WO2022091281A1

WO2022091281A1 - Information processing device, information processing method, and program

Info

Publication number: WO2022091281A1
Application number: PCT/JP2020/040569
Authority: WO
Inventors: 佳昭東海林; 志朗小笠原; 朋子柴田; 友則森; 有記卜部; 美沙深井
Original assignee: 日本電信電話株式会社
Priority date: 2020-10-29
Filing date: 2020-10-29
Publication date: 2022-05-05
Also published as: JP7452693B2; JPWO2022091281A1

Abstract

Provided is an information processing device that searches for an advisor in response to a request from a person who is seeking advice. The information processing device comprises: an information acquisition unit that acquires, in response to a search request from a first user for searching for a candidate user from among a plurality of users, first text information which is handled in a terminal device used by the first user; a condition generation unit that classifies, in accordance with the frequency of appearance in second text information pertaining to previous work of the first user, words contained in the acquired first text information into a first word group having a frequency of appearance of lower than a first threshold and a second word group having a frequency of appearance of not lower than the first threshold; a search process unit that extracts a candidate user from among the plurality of users in accordance with the frequency of appearance of words belonging to the first word group in third text information pertaining to previous work of each of the users; and a result output unit that outputs information for presenting, to the first user, information pertaining to the candidate user.　

Description

Information processing equipment, information processing methods and programs

An embodiment of the present invention relates to an information processing apparatus, an information processing method and a program.

In companies, etc., a person in charge (personnel person, accounting person, etc.) is assigned to the person who carries out the work, and the work is carried out according to the assigned person. The person in charge of the work is a person whose skill set including experience is uniform to some extent. Each business operator can naturally listen to conversations between people around him without having to participate directly, who is consulting with whom, who is familiar with what, and who It is thought that it is possible to detect what is in trouble on a daily basis.

In the future, with the diversification of business forms, it is expected that the skill sets possessed by each human resource will diversify. In addition, it is expected that the business execution system will be a mixture of remote environment and office environment, and the chances of hearing the above-mentioned exchanges with the surroundings will decrease.

Therefore, it is expected that the situations in which each business operator needs help will be diverse.
For those in need of help, it can be more difficult than ever to know who is familiar with what and to find the right place to consult in the event of a problem. Furthermore, it is expected that it will be more difficult for the helper to determine which troubles can be easily helped based on their own experience.

In this way, when a problem that requires consultation with another person occurs in business, etc., there is a need to search for a consultation destination where the person who wants to consult has experience with the problem. Here, a technique has been proposed that makes it possible to search for in-house users who have abundant knowledge about what they want to know (see, for example, Non-Patent Document 1).

However, in order to search for a person who has work experience about what he / she wants to know, it is necessary to register each person with a tag so that he / she can search for the work experience he / she has in advance. In addition, a search based on the keywords entered by the consultant does not always search for an appropriate consultation destination (for example, the system provider is searched even though he / she wants to know how to use the system in a specific business). Conceivable.

The present invention was made by paying attention to the above circumstances, and an object thereof is to provide a technique that enables a more appropriate search without requiring prior tagging for the search target person.

In order to solve the above problems, the first aspect of the present invention is in the information processing apparatus.
Information for acquiring the first text information handled by the terminal device used by the first user in response to a search request issued by the first user to search for a candidate user from among a plurality of users. Acquisition department and
The first word group whose appearance frequency is lower than the first threshold value according to the appearance frequency of the words included in the first text information in the second text information related to the past work of the first user. And a condition generation unit that divides into a second language group whose appearance frequency is equal to or higher than the first threshold value.
A search processing unit that extracts candidate users from a plurality of users according to the frequency of appearance of words belonging to the first word group in the third text information related to the past work of each user.
It is provided with a result output unit that outputs information for presenting information about the candidate user to the first user.

According to the first aspect of the present invention, the text information handled by the terminal device used by the first user is acquired in response to the search request from the first user. The words included in the text information are classified according to the frequency of appearance in the second text information related to the past work of the first user. Words that appear infrequently in the second text information relating to the past work of the first user can be rephrased as words that are inexperienced by the first user or words that require information by the first user. .. Among such words in the text information handled by the first user in the terminal device, the search target user has a low frequency of appearance in the second text information related to the past work for the first user. Candidate users are extracted based on the frequency of appearance in the second text information related to the past work of.

In this way, candidate users are extracted according to the frequency of appearance in the third text information related to the past work of the search target user for the necessary information, so that it is not necessary to tag the search target user in advance. .. Further, since the search is performed based on the information presumed to be useful for the first user in consideration of the experience of the first user, more appropriate search results can be obtained. Further, since it is not necessary to input a search query, it is highly convenient for the first user, and it is possible to flexibly perform a search that reflects the current situation without being bound by a specific keyword.

That is, according to the first aspect, it is possible to provide a technique that enables a more appropriate search without requiring prior tagging of the search target person.

FIG. 1 is a diagram showing an example of an overall configuration of a search system including a search server as an information processing device according to an embodiment. FIG. 2 is a schematic diagram showing an outline of the processing of the search server shown in FIG. FIG. 3 is a block diagram showing an example of a functional configuration of a search server as an information processing device according to an embodiment. FIG. 4 is a block diagram showing an example of the hardware configuration of the search server shown in FIG. FIG. 5 is a flowchart showing an outline of processing by the search server shown in FIG. FIG. 6 is a flowchart showing an example of the procedure of the terminal handling content grasping process among the processes shown in FIG. FIG. 7 is a diagram showing an example of text information acquired by the process shown in FIG. FIG. 8 is a diagram showing a first example of data stored in the process shown in FIG. FIG. 9 is a diagram showing a second example of data stored in the process shown in FIG. FIG. 10 is a flowchart showing an example of the procedure of the pairing condition generation process among the processes shown in FIG. FIG. 11 is a schematic diagram showing a first example of the determination process among the processes shown in FIG. FIG. 12 is a schematic diagram showing a second example of the determination process among the processes shown in FIG. FIG. 13 is a diagram showing an example of data stored in the process shown in FIG. FIG. 14 is a flowchart showing an example of the procedure of the pairing process among the processes shown in FIG. FIG. 15 is a diagram showing an example of data stored in the process shown in FIG. FIG. 16 is a flowchart showing an example of the procedure of the pairing result output process among the processes shown in FIG.

Hereinafter, embodiments relating to the present invention will be described with reference to the drawings. Hereinafter, the same or similar reference numerals are given to the elements that are the same as or similar to the described elements, and the duplicated description is basically omitted. For example, when there are multiple identical or similar elements, a common code may be used to explain each element without distinction, and the common code may be used to describe each element separately. In addition, a branch number may be used.

[One Embodiment]
(1) Configuration (1-1) Search System FIG. 1 is a diagram showing an example of the overall configuration of a search system 100 including an information processing apparatus according to an embodiment of the present invention. The search system 100 includes a search server 1 capable of communicating with each other via a network NW, and user terminals UT1, UT2, ... UTn (hereinafter, collectively referred to as "user terminal UT"). ..

The information processing device according to one embodiment can be implemented as the search server 1. The search server 1 is a server computer or a personal computer managed by an organization such as a company, a school, a union, or a membership community.

The search server 1 receives a request from a user who has a problem (hereinafter referred to as a "consultant" or a "consultant user") by communicating with each user terminal UT, and receives a consultation (a user who receives a consultation (hereinafter referred to as a "consultant"). Hereinafter, a process of searching for a candidate of "consultation destination" or "consultation destination user") and presenting the search result to the consultation source user is performed. The search server 1 can also notify the consulting user of the fact that he / she has been extracted as a candidate, that a problem has occurred, or the information of the consulting source user. In this way, the search server 1 connects the consulting source user and the consulting destination user by recommending the consulting destination user to the consulting source user and making the consulting candidate user aware of the occurrence of a problem (). Here, it is referred to as "pairing".) Support is provided.

