the expert pool generation module extracts a keyword indicating a frequency of a predetermined value or more among the keywords included in the document registered in the network by the specific network user with an effective tag of the corresponding network user.
The method according to claim 1,
Wherein the expert pool generation module extracts keywords retrieved by a specific network user from a predetermined number of times or more of the keywords used to search for contents in the network, using the valid tags of the corresponding network users.
The method according to claim 1,
Wherein the expert pool generation module selects a special field to which the valid tag having a frequency of the extracted valid tag equal to or greater than a predetermined value belongs is a specialized field of the network user.
delete The method according to claim 1,
The expert pool generation module calculates an expert index of a selected expert in each special field using the network activity details of the network users and the social networking analysis result, , Expert search system.
The method of claim 8,
And the expert search module arranges the experts derived from the expert pool according to the calculated expert index and provides the experts to the user.
The method of claim 9,
Wherein the expert search module provides the other user as an intermediary of a corresponding expert to the user when there is another user in the network having a common knowledge relationship between the user and the searched expert.
The method of claim 8,
Wherein the feedback module receives from the user expert-specific evaluation information including at least one of a recommendation number of each expert, a favorite tagged count, an answer satisfaction and an answer speed.
The method of claim 11,
Wherein the feedback module recalculates the expert index using the expert-specific evaluation result input from the user.
Analyzing the network activity details of the network users in the expert pool generation module, and selecting an expert in the field according to the analysis result;
Constructing an expert pool by ranking selected experts in the expert pool creation module;
An expert searching step of searching the expert pool according to a user's query for searching for an expert in the expert search module and providing a list of experts derived from the search results to the user; And
And a feedback step of, in the feedback module, updating the expert pool using the expert-specific evaluation result input from the user,
The expert selection step may include extracting an effective tag for each network user from the activity details of the network users in the network, selecting a specialty field of each network user using the effective tag,
Wherein the expert selection step includes analyzing a social networking activity of the network users according to a specific keyword and analyzing a network user having a connection degree with other network users as a result of the social networking activity analysis, To search for experts.
delete 14. The method of claim 13,
The activity details in the network include one of mail reception / transmission history of each network user, post registration / inquiry history in a bulletin board, blog post registration / inquiry history, social network service utilization history, and personal profile information registered by the network users Or more.
14. The method of claim 13,
Wherein the expert selection step extracts a keyword indicating the frequency of a predetermined value or more among the keywords included in the document registered in the network by the specific network user with the effective tag of the corresponding network user.
14. The method of claim 13,
Wherein the expert selection step extracts a keyword retrieved by a specific network user from a predetermined number of times or more of the keywords used to search for contents in the network, using an effective tag of the corresponding network user.
14. The method of claim 13,
Wherein the expert selection step selects the special field to which the valid tag having the extracted valid tag number equal to or greater than a preset value belongs to the special field of the network user.
delete 14. The method of claim 13,
The expert pool configuration step may include calculating an expert index of a selected expert for each special field using the network activity details of the network users and the social networking analysis result and ranking the selected experts according to the calculated expert index How to search experts.
The method of claim 20,
Wherein the expert searching step sorts the experts derived from the expert pool according to the calculated expert index and provides the experts to the user.
23. The method of claim 21,
Wherein the expert searching step provides the other user as an intermediary of a corresponding expert to the user when there is another user in the network that has a common knowledge relationship between the user and the searched expert.
The method of claim 20,
Wherein the feedback step receives from the user expert-specific evaluation information including at least one of a recommendation number of each expert, a favorite tagged count, an answer satisfaction, and an answer speed.
24. The method of claim 23,
Wherein the feedback step recalculates the expert index using the expert-specific evaluation result input from the user.
A computer-readable recording medium having recorded thereon a program for performing the method according to any one of claims 13, 15 to 18, and 20 to 24 on a computer.

Images