Consultation support control device, method, and program

The consultation support system addresses the inefficiency in remote work by calculating a second evaluation index based on the distribution of first evaluation indices, prioritizing users with relevant experience, thereby improving problem resolution efficiency.

JP7948340B2Active Publication Date: 2026-11-11NIPPON TELEGRAPH & TELEPHONE CORP
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
JP2024569691
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2023-01-10
Publication Date
2026-11-11
Estimated Expiration
2043-01-10

AI Technical Summary

Technical Problem

Existing technologies fail to distinguish between employees with high recommendation degrees who have relevant business experience and those with less relevant experience, leading to inefficient problem resolution in remote work settings.

Method used

A consultation support system calculates a second evaluation index based on the distribution of first evaluation indices for each user's data set, prioritizing users with extensive experience related to the specific problem by selecting data sets with high suitability scores and averaging these scores to determine the most suitable consultant.

Benefits of technology

This approach ensures that employees are paired with consultants who have extensive experience in addressing their specific problems, enhancing problem resolution efficiency and quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007948340000001
    Figure 0007948340000001
  • Figure 0007948340000002
    Figure 0007948340000002
  • Figure 0007948340000003
    Figure 0007948340000003
Patent Text Reader

Abstract

An aspect of the present invention acquires, for a plurality of first users, a plurality of first data items including terms in which experiences of the first users are reflected, and acquires a specific term relating to a problem of a second user. In this situation, for each of the first data items, a first evaluation index indicating the suitability as a consulting destination of the problem is calculated, in accordance with the appearance frequency of the specific term. On the basis of the distribution state of the first evaluation indexes in the plurality of first data items, first data which satisfies a preset priority condition is selected, and on the basis of the first evaluation index corresponding to the selected first data, a second evaluation index is set for each of the first users. On the basis of the set second evaluation index, a user to be a consulting destination of the second user is selected, from among the plurality of first users.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] One aspect of the present invention relates to a consultation support control device, method, and program having a function of pairing, for example, a consulter who has encountered a problem in business with a person in charge who is the consultation partner.

BACKGROUND ART

[0002] In recent years, insufficient communication when employees perform their duties has become a problem. Particularly in remote work, compared with in-person work, natural conversations such as casual chats between employees are less likely to occur, and opportunities to see and hear conversations between other employees are lost. For this reason, even if a work-related problem arises, the employee finds it difficult to casually consult other employees, and it also becomes difficult to grasp who has what kind of knowledge, or who is facing what kind of problem, which may lead to a reduction in work efficiency and quality.

[0003] Accordingly, technologies have been proposed that enable early resolution of problems by pairing a consulter with a consultation partner who has knowledge related to the content of the problem in a remote environment when a problem arises during remote work.

[0004] For example, in Patent Document 1, for a plurality of persons in charge who are candidates for consultation partners, the appearance frequency of terms related to the problem is determined from screen data handled by the persons in charge on their terminals, and the recommendation degree for each screen data is calculated based on this appearance frequency. Then, a technique has been proposed for selecting a person in charge who holds screen data with a relatively high calculated recommendation degree as the consultation partner.

PRIOR ART DOCUMENTS

PATENT DOCUMENTS

[0005]

PATENT DOCUMENT 1

SUMMARY OF THE INVENTION

PROBLEMS TO BE SOLVED BY THE INVENTION

[0006] However, in the technique proposed by Patent Document 1, the recommendation degree of a person in charge is simply calculated as the sum of the recommendation degrees of a plurality of pieces of screen data handled by the person in charge, and a person in charge with a high calculated total value of the above recommendation degrees is selected as a consultation contact. That is, the distribution status of the recommendation degrees possessed by the screen data in the set of screen data handled by the person in charge is not taken into consideration. For this reason, it is difficult to distinguish between a person in charge with a high recommendation degree, that is, a person in charge who holds screen data closer to the business situation of the trouble, and a person in charge with a low recommendation degree, that is, a person in charge who has many pieces of screen data far from the business situation of the trouble. As a result, there is a problem that a high recommendation degree is calculated even for a person in charge with little business experience related to the trouble, and such a person may be selected as the consultation contact.