The network NW may be, for example, the Internet, an intranet, a LAN (Local Area Network), a WAN (Wide Area Network), or the like, and may include a wired or wireless network.

The user terminal UT is an information processing terminal used by the user, and is, for example, a personal computer, a smartphone, a tablet terminal, a mobile phone, or the like. The user belongs to the above-mentioned organization that manages the search server 1, and can perform business using the user terminal UT and communicate with other users via the user terminal UT. be. The user terminal UT may be a dedicated terminal for each user, or may be shared by a plurality of users.

In the following, as an example, a situation in which a user as a business operator belonging to a company uses the search system 100 using each user terminal UT will be described. The search server 1 may be a device separate from the user terminal UT, or may be integrated with any user terminal UT.

As mentioned above, in the business environment of recent years, the skill sets possessed by each user are diversified, and "who is familiar with what", "who is in trouble", etc. are naturally detected on a daily basis. Is becoming difficult. Therefore, when a problem that requires consultation with another person occurs, the user who wants to consult needs to search for a consultation destination that has experience in the problem. The search server 1 is a person who can share "business situation at the time of trouble" and "solution suitable for the situation" with the minimum effort (including explanation) when such a trouble occurs. Is intended to allow both the counselor and the counselor to find each other.

In the conventional method, content that has a mechanism to explicitly retain the creator of created / registered documents (email, Web page, office document, etc.) is stored, and people who want to find experts can search queries or keywords. By inputting, the creator / user of the content including the keyword is extracted. Here, in order to perform a search, in order to clarify who has what kind of knowledge on the system, each work experience is actively tagged to the relevant person (for example, "# reception", "#". "Development", "# Budget management") needs to be done. Alternatively, a mechanism for automatically tagging each work experience to the relevant person is required, and technology for that is required.

In addition, in the conventional method, when extracting a consultation destination using a keyword, the document created / registered by the person or the description content of the sent / received email is used as information on the experience of the consultation destination candidate. However, in this case, the holders of experience with a certain keyword are limited to document creators / registrants other than sent / received emails.

For example, if a problem occurs when using a business system, a document containing the vocabulary "related to the problem or business status (such as the contents displayed on the business system screen)" used as a search keyword is a business system usage manual. Most of them are created / registered by business system providers, and few are created / registered by users. Therefore, there is a higher possibility that the business system provider will be extracted as a consultation destination than the business system user. However, the business system provider does not usually perform business as a user. In addition, even if a problem occurs when using a business system, it is not necessarily related to how to use the business system, and a specific business that is unknown to the business system provider and is to be performed on the business system. It may be related to the content. For these reasons, it is unlikely that the business system provider has experience in solving problems, but rather the user is more likely to meet the requirements of the relevant case. As a result, there is a risk that people who actually meet the requirements of the relevant project will be omitted from the candidates for consultation.

Further, in the conventional method, only the keyword input by the counselor himself is used as a search condition, and the counselor is extracted. As the search keywords are listed below, for example, (Example a) to (Example c), it is not possible to distinguish between those related to business conditions and those related to troubles.
(Example a) When the search keyword selected by the counselor is limited to the vocabulary related to the work situation: Even if the counselor who has abundant experience in the same work situation as the counselor can be extracted, he / she has experience in solving problems. Whether or not is not considered. Therefore, there is a high possibility that the consultant does not have the experience of solving the problem, and in that case, it is not useful for solving the problem.
(Example b) When the search keyword selected by the counselor is limited to the vocabulary related to the problem: Even if the counselor who has abundant experience in the problem can be extracted, the counselor is facing the problem. It does not take into account whether or not you have experience in the same business situation as the situation. Therefore, there is a high possibility that the consultant does not have experience in the business situation, and in that case, a lot of explanation is necessary for the consultant to understand the business situation at the time of his / her trouble. Will be. Even if the counselor shares his / her own experience as it is, the solution does not correspond to the counselor's business situation, and it is necessary to prepare a new explanation according to the counselor's business situation.
(Example c) When the search keyword selected by the consultant itself includes vocabulary related to both business status and trouble: It is not distinguished whether the search keyword is related to business status or trouble, for example, the search keyword. The creators / users of the content containing more content will be extracted as consultation destinations. Therefore, the consultation destination to be extracted is not limited to the creator / user of the content including the vocabulary related to the trouble, and the same problem as the above (example a) occurs.

Based on the above problems, the search server 1 or the search system 100 according to the embodiment pays attention to at least one of the following points.
[Point 1] Text information handled by each user terminal UT is acquired in the background, recorded and accumulated in association with the business performer (user), and used for grasping the business experience of each business performer.
[Point 2] The business information of the current consultant is divided into "problem information" and "peripheral information".
[Point 3] Select candidates for consultation based on work experience related to trouble information, and assign a higher degree of recommendation to those who have more trouble information and peripheral information.
[Point 4] Check the status of possession of work experience of trouble information and peripheral information not only for the counselor but also for all the business performers. As a result, pairing is realized not only from the perspective of the counselor but also from the perspective of the counselor.
[Point 5] As a result of the pairing process, the candidate for consultation who has been assigned a high degree of recommendation is notified that there is a problem that may be supported based on his / her own experience.
[Point 6] In relation to the above [Point 1], in addition to the text information handled by the user terminal UT, the screen image displayed and the path of the document used are acquired and associated with the text information. Record and accumulate. Text information including trouble information and peripheral information, which are pairing conditions, from the accumulated text information when the candidate for consultation receives a consultation or receives a notification related to [Point 5]. And display the screen image and path associated with it.

FIG. 2 shows an outline of the processing of the search server 1 according to the embodiment. The counselor (consulting source user) USX has a problem and is wondering who to consult. It is assumed that the text information handled by the user terminal UTX used by the consultant USX is stored in advance in an arbitrary storage unit as work experience (log). When a trouble occurs as shown in FIG. 2, when the consultant USX issues a search request to the search server 1 via the user terminal UTX, the search server 1 sends a search request to the search server 1 at that time point (or a certain time including that time point). The text information handled by the user terminal UTX in the frame) is acquired as the current business status. The search server 1 compares the words or words included in the acquired text information (here, collectively referred to as "vocabulary") with the accumulated work experience, and calculates the frequency of appearance in the accumulated work experience. The vocabulary distribution image VDX represents how often each word in the text information acquired as the current business situation appears in the business experience of the consultant USX. Here, it is shown that the light-colored area has a low frequency of appearance, and the dark-colored area has a high frequency of appearance.

Based on the frequency of appearance, the search server 1 extracts words with little experience as "problem information" and words with a lot of experience as "peripheral information" among the words included in the current business situation of the consultant USX. do. Judgment of the amount of experience can be made using a pre-specified threshold.

Next, the search server 1 determines the amount of experience of trouble information and peripheral information for business performers other than the consultant. It is assumed that the text information handled by each user terminal UT is acquired in advance as work experience for these business performers and is stored in an arbitrary storage unit. In this example, user US1 and user US2 are extracted as consultation destination candidates. It is determined that the user US1 has sufficient experience in particular peripheral information, and the user US2 has less experience in peripheral information but more experience in trouble information.

In the following explanation, for convenience, among all the business performers (all users) who use the search system 100, the counselor (consulting source user) is represented as USX to distinguish it from the business practitioners other than the counselor. Similarly, among all user terminals UT, the user terminal used by the consulting source user USX is referred to as UTX. However, as is understood, the consulting source user USX and the user terminal UTX do not refer to any fixed user or user terminal, and may be replaced with another user or user terminal at any time depending on the situation in which a problem occurs. Hereinafter, when the term "user terminal UT" is simply referred to, the user terminal UTX may be included.

(1-2) Search Server (1-2-1) Functional Configuration Next, the configuration of the search server 1 according to the embodiment will be described.
FIG. 3 shows an example of the functional configuration of the search server 1. In FIG. 3, the search server 1 outputs a pairing result, a functional unit F1 for grasping the handling contents of the user terminal UT, a functional unit F2 for generating a pairing condition, and a functional unit F3 for performing pairing processing. It has a functional unit F4 to perform.

The search server 1 includes a terminal handling content acquisition unit 11 and a terminal handling content storage unit 15 with respect to the functional unit F1. The search server 1 also includes a pairing condition generation unit 21, a pairing condition editing unit 22, and a pairing condition holding unit 25 with respect to the functional unit F2. The search server 1 also includes a pairing process execution unit 31 with respect to the functional unit F3. The search server 1 also includes a pairing result presentation unit 41, a pairing result notification unit 42, and a pairing result holding unit 45 with respect to the functional unit F4.

The terminal handling content acquisition unit 11 performs a process of acquiring text information handled by the user terminal UT (particularly, the user terminal UTX). The terminal handling content acquisition unit 11 is, for example, an interface independently provided by UI Automation (hereinafter referred to as "UIA"), Microsoft Active Accessibility (hereinafter referred to as "MSAA"), or a program operating in the user terminal UT. Can be used to acquire the text information displayed on the screen of the user terminal UT. Alternatively, the terminal handling content acquisition unit 11 may acquire information from the image displayed on the screen of each user terminal UT by converting it into text by character recognition technology, or the voice input / output by each user terminal UT. Information may be acquired by converting the signal into text by voice recognition technology or the like. The terminal handling content acquisition unit 11 acquires text information by converting electronic data into text by applying existing techniques to various data formats. The text information acquired by the terminal handling content acquisition unit 11 is stored in the terminal handling content storage unit 15 or passed to the pairing condition generation unit 21 for cooperation. As an option, the terminal handling content acquisition unit 11 may acquire the screen image of the entire screen or the window for which the text information is acquired, or the path of the document, together with the text information. The terminal handling content acquisition unit 11 can acquire the handling content not only from the user terminal UTX used by the consultant USX but also from the user terminal UT used by a user other than the consultant.

The terminal handling content storage unit 15 has a function of distinguishing and holding the text information handled by the user terminal UT acquired by the terminal handling content acquisition unit 11. The terminal handling content storage unit 15 may hold the acquired text information as it is, or may hold it in a processed form such as the appearance frequency distribution of words included in the text information. As an option, the terminal handling content storage unit 15 may also hold a screen image of the entire screen or window for which text information is acquired, a document path, and the like.

The pairing condition generation unit 21 compares the text information acquired by the terminal handling content acquisition unit 11 and handled by the user terminal UTX when a problem occurs with the text information stored in the terminal handling content storage unit 15. Then, the process of extracting the words corresponding to the trouble information and the peripheral information is performed. More specifically, the pairing condition generation unit 21 divides the text information into words, and for each of the divided words, the consultant himself or another business performer stored in the terminal handling content storage unit 15. The appearance situation in the accumulated text information is examined, and it is determined whether or not it corresponds to "problem information" or "peripheral information". The pairing condition generation unit 21 stores the determination result in the pairing condition holding unit 25.

The pairing condition holding unit 25 holds the vocabulary of trouble information and the vocabulary of peripheral information. As an option, the pairing condition holding unit 25 may hold the text information acquired from the user terminal UTX at the time of trouble, the screen image acquired together with the text information, and the path of the document.

The pairing condition editing unit 22 performs a process for the consultant to display the vocabulary of each of the trouble information and the peripheral information held by the pairing condition holding unit 25. For example, the pairing condition editing unit 22 generates information for displaying the information held by the pairing condition holding unit 25 on the display unit (integrated or external display, etc.) of the user terminal UTX, and the user terminal. Send to UTX. The pairing condition editing unit 22 also performs a process of deleting, changing, or adding the vocabulary of the trouble information and the peripheral information according to the operation of the consultant input via the user terminal UTX. The pairing condition editing unit 22 is optional and may be omitted.

The pairing process execution unit 31 extracts candidates for consultation destination users from users other than the consultation source user according to work experience, based on the trouble information and peripheral information held by the pairing condition holding unit 25. .. More specifically, the pairing process execution unit 31 calculates the following evaluation indexes A and B, respectively, by comparing the trouble information and the peripheral information with the text information accumulated in association with each business operator. Based on the evaluation index A, a person who is determined to have work experience related to a problem is extracted, and then a process of assigning a higher recommendation degree to a person having a larger evaluation index B and the evaluation index A is performed.
Evaluation index A: Amount of work experience possessed by each business operator regarding trouble information Evaluation index B: Amount of business experience possessed by each business operator regarding peripheral information

The pairing result holding unit 45 has a function of holding the consultation destination candidate extracted by the pairing processing execution unit 31 and the degree of recommendation of each. As an option, the pairing result holding unit 45 has, for each consultant candidate, the frequency of appearance of each word in the vocabulary of trouble information and the vocabulary of peripheral information in the accumulated text information, etc. It is also possible to maintain the degree of experience of the trouble and the work situation at the time of the trouble.

The pairing result presentation unit 41 performs a process of causing the consultant to display the data held by the pairing result holding unit 45. For example, the pairing result presentation unit 41 generates information for displaying the pairing result on the display unit (integrated or external display, etc.) of the user terminal UTX of the consulting source user USX, and transmits the information to the user terminal UTX. .. As an option, the pairing result presentation unit 41 displays such that communication (telephone, e-mail, business chat, etc.) with the consultant candidate is started in response to the consultant's selection operation of the consultant candidate. Information may be generated and also transmitted to the user terminal UTX.

The pairing result notification unit 42 ranks within a predetermined threshold value when arranged in descending order of recommendation level among the consultation destination candidates extracted as a result of the pairing process execution by the pairing process execution unit 31. Performs processing to notify the business operator of the occurrence of a problem. For example, the pairing result notification unit 42 determines that the business performer whose recommendation level is within the threshold value is the consultant user, and is extracted as a candidate for the user terminal UT of the consultant user, which is a problem. Notify the occurrence of the problem or information about the consulting source user. As an option, the pairing result notification unit 42 is acquired by the consultant's terminal UTX when a problem occurs, and is held by the pairing condition holding unit 25, the text information, the screen image acquired together with the text information, and the document. Further information may be provided to display the path. Further, as an option, the pairing result notification unit 42 identifies and associates the text information of the consultation destination candidate, which is stored in the terminal handling content storage unit 15, with the trouble information and the peripheral information. You may notify the screen image or the path that was given. Further, as an option, the pairing result notification unit 42 generates display information such that communication (telephone, e-mail, business chat, etc.) with the counselor is started in response to the counseling reception operation by the counselor candidate. In addition, it may be transmitted to the user terminal UT.

(1-2-2) Hardware Configuration FIG. 4 schematically shows a hardware configuration example of the search server 1. As shown in FIG. 4, the search server 1 includes a processor 101, a RAM 102, a program memory 103, a storage device 104, and an input / output interface 105, which are connected to each other via a bus 106. The processor 101 controls the RAM 102, the program memory 103, the storage device 104, and the input / output interface 105, and exchanges signals with them.