[0007] The present invention has been made in view of the above circumstances, and aims to provide a technique that enables preferential selection of consultation contacts with rich business experience related to a specific trouble. [Means for Solving the Problems]

[0008] To solve the above problems, one aspect of a consultation support control apparatus or a consultation support control method according to the present invention adopts the following measures. That is, for each of a plurality of first users, a plurality of first data including terms reflecting the experience of the first user is acquired, and a specific term related to the trouble of a second user is acquired. In this state, first, for each of the first data, a first evaluation index representing the suitability as a consultation contact for the trouble is calculated according to the appearance frequency of the specific term. Next, the distribution status of the first evaluation indices in the plurality of first data As an indicator representing this, the average value of the first evaluation index among the first data is calculated, the first data from among the multiple first data is selected in which the first evaluation index is equal to or greater than the average value, and the sum of the first evaluation index of the selected first data is calculated, and the calculated sum is used as the second evaluation index of the first user. is set. Then, based on the set second evaluation index, a user to be the consultation contact for the second user is selected from the plurality of first users.

[0009] According to one aspect of this invention, for each first user, a first data set with a high evaluation index is selected based on the distribution of the first evaluation index in a plurality of first data sets. A second evaluation index is then set for each first user based on the first evaluation index of the selected first data set. Based on this second evaluation index, a user who will be consulted by the second user is selected from among the first users.

[0010] In other words, a first set of data containing many specific terms related to the second user's problems is selected, a second set of evaluation metrics for the first user is set based on the first set of evaluation metrics, and an appropriate user is selected as a contact person based on these first evaluation metrics.

[0011] Therefore, compared to simply summing up all the data from the first user and using that as the evaluation index for the first user, it becomes possible to prioritize selecting the first user, who has more experience in dealing with problems, as a consultant. This makes it possible to efficiently guide the second user, who is the consultant, towards resolving their problems. [Effects of the Invention]

[0012] In other words, according to one aspect of this invention, it is possible to provide a technology that allows for the priority selection of a consultant with extensive experience in the field related to a specific problem. [Brief explanation of the drawing]

[0013] [Figure 1] Figure 1 is a diagram showing a schematic configuration of a consultation support system according to the first embodiment of this invention. [Figure 2] Figure 2 is a block diagram showing an example of the hardware configuration of a consultation support control device according to the first embodiment of this invention. [Figure 3] Figure 3 is a block diagram showing an example of the software configuration of a consultation support control device according to the first embodiment of this invention. [Figure 4]Figure 4 is a flowchart showing an example of the processing procedure and processing content of the consultation support control performed by the control unit of the consultation support control device shown in Figure 3. [Figure 5] Figure 5 is a flowchart showing an example of the processing procedure and content for setting the recommendation level for each person in charge, which is part of the consultation support control processing procedure shown in Figure 4. [Figure 6] Figure 6 shows an example of the screen data selection process in the recommendation level setting process for each person in charge shown in Figure 5. [Figure 7] Figure 7 shows an example of the data calculated during the consultation support control process shown in Figure 4. [Figure 8] Figure 8 is a block diagram showing an example of the software configuration of a consultation support control device according to a second embodiment of the present invention. [Figure 9] Figure 9 is a flowchart showing an example of the processing procedure and content of the recommendation level setting process for each person in charge, which is part of the consultation support control procedure executed by the control unit of the consultation support control device shown in Figure 8. [Figure 10] Figure 10 shows an example of the distribution of recommendation scores by person in charge, which is used to explain the recommendation score setting process by person in charge shown in Figure 9. [Figure 11] Figure 11 shows an example of a recommendation distribution by individual staff member, obtained by normalizing the recommendation distribution by individual staff member shown in Figure 10 with respect to the recommendation distribution of all staff members. [Figure 12] Figure 12 shows an example of data calculated during the consultation support control process shown in Figure 9. [Modes for carrying out the invention]

[0014] Hereinafter, several embodiments of this invention will be described with reference to the drawings.

[0015] [First Embodiment] (Example configuration) (1) System Figure 1 shows an example of the overall configuration of a consultation support system according to the first embodiment of this invention. This system enables the transmission of information data via a network (NW) between multiple user terminals UT1-UTn, each used by an employee in a company, and a consultation support control device (SV). An employee may include a first user (also called the person in charge) who is the recipient of the consultation, and a second user (also called the person seeking consultation) who initiates the consultation. This system may be applied not only to companies, but also to government agencies, research institutions, educational institutions such as schools, etc.