The processor 101 includes a general-purpose circuit such as a CPU. The RAM 102 is used by the processor 101 as a working memory. The RAM 102 includes a volatile memory such as SDRAM. The program memory 103 stores a program executed by the processor 101, including an information generation program. The program contains computer executable instructions. For example, a ROM is used as the program memory 103.

The processor 101 expands the program stored in the program memory 103 into the RAM 102, interprets and executes the program. When the information generation program is executed by the processor 101, the terminal handling content acquisition unit 11, the pairing condition generation unit 21, the pairing condition editing unit 22, the pairing processing execution unit 31, and the pairing described above for the search server 1 are executed. The processor 101 can execute the processing functions of the result presentation unit 41 and the pairing result notification unit 42.

The storage device 104 can function as a storage area for the terminal handling content storage unit 15, the pairing condition holding unit 25, and the pairing result holding unit 45 described above. The storage device 104 includes a non-volatile memory such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive). A part of the storage device 104 may be used as the program memory 103.

The input / output interface 105 includes a communication module for communicating with an external device and a plurality of terminals for connecting peripheral devices. The external device is, for example, a user terminal UT. The communication module may include, for example, a wired module and / or a wireless module. Examples of peripherals include displays, keyboards, and mice.

The processor 101 may include a plurality of processors. Further, at least a part of the above processing functions may be realized in various other formats including integrated circuits such as ASIC (Application Specific Integrated Circuit) and FPGA (field-programmable gate array). At least a part of the storage area of the storage device 104 may be provided in a device different from the search server 1.

(2) Operation (2-1) Overview of the entire operation Next, the information processing operation by the search server 1 as the information processing device according to the embodiment configured as described above will be described.

FIG. 5 is a diagram showing an outline of the information processing operation.
In step S1, the search server 1 performs a terminal handling content grasping process. In the process of grasping the contents handled by the terminal, the text information (first text information) handled by the user terminal UTX is used in response to the search request issued by the consultant (first user) when a problem occurs. Including getting. In the process of grasping the terminal handling contents, the acquisition of text information (second text information) as the work experience of the consultant in the consultation source user terminal UTX and the work experience of all user terminals UT except the consultation source user terminal UTX. It may further include the acquisition of text information (third text information).

In step S2, the search server 1 performs a pairing condition generation process. In the pairing condition generation process, the words included in the acquired first text information are combined with the first language group whose appearance frequency is lower than a predetermined threshold value according to the appearance frequency in the second text information. It includes a process of classifying into a second word group whose appearance frequency is equal to or higher than a predetermined threshold. The first group of words corresponds to "problem information" and includes words that are less experienced for the counselor. The second group of words corresponds to "peripheral information". Here, the "appearance frequency" is calculated as the number of words appearing in the text information to be compared divided by the total number of all words included in the text information to be compared. Will be done. In the example of step S2, the number of words included in the acquired first text information appearing in the second text information is calculated, and the number is included in all the second text information. Calculated by dividing by the total number of words.

In step S3, the search server 1 performs pairing processing. The pairing process includes a process of extracting candidates for consultation destination users from users other than the consultation source user and calculating the degree of recommendation for each, considering the frequency of appearance of trouble information and peripheral information as the amount of work experience.

In step S4, the search server 1 outputs the pairing result. The output of the pairing result includes a process for displaying the pairing result to the consulting source user and the consulting destination user.

The above steps S1 to S4 will be described in more detail below. In the following explanation
・ A set of all business performers (including counselors and counselors): K
-A set of records for each business performer k (∈ K): L _k
・ Trouble information (set of vocabulary included in): T
・ Peripheral information (set of vocabulary contained in): B
And.

The search server 1 calculates the appearance frequency of the corresponding word: _{mi, k} _from the appearance frequency distribution of the vocabulary for each word ti included in the trouble information T. After that, the following is calculated as "the amount of work experience possessed by trouble information".

In other words, the degree of coverage of trouble information represents the ratio of words existing in the record of each business operator among the words belonging to the first language group (vocabulary of trouble information). In other words, the degree of handling of trouble information represents a value obtained by dividing the total frequency of words belonging to the first language group appearing in the records of each business operator by the total number of words belonging to the first language group. ..

Further, the search server 1 calculates the appearance frequency n _{j, k} of the corresponding word from the appearance frequency distribution of the vocabulary for each word b _j included in the peripheral information B. Then, the following is calculated as the "holding amount of work experience related to peripheral information".

In other words, the degree of coverage of peripheral information represents the ratio of words existing in the record of each business operator among the words belonging to the second language group (vocabulary of peripheral information). In other words, the degree of handling of peripheral information represents a value obtained by dividing the total frequency of words belonging to the second language group appearing in the records of each business operator by the total number of words belonging to the second language group.

Further, the search server 1 extracts consultation destination candidates from the set K using the "holding amount of business experience related to trouble information", and for each consultation destination candidate k, "holding amount of business experience related to trouble information". And "the amount of work experience related to peripheral information" is used to calculate the following "recommendation degree" r _k and give it to each consultant candidate k.

In the above formula, α, β, γ, and δ reflect which of the evaluation indexes regarding "the amount of work experience related to trouble information" and "the amount of work experience related to peripheral information" reflected in the degree of recommendation. This is a parameter that controls the information, and is specified in advance by, for example, the administrator of the search server 1.

In other words, the degree of recommendation is a value obtained by weighting and adding the degree of coverage of trouble information, the degree of handling of trouble information, the degree of coverage of peripheral information, and the degree of handling of peripheral information for each consultant candidate k. The degree of recommendation is higher as the value of the degree of coverage of trouble information is larger, the degree of handling of trouble information is larger, the degree of coverage of peripheral information is larger, and the degree of handling of peripheral information is larger.

In addition, it is not necessary to use all of the degree of coverage of trouble information, the degree of handling of trouble information, the degree of coverage of peripheral information, and the degree of handling of peripheral information in calculating the degree of recommendation, and one of these. It may be calculated using one. In other words, the above α, β, γ, δ can be a positive value or zero, and at least one of α, β, γ, δ may be non-zero.
The operation of the search server 1 will be described in more detail below.

(2-2) Processing for grasping terminal handling contents FIG. 6 is a diagram showing details of the processing in step S1 shown in FIG.
In step S101, the search server 1 monitors the occurrence of troubles. If it is determined that a problem has occurred in step S101, the process proceeds to step S102. For example, the search server 1 executes subsequent processing triggered by a search request for searching for a consultation destination from any user terminal UT. The search request is transmitted from the user terminal UTX to the search server 1 by, for example, the consulting source user pressing a "consultation button" displayed as a GUI on the display of the user terminal UTX.

In step S102, the terminal handling content acquisition unit 11 acquires the text information handled by the user terminal UTX when a problem occurs. The text information may be acquired only from the screen displayed to the user on the display of the user terminal UTX when the search request is transmitted from the user terminal UTX, or the user terminal including the part not displayed on the screen. It may be obtained from the electronic file active above.

As described above, the terminal handling content acquisition unit 11 can acquire the text information displayed on the screen by using the interface provided independently by the UIA, the MSAA, or the program operating in the user terminal UT. Alternatively, the terminal handling content acquisition unit 11 may convert the image displayed on each terminal screen into text by character recognition technology, or may convert the voice signal input / output by each terminal into text by voice recognition technology or the like. good. The terminal handling content acquisition unit 11 acquires text information by converting it into text by applying existing techniques to various data formats. As an option, the terminal handling content acquisition unit 11 may acquire the screen image of the entire screen or the window for which the text information is acquired, or the path of the document, together with the text information.

FIG. 7 shows an example of text information acquired by the terminal handling content acquisition unit 11. Here, the order content registration process is performed on the user terminal UTX, and the screen DS1 captures the display on the display of the user terminal UTX at that time. The screen DS1 includes text information such as "order details" and "order slip number". Based on this screen display, the text information TI1 is acquired as described above.

Next, in step S103 of FIG. 6, the terminal handling content acquisition unit 11 distinguishes the business performer by associating the acquired text information with the user ID and stores it in the terminal handling content storage unit 15. Textual information may also be associated with date and time information.

In this way, the terminal handling content storage unit 15 accumulates information each time the terminal handling content acquisition unit 11 acquires text information. Alternatively, as a premise for starting the operation by the search server 1, it may be assumed that a certain amount or more of text information about all users is stored in the terminal handling content storage unit 15 in advance regardless of whether or not a trouble has occurred.

Further, here, the terminal handling content storage unit 15 may hold the text information in a processed form such as the appearance frequency distribution of the vocabulary included in the text information. As an option, the terminal handling content storage unit 15 holds the screen image of the entire screen or window of the user terminal UT for which the text information is acquired, and the path of the target document in association with the text information together with the acquisition time. May be good. The data may be distributed and arranged in an area on the data storage device that can be accessed only by each business operator of each user terminal UT, or may be collectively arranged for all business operators on a file server or the like. good. Alternatively, the arrangement method may be changed depending on the type of data, such as arranging text information, screen images, and document paths in a distributed manner and arranging only the appearance frequency distribution of vocabulary collectively.

FIG. 8 shows a first example of data held in the terminal handling content storage unit 15. In the example of FIG. 8, an example is shown in which text information is retained for each business performer (business performer 1, ... business performer k) with different acquisition timings. In this example, the items include "acquisition time", "text information", "screen image", and "path". However, acquisition and retention of acquisition time, screen image and path are optional.

FIG. 9 shows a second example of data held in the terminal handling content storage unit 15. The example of FIG. 9 shows an example in which text information is processed and held in a vocabulary appearance frequency distribution. In this example, the items include "word" and "number of occurrences". For each word (AAA, order details, payment method ...) extracted from the text information for each business operator, the number of appearances (352, 60, 60 ...) in all the data accumulated so far. ) The number is calculated and updated / recorded.

(2-3) Pairing Condition Generation Process FIG. 10 is a diagram showing details of the process of step S2 shown in FIG.
In step S201, the pairing condition generation unit 21 acquires the text information acquired by the terminal handling content acquisition unit 11.

In step S202, the pairing condition generation unit 21 divides the acquired text information into morphemes by morphological analysis. Of the divided morphemes, less important ones such as particles may be removed. Alternatively, morphemes may be integrated to form more complex words by referring to a pre-registered dictionary. The individual information obtained by the division is referred to herein as a word or word. The morphological analysis is an example and may be divided by another method.

In step S203, the pairing condition generation unit 21 examines the appearance status of each obtained word in the text information stored in the terminal handling content storage unit 15, and corresponds to "problem information" and "peripheral information". Determine if you want to. Here, the text information to be compared for each word may be the text information accumulated with respect to the counselor himself or another business performer. The determination of "problem information" and "peripheral information" by the pairing condition generation unit 21 is performed by using, for example, the following method.

(2-3-1) First Example of Process for Determining "Troublesome Information" and "Peripheral Information"
(2-3-1-1) First step For each word obtained in step S202, the number of times that each word appears in the text information accumulated by the counselor himself, which is accumulated in the terminal handling content storage unit 15, is examined. Find the frequency of appearance.
(2-3-1-2) Second step Next, the frequency of appearance of each word obtained in (2-3-1-1) above is compared with a preset threshold value to determine high or low, for example. A word having an appearance frequency equal to or higher than the threshold value is determined to be "peripheral information", and a word having an appearance frequency lower than the threshold value is determined to be "problem information".

FIG. 11 is a diagram illustrating the determination according to the first embodiment. For each word acquired from the counselor's terminal UTX, the word with the highest frequency of appearance is determined as "peripheral information" PW according to the frequency of appearance in the past text information accumulated by the counselor, and the frequency of appearance is high. A low word is determined to be "trouble information" TW.

(2-3-2) Second Example of Process for Determining "Troublesome Information" and "Peripheral Information" (2-3-2-1) First Step
For each word obtained in step S202, the number of appearances in the text information accumulated by the counselor himself / herself accumulated in the terminal handling content storage unit 15 is examined, and the appearance frequency is obtained.
(2-3-2-2) Second step
The frequency of appearance of each word of the counselor himself obtained in (2-3-2-1) above is compared with the threshold value to determine the level.
(2-3-2-3) 3rd step
For each word obtained in step S202, the number of times of appearance in the stored text information is examined for each business performer other than the consultant stored in the terminal handling content storage unit 15, and the frequency of appearance is obtained.
(2-3-2-4) 4th step
The frequency of appearance of each word for each business operator obtained in (2-3-2-3) above is compared with the threshold value to determine the level.
(2-3-2-5) 5th step
Count the number of business performers judged to be "high" and the number of business performers judged to be "low" obtained in (2-3-2-4) above.
(2-3-2-6) 6th step
Based on the results of (2-3-2-2) and (2-3-2-5) above, it is determined whether or not each word corresponds to "problem information" and "peripheral information". The threshold values used in (2-3-2-2) and (2-3-2-4) may be the same or different values.

FIG. 12 is a diagram illustrating the determination according to the second embodiment. For each word acquired from the counselor's terminal UTX, the word with the highest frequency of appearance is "peripheral information" according to the frequency of appearance in the past text information accumulated by the counselor, as in the first embodiment. A word that is determined to be PW and has a low frequency of appearance is determined to be "problem information" TW. However, unlike the first embodiment, words having a low frequency of appearance in the text information of other business performers for all other business performers are excluded from the "peripheral information" PW and the "problem information" TW. In this way, by excluding words that appear infrequently for all other business performers, we search for past response cases and response experiences that are unique only when a problem occurs throughout the past operations of all business performers. Words that are useless above (eg, ID of a new project, etc.) can be excluded.

(2-3-3) Example of determination of threshold value The threshold values used in (2-3-1-2), (2-3-2-2) and (2-3-2-4) above are For example, it can be determined as follows.
[Example 1] A person such as the administrator of the search server 1 specifies in advance as a fixed value.
[Example 2] For the vocabulary in the text information accumulated by the counselor, calculate the statistical value of appearance frequency (mean value, median value, mode value, variance, deviation value, etc.) and determine from the statistical value. ..
[Example 3] For the vocabulary in the accumulated text information of all business practitioners, the statistical values of appearance frequency (average value, median value, mode value, variance, deviation value, etc.) are calculated and determined from the statistical values. do.

(2-3-4) Example of saving the determination result Next, in step S204 of FIG. 10, the pairing condition generation unit 21 stores the determination result in the pairing condition holding unit 25.

The pairing condition holding unit 25 holds the vocabulary of trouble information and the vocabulary of peripheral information. As an option, the pairing condition holding unit 25 may hold the text information acquired at the time of trouble, the screen image acquired together with the text information, and the path of the document.

FIG. 13 shows an example of data held in the pairing condition holding unit 25. In this example, the items include "pairing process ID", "consultant", "problem information", "peripheral information", "text information", "screen image", and "path". The "text information", "screen image", and "path" are information of the same name as the data held in the terminal handling content storage unit 15, and are all optional.