[0016] User terminals UT1 to UTn consist of, for example, personal computers and, in addition to normal information processing and communication functions, are equipped with a function to save screen data displayed on the terminal screen as a terminal log and application programs used in business operations. Using these application programs, it is possible to, for example, conduct online meetings with other user terminals UT1 to UTn or access the consultation support control device SV. Note that smartphones, tablet devices, and other devices can also be used as user terminals UT1 to UTn.

[0017] A network (NW) comprises, for example, a wide-area network centered on the internet, and an access network for accessing this wide-area network. Examples of access networks include wired or wireless public communication networks, wired or wireless LANs (Local Area Networks), and CATV (Cable Television) networks. Alternatively, an internal company network such as a LAN may be used as the network (NW).

[0018] (2) Consultation support control device SV Figures 2 and 3 are block diagrams showing examples of the hardware and software configurations of the Consultation Support Control Device SV, respectively.

[0019] The consultation support control device SV consists of a server computer located, for example, on a LAN, the Web, or the cloud, and includes a control unit 1A that uses a hardware processor such as a Central Processing Unit (CPU). A storage unit having a program storage unit 2 and a data storage unit 3, and a communication interface unit (hereinafter referred to as I / F) 4 are connected to this control unit 1A via a bus 5.

[0020] Furthermore, the consultation support control device SV may be implemented not only by a server computer located on a LAN, the Web, or the cloud, but also by a user terminal such as a personal computer or smartphone used by the user.

[0021] The communication interface unit 4, under the control of the control unit 1A, uses the communication protocol defined by the network NW to send and receive information data between itself and user terminals UT1 to UTn.

[0022] The program storage unit 2 is configured, for example, by combining a non-volatile memory that can be written to and read at any time, such as an HDD (Hard Disk Drive) or SSD (Solid State Drive), as a storage medium, with a non-volatile memory such as ROM (Read Only Memory). In addition to middleware such as an OS (Operating System), it stores application programs necessary to execute various control processes according to one embodiment of this invention.

[0023] The data storage unit 3 is, for example, a combination of non-volatile memory such as an HDD or SSD that can be written to and read at any time as a storage medium, and volatile memory such as RAM (Random Access Memory). The storage area according to the first embodiment includes a person in charge information storage unit 31, a screen data storage unit 32, a problem word storage unit 33, a screen data recommendation level storage unit 34, and a pairing information storage unit 35.

[0024] The personnel information storage unit 31 stores attribute information, including the name and contact information of the person to be consulted, in association with the personnel's identification information (person ID). Alternatively, instead of the personnel's attribute information, terminal IDs associated with user terminals UT1 to UTn used by the person in question may be used, in which case the personnel's attribute information is not necessarily required.

[0025] The screen data storage unit 32 stores screen data handled by the person in charge, such as screen data created, reviewed, or viewed by the person in charge, in association with the person in charge's ID.

[0026] The problem word memory unit 33 stores multiple terms that represent the client's problem as problem words (specific terms), associating them with the client's identification information (client ID) and information that identifies the consultation case (e.g., consultation ID). In addition to terms that directly represent the problem, problem words also include terms that are related to the problem, such as terms that describe the surrounding circumstances when the problem occurred.

[0027] The screen data recommendation score storage unit 34 stores a recommendation score for each screen data handled by the person in charge, which is calculated as a first evaluation index for evaluating the suitability of the person in charge as a contact point for problems, in association with the person in charge ID and the screen data ID.

[0028] The pairing information storage unit 35 stores information representing the pair between a consultation ID, which is information that uniquely defines a consultation case, that is, when and by whom the consultation was conducted, and the person selected as the recipient of that consultation, as pairing information.

[0029] The control unit 1A includes, as a processing function according to the first embodiment of this invention, a person in charge information acquisition processing unit 11, a screen data acquisition processing unit 12, a problem word acquisition processing unit 13, a screen data recommendation degree calculation processing unit 14, a person in charge recommendation degree calculation processing unit 15, a pairing processing unit 16, and a pairing information notification processing unit 17. All of these processing units 11 to 17 are realized by causing the hardware processor of the control unit 1 to execute an application program stored in the program storage unit 2.