As an option, the information stored in the pairing condition holding unit 25 can be edited by the consultant. As described above, the pairing condition editing unit 22 enables such editing. The pairing condition editing unit 22 holds the pairing condition for the user terminal UTX used by the consultant every time the information held in the pairing condition holding unit 25 is updated or at regular intervals, for example. Information for displaying the trouble information and peripheral information held in the unit 25 is generated and transmitted. When the counselor performs an operation requesting deletion, change, addition, etc. of a word via the user terminal UTX, the request is transmitted to the search server 1, and the pairing condition editing unit 22 responds to the counselor's request. The information stored in the pairing condition holding unit 25 is edited.

(2-4) Pairing process FIG. 14 is a diagram showing details of the process of step S3 shown in FIG. This process is mainly executed by the pairing process execution unit 31. As described above, the pairing process execution unit 31 compares the trouble information and peripheral information held by the pairing condition holding unit 25 with the text information accumulated in association with each business performer.
Evaluation index A: Amount of work experience possessed by each business operator related to trouble information Evaluation index B: Business experience related to peripheral information is calculated, and based on evaluation index A, business related to trouble Persons who are determined to have experience are extracted, and then a higher degree of recommendation is assigned to those who have a larger evaluation index B and evaluation index A.

First, in step S301, the pairing process execution unit 31 reads out the trouble information and peripheral information of the consultant from the pairing condition holding unit 25.

In step S302, the pairing process execution unit 31 extracts a business operator who has a lot of experience in using trouble information as a consultation destination candidate based on the above evaluation index A.

In step S303, the pairing process execution unit 31 assigns a high degree of recommendation to a business operator who knows trouble information and has a lot of experience in peripheral information.

In step S304, the pairing process execution unit 31 saves the pairing result in the pairing result holding unit 45.

The pairing process will be described in more detail below. Similar to the above, in the following description,
Group of business performers: K
Trouble information (set of vocabulary contained in): T
Peripheral information (set of vocabulary contained in): B
Is used.

(2-4-1) First embodiment of pairing processing: Example of processing when text information is held separately at the acquisition timing. It is assumed that the text information is held as different "records" (rows in FIG. 8) due to the difference in acquisition timing. Let L _k be a set of records of each business performer k (∈ K).

In this first embodiment, the pairing process execution unit 31 includes both trouble information and peripheral information for each record, not for the entire cumulative text information of each business performer. To find out. This makes it possible to consider the experience of handling trouble information and peripheral information at the same timing, that is, how much experience of the same business situation as the counselor.

If each record is given a time stamp, the timing at which the text information is acquired may be taken into consideration, such as limiting the records to those within a certain period from the time of the trouble.

(2-4-1-1) First step
The pairing process execution unit 31 has the following (i) and () for each record l (∈ L _k ) of the text information of each business performer k (∈ K) stored in the terminal handling content storage unit 15. ii) is carried out.
(I) The pairing process execution unit 31 acquires the appearance frequencies _{mi, k, l} _of the corresponding word for each word ti included in the trouble information T. Then calculate the following.

(Ii) The pairing process execution unit 31 acquires the appearance frequencies n _{j, k, l} of the corresponding word for each word b _j included in the peripheral information B. Then, calculate the following.

(2-4-1-2) Second step
The pairing process execution unit 31 compares each record l of the text information of each business operator k with the degree of coverage g _{k, l} of the trouble information in the record and its threshold value g ^* to check whether the record l is related to the trouble. Then, the judgment is made as follows.

(2-4-1-3) Third step
The pairing process execution unit 31 implements the following (iii) and (iv) for each business performer k.
(Iii) The following is calculated as the "holding amount of work experience related to trouble information".

(Iv) The following is calculated as the "holding amount of work experience related to peripheral information".

(2-4-1-4) 4th step
The pairing process execution unit 31 determines whether or not each business performer k has work experience regarding troubles.

And "the amount of work experience related to trouble information" is used to determine whether or not it is determined that the person has work experience related to trouble in either or both of the following.

(2-4-1-5) 5th step The pairing process execution unit 31 is a business performer who is determined to have work experience related to a problem in the 4th step of (2-4-1-4) above. The "recommendation degree" r _k is calculated for k.

(2-4-1-5-1) First Example of Recommendation Degree Calculation Method The pairing processing execution unit 31 describes "the amount of work experience related to trouble information" and "peripheral information" for each work performer k. The "recommendation degree" _rk can be calculated as follows by using the "holding amount of work experience".

However, α, β, γ, and δ indicate which of the evaluation indexes related to “the amount of work experience related to trouble information” and “the amount of work experience related to peripheral information” to be reflected in the degree of recommendation. It is a parameter to be controlled, and as described above, it is specified in advance by, for example, the administrator of the search server 1. α, β, γ, δ can take zero or positive values, and at least one can take non-zero values.

(2-4-1-5-2) Second Example of Recommendation Degree Calculation Method The pairing processing execution unit 31 includes each word ti included in the trouble information T and each word b _j included in the peripheral information _B. The following weights are calculated for. This corresponds to IDF (Inverse Document Frequency) when each record l of the accumulated text information of each business operator k is regarded as one document.

The pairing process execution unit 31 further, as "a weighted possession amount of work experience regarding trouble information",

As "weighted holding amount of work experience related to peripheral information"

Is calculated. The "recommendation degree" r _k is calculated as follows for each work performer k determined to have work experience related to the trouble in the above fourth step.

(2-4-2) Second embodiment of pairing processing: An example of processing in which text information is held as a vocabulary appearance frequency distribution Text of each business operator stored in the terminal handling content storage unit 15. It is assumed that the information does not distinguish the difference in acquisition timing, and as shown in FIG. 9, the cumulative number of appearances indicating how many times each word has appeared by the start of processing is retained.

In this case, the pairing process execution unit 31 decides to check to what extent both the trouble information and the peripheral information are included in the entire cumulative text information of each business performer as follows. Become. Therefore, it is not taken into consideration how much each business operator has the experience of handling trouble information and peripheral information at the same timing. On the other hand, as compared with the method of examining individual records, the processing amount of the pairing process can be significantly reduced, and the processing load of the search server 1 can be greatly reduced.

(2-4-2-1) First step
The following (v) and (vi) are carried out for the appearance frequency distribution of the vocabulary of each business performer k (∈ K) accumulated in the terminal handling content storage unit 15.
(V) For each word ti included in the trouble information T, the frequency _{mi and k} _of the corresponding word are acquired from the frequency distribution of the vocabulary. After that, the following is calculated as the "holding amount of work experience related to trouble information".

(Vi) For each word b _j included in the peripheral information B, the appearance frequency n _{j, k} of the corresponding word is acquired from the appearance frequency distribution of the vocabulary. Then, the following is calculated as the "holding amount of work experience related to peripheral information".

(2-4-2-2) Second step
Whether or not each business performer k has work experience related to troubles is determined by using "the amount of work experience related to trouble information" to have work experience related to troubles in either or both of the following. Judgment is made by whether or not it is judged.

(2-4-2-3) Third step
The pairing process execution unit 31 calculates the “recommendation degree” r _k for each work performer k determined to have work experience related to the trouble in the above second step.

(2-4-2-3-1) First Example of Recommendation Degree Calculation Method The pairing processing execution unit 31 describes "the amount of work experience related to trouble information" and "peripheral information" for each work performer k. The "recommendation degree" _rk can be calculated as follows by using the "holding amount of work experience".

( _{2-4-2-3-2) The following weights are applied to each word ti included in the trouble information T and each word b j} _included in the peripheral information B in the second embodiment of the recommendation degree calculation method. calculate. This corresponds to IDF (Inverse Document Frequency) when the accumulated text information of each business operator k is regarded as one document.

(2-4-3) Saving the pairing result The consultant candidate extracted / calculated by the pairing process execution unit 31 as described above and the degree of recommendation thereof are retained in the pairing result in step S304 of FIG. It is stored in the unit 45.

FIG. 15 shows an example of information stored in the pairing result holding unit 45.
As shown in FIG. 15, the pairing result holding unit 45 holds a "consultation candidate" and each "recommendation degree" in association with a "pairing process ID" that identifies each pairing process. Will be done. In the example of FIG. 15, the "consultation candidate" is stored as a user ID, but may be retained by a name, a nickname, or the like.

Further, as an option, as shown in FIG. 15, the pairing result holding unit 45 can also hold "problem information" and "peripheral information" for each consultant candidate. In the example of FIG. 15, when looking at the record of "pairing processing ID = PR0001", "consultation candidate = User0051" is calculated as "recommendation degree = 23.2", and "business experience possession amount" regarding trouble information is calculated. Is "coverage = 1.0" and "handling = 3.8", and the frequency of appearance by vocabulary is "monthly development = 126" and "total of actual results at the end of this month = 103". The "experience holding amount" is "coverage = 1.0" and "handling = 8.2", and the frequency of appearance by vocabulary is saved as "SMART = 418", "project ID = 356", and "ordered project ID = 301". .. Further, as an option, the pairing result holding unit 45 displays the frequency of appearance of each of the "problem information" and "peripheral information" in the accumulated text information, the trouble in the candidate, and the business situation at the time of occurrence. The degree of experience and the like may also be retained.

(2-5) Pairing result output processing FIG. 16 is a diagram showing details of the processing in step S4 shown in FIG.
In step S401, the pairing result presenting unit 41 and the pairing result notification unit 42 read out the pairing result stored in the pairing result holding unit 45, respectively.

In step S402, the pairing result presentation unit 41 generates and outputs presentation information for presenting the pairing result to the counselor. The output presentation information is transmitted to the user terminal UTX used by the consultant via, for example, the network NW. Upon receiving this presentation information, the user terminal UTX generates a corresponding display screen, displays it on a display or the like, and presents it to the consultant. The presented information may include information for displaying the contact information of the consultant candidate on the display screen. As an option, when the consultant's selection operation of the consultant candidate is accepted via the display screen of the user terminal UTX, the consultant's user terminal UTX communicates with the selected consultant candidate (telephone, email, business). (Chat, etc.) may be started. Communication between the counselor and the consultant candidate may be via the search server 1 or may not be via the search server 1.

In step S403, the pairing result notification unit 42 is a business performer (hereinafter, “final candidate”) whose order is within a predetermined threshold when arranged in descending order of recommendation level among the extracted consultant candidates. ”), Generates and outputs notification information for notifying the occurrence of a problem. The output notification information is transmitted to the user terminal UT used by each final candidate, for example, via the network NW. Upon receiving this notification information, the user terminal UT generates a corresponding display screen, displays it on a display or the like, and presents it to each final candidate. As an option, the notification information that is output is the text information that is acquired by the consultant's terminal when a problem occurs and is held by the pairing condition holding unit, the screen image acquired along with it, the document path, etc. It may contain information for display. As an option, the output notification information identifies the information including trouble information and peripheral information from the text information of the final candidate stored in the terminal handling content storage unit 15, and is associated with it. It may include information for displaying a screen image or a path.

Furthermore, as an option, when the consultation reception operation by the final candidate is accepted via the display screen of the user terminal UT, communication with the consultant (telephone, email, business chat, etc.) is started from the user terminal UT of the final candidate. You may do so. Again, the communication between the final candidate and the counselor may be via the search server 1 or may not be via the search server 1.

Note that the above steps S402 and S403 may be executed at arbitrary timings, may be executed simultaneously in parallel, or may be executed sequentially.

As described in detail above, in one embodiment of the present invention, the first aspect is in response to a search request issued by a first user (consulting source user) USX to search for a candidate user from a plurality of users. The first text information handled by the terminal device UTX used by the user of the above is acquired. Then, with respect to the word included in the first text information, the appearance frequency in the second text information acquired from the terminal device used by the first user in the past is calculated. The words included in the first text information are the first language group (problem information) whose appearance frequency is lower than the first threshold value according to the appearance frequency in the second text information, and the appearance frequency is described above. It is classified into a second language group (peripheral information) above the first threshold value. Next, with respect to the words belonging to the first language group, the frequency of appearance in the third text information related to the past work of each of the plurality of users to be searched is determined, and candidate users are extracted according to the frequency of appearance. To. Then, the information about the extracted candidate user is presented to the first user who is the consultation source user. Further, the frequency of appearance of words belonging to the second language group can be used for extracting candidate users. For the extracted candidate users, the degree of recommendation is calculated based on the frequency of appearance of words in the first word group (problem information) and / or the second word group (peripheral information). Candidate users may be presented to the consulting source user together with the calculated recommendation level or in an order according to the calculated recommendation level. Further, the candidate user may also be notified of information about the consulting source user, trouble information, or peripheral information.

(3) Effect As described in detail above, according to one embodiment, the text information (vocabulary) handled in the work of all the work performers is accumulated for each work performer, and a person in charge is in the work. If something goes wrong, for example, when you press the consultation button on the screen, the vocabulary in the business screen is extracted, the vocabulary of the trouble information and peripheral information is determined, and the consultant who has that experience It is searched and presented to the person in charge. More specifically, the judgment of trouble information and peripheral information is based on the vocabulary in the business screen that appears less frequently (unfamiliar with less experience in the past) in the text information accumulated by the consultant himself. It is judged that it is a problem to be consulted, and other vocabulary is judged as peripheral information. In addition, when searching for consultation destinations, among the business practitioners, the accumulated text information has a high degree of coverage and the number of occurrences of troublesome vocabulary (the consultant has a lot of experience with troubles), and the degree of coverage of peripheral information vocabulary. It also searches for and recommends consultants who have a high number of appearances (have the same work experience as the consultant). As a result, tagging related to work experience is not required, and the search is performed in consideration of the background work experience of the counselor and the counselor, so that a more appropriate counselor can be recommended.

In other words, the search system 100 acquires the text information handled by each user terminal UT in the background, records and stores it in association with each business performer (user). The search server 1 uses this accumulated information to grasp the work experience of each work performer, so that the work experience is explicitly / actively registered (input, tagging, etc.) for the purpose of consultant pairing. Is unnecessary. Also, in mail systems, content management systems, and office documents, not only the creator but also the referrer, which is retained as the meta information of the document, is the vocabulary in the document (especially the part displayed on the terminal screen). It will be possible to treat as a holder of work experience related to.

Further, the search server 1 classifies the text information related to the business information of the current consultant into "problem information" and "peripheral information". Select candidates for consultation based on work experience related to trouble information, and assign a higher degree of recommendation to those who have both trouble information and peripheral information. As a result, by setting the determination based on the amount of work experience possessed by each business operator regarding trouble information as an extraction condition, the candidates other than those who have business experience related to trouble information are excluded from the candidates for consultation. As a result, the candidate is more likely to have experience in solving problems. In addition, by determining the degree of recommendation of the candidate for consultation using the amount of work experience of each business operator related to peripheral information, the person who has more business experience related to peripheral information has higher priority as a consultant. Recommended. As a result, consultations will be held between people who have experience in the same work situation.
-The counselor does not need a lot of explanation to get the counselor to understand the business situation at the time of his / her trouble.
-By sharing their own experience as it is, the consultant will have a solution that suits the business situation of the consultant, and there is no need to prepare a new explanation that matches the business situation of the consultant.
Etc. are possible.

Furthermore, the search server 1 checks the possession status of work experience of trouble information and peripheral information not only for the consultant but also for all the business performers. As a result, pairing is realized not only from the perspective of the counselor but also from the perspective of the counselor.

Furthermore, as a result of the pairing process by the search server 1, the consultant candidate assigned a high degree of recommendation is notified that there is a problem that may be supported based on his / her own experience. As a result, the business operator who can be a consultant can easily notice the occurrence of a problem that can be solved based on his / her own experience. Also, you can easily distinguish it from other problems that are difficult to solve in your own experience.

Furthermore, based on the information generated by the search server 1, in addition to the text information handled by the consultation source user terminal UTX, screen images and document paths are acquired, and recorded and stored in association with the text information. When a candidate for consultation receives a consultation or receives a notification, the text information including trouble information and peripheral information, which is a pairing condition, is identified from the accumulated text information and associated with it. Display screen images and paths. Share the identified text information, screen image, and path to the consultant without the candidate having to search for past documents or redisplaying the past matter on the system screen. If possible, the solution cases experienced by the consultant candidates can be easily presented to the consultant.

Furthermore, the counselor does not need to enter a specific text about what he / she is having trouble with, even in situations such as "I cannot specify the problem concretely" or "I do not understand what I do not understand". , It is possible to present a more appropriate consultation destination to the consultant.

(4) Other Embodiments The present invention is not limited to the above embodiment.
For example, the search server 1 has been described as having a terminal handling content storage unit 15, a pairing condition holding unit 25, and a pairing result holding unit 45, but the present invention is not limited thereto. At least one of the terminal handling content storage unit 15, the pairing condition holding unit 25, and the pairing result holding unit 45 may be provided in an external device separate from the search server 1. The external device may be a database server separate from the search server 1, a database provided in the cloud, or any of the user terminals UT. Further, they may be dispersedly provided.

Similarly, the functional units F1 to F4 provided in the search server 1, the terminal handling content acquisition unit 11, the pairing condition generation unit 21, the pairing condition editing unit 22, the pairing processing execution unit 31, the pairing result presentation unit 41 and The pairing result notification unit 42 may be distributed and arranged in a plurality of devices, and the devices may cooperate with each other to perform processing. Further, each of these parts may be realized by using a circuit. The circuit may be a dedicated circuit that realizes a specific function, or may be a general-purpose circuit such as a processor.

Further, it was explained that the search server 1 extracts candidates by determining the work experience of both the trouble information and the peripheral information about the work performer to be searched. However, the work experience may be determined only for either the trouble information or the peripheral information. As a result, the processing load of the search server 1 can be reduced, and the search processing speed can be increased. The counselor may be able to select at any time whether to use the trouble information or the peripheral information for the search. In this case, it is possible to perform a search according to the situation and preference of the counselor.

Further, in the pairing condition generation process described with respect to FIG. 10, the frequency of appearance of each word in the first text information corresponding to the current business situation of the consultant may be taken into consideration. For example, when a specific word frequently appears in the first text information, processing may be performed so that the amount of work experience (degree of coverage and degree of handling) of the word strongly contributes to the degree of recommendation.

Further, the flow of each process described above is not limited to the procedure described above, and the order of some steps may be changed, or some steps may be performed in parallel. .. Further, the series of processes described above need not be continuously executed in time, and each step may be executed at any timing.

The method described above is, for example, a magnetic disk (floppy (registered trademark) disk, hard disk, etc.) or an optical disk (CD-ROM, DVD, MO, etc.) as a program (software means) that can be executed by a computer (computer). , It can be stored in a recording medium (storage medium) such as a semiconductor memory (ROM, RAM, flash memory, etc.), and can also be transmitted and distributed by a communication medium. The program stored on the medium side also includes a setting program for configuring the software means (including not only the execution program but also the table and the data structure) to be executed by the computer in the computer. A computer that realizes the above-mentioned apparatus reads a program recorded on a recording medium, constructs software means by a setting program in some cases, and executes the above-mentioned processing by controlling the operation by the software means. The recording medium referred to in the present specification is not limited to distribution, and includes storage media such as magnetic disks and semiconductor memories provided in devices connected inside a computer or via a network.

In addition, processing such as acquisition and division of text information can be variously modified and carried out without departing from the gist of the present invention.

The present invention is not limited to the above embodiment, and can be variously modified at the implementation stage without departing from the gist thereof. In addition, each embodiment may be carried out in combination as appropriate, in which case the combined effect can be obtained. Further, the above-described embodiment includes various inventions, and various inventions can be extracted by a combination selected from a plurality of disclosed constituent requirements. For example, even if some constituent elements are deleted from all the constituent elements shown in the embodiment, if the problem can be solved and the effect is obtained, the configuration in which the constituent elements are deleted can be extracted as an invention.

1 ... Search server 11 ... Terminal handling content acquisition unit 15 ... Terminal handling content storage unit 21 ... Pairing condition generation unit 22 ... Pairing condition editing unit 25 ... Pairing condition holding unit 31 ... Pairing processing execution unit 35 ... Pairing Condition holding unit 41 ... Pairing result presentation unit 42 ... Pairing result notification unit 45 ... Pairing result holding unit 100 ... Search system

Claims

In response to a search request issued by the first user to search for a candidate user from among a plurality of users, the first text information handled by the terminal device used by the first user is acquired. Information acquisition department and
The first word whose appearance frequency is lower than the first threshold value according to the appearance frequency in the second text information related to the past work of the first user. A condition generation unit that divides the group into a group and a second word group whose appearance frequency is equal to or higher than the first threshold value.
A search processing unit that extracts the candidate users from the plurality of users according to the frequency of appearance of words belonging to the first word group in the third text information related to the past work of each user.
An information processing device including a result output unit that outputs information for presenting information about the candidate user to the first user.
The search processing unit
For the candidate user, the first index relating to the ratio of words existing in the third text information among the words belonging to the first word group, or the word belonging to the first word group is the third. Based on the second index related to the sum of the frequencies appearing in the text information of, the higher the value of the first index or the second index, the higher the recommendation level of each candidate user. Is further calculated,
The result output unit is
As the information about the candidate user, the calculated recommendation degree is output together with the information for identifying the candidate user.
The information processing apparatus according to claim 1.
In the search processing unit, the third index relating to the ratio of words existing in the third text information among the words belonging to the second word group, or the word belonging to the second word group is the first. Based on the fourth index related to the sum of the frequencies appearing in the text information of 3, the recommendation level is set so that the higher the value of the third index or the fourth index, the higher the recommendation level. calculate,
The information processing apparatus according to claim 2.
The condition generation unit excludes words included in the first text information whose frequency of appearance in the third text information related to the past work of each of the plurality of users is lower than the second threshold value. Then, the remaining words included in the first text information are divided into the first word group and the second word group.
The information processing apparatus according to any one of claims 1 to 3.
The information acquisition unit acquires, as the first text information, text information displayed on a display screen associated with the terminal device used by the first user.
The information processing apparatus according to any one of claims 1 to 4.
The result output unit further outputs information for presenting information about the first user, information about the first language group, or information about the second language group to each of the candidate users. The information processing apparatus according to any one of claims 1 to 5.
In response to a search request issued by the first user to search for a candidate user from among a plurality of users, the first text information handled by the terminal device used by the first user is acquired. That and
The first word whose appearance frequency is lower than the first threshold value according to the appearance frequency in the second text information related to the past work of the first user. It is divided into a group and a second word group whose frequency of appearance is equal to or higher than the first threshold value.
Extracting the candidate users from the plurality of users according to the frequency of appearance of words belonging to the first word group in the third text information related to the past work of each user.
An information processing method executed by an information processing apparatus, which comprises outputting information for presenting information about the candidate user to the first user.
A program that causes a computer to execute processing by each part of the apparatus according to any one of claims 1 to 6.