[0030] Furthermore, some or all of the above-mentioned processing units 11 to 17 may be implemented using hardware such as LSI (Large Scale Integration) or ASIC (Application Specific Integrated Circuit).

[0031] The personnel information acquisition processing unit 11 acquires attribute information for multiple personnel who may be the point of contact for consultation from the user terminals UT1 to UTn used by those personnel via the communication interface unit 4, and stores the acquired attribute information in the personnel information storage unit 31 in association with the personnel ID. Alternatively, instead of acquiring the attribute information of the personnel, the terminal ID of the user terminal used by the personnel may be acquired.

[0032] The screen data acquisition processing unit 12 acquires multiple screen data that the person in charge has handled, for example, from the past to the present, from user terminals UT1 to UTn used by that person in charge, via the communication I / F unit 4, and stores the acquired multiple screen data in the screen data storage unit 32 in association with the person in charge ID.

[0033] The problem word acquisition processing unit 13 acquires multiple business-related problem words transmitted from user terminals UT1 to UTn used by the consultant via the communication I / F unit 4. The acquired multiple problem words are then stored in the problem word storage unit 33, in association with the consultant ID and consultation ID that identify the consultation case, which are sent along with the problem words.

[0034] In this example, we will explain how to acquire and remember problem-related words, but you can also acquire terms that represent "surrounding information" to describe the work situation (for example, what kind of work was being done when the problem occurred), in addition to specific terms related to the problem.

[0035] The screen data recommendation calculation processing unit 14 calculates the frequency of occurrence of multiple problem words stored in the problem word storage unit 33 for each screen data stored in the screen data storage unit 32. Then, based on the calculated frequency of occurrence, it calculates a first evaluation index for evaluating the suitability of the person as a contact for consultation regarding the problem. In this example, the recommendation score for each screen data is calculated as the first evaluation index. The screen data recommendation calculation processing unit 14 stores the calculated recommendation score for each screen data in the screen data recommendation storage unit 34, associating it with the person in charge ID and the screen data ID.

[0036] The 담당자 Recommendation Score Calculation Processing Unit 15 selects, for each 담당자, screen data whose recommendation score for each screen data satisfies pre-calculated priority conditions, based on the distribution of recommendation scores for each screen data stored in the screen data recommendation score storage unit 34. Then, based on the recommendation scores for each screen data of the selected screen data, it sets a recommendation score for each 담당자, which represents a second evaluation index for assessing their suitability as a consultant for problems. The process of setting this recommendation score for each 담당자 will be described in detail in the operation example.

[0037] The pairing processing unit 16 selects an appropriate person to consult with the person who reported a problem, based on the recommendation level for each person set by the person recommendation level calculation processing unit 15, associates the person ID of the selected person with the consultation ID, and stores this as pairing information in the pairing information storage unit 35.

[0038] The pairing information notification processing unit 17 reads the attribute information of the person in charge and the attribute information of the person in charge from the person in charge information storage unit 31, based on the person in charge ID and the person in charge ID stored in the pairing information storage unit 35. Then, based on the attribute information of the person in charge that has been read, it transmits the pairing information from the communication I / F unit 4 to the user terminals UT1 to UTn of the person in charge.

[0039] (Example of operation) Next, we will explain an example of the operation of the device configured as described above.

[0040] Figure 4 is a flowchart showing an example of the processing procedure and processing content of the consultation support control performed by the control unit 1A of the consultation support control device SV.

[0041] (1) Preparation As preparation before starting consultation support control, the control unit 1A of the consultation support control device SV first, in step S10, under the control of the person in charge information acquisition processing unit 11, acquires attribute information, including the employee's name and contact information, from, for example, the management server of the company to which the system is provided, and stores the acquired attribute information as person in charge information in the person in charge information storage unit 31.

[0042] Furthermore, obtaining contact person information may be done by sending acquisition requests to each of the user terminals UT1 to UTn used by the contact person who may be the point of contact, or it may be done when a registration request is sent from the contact person's user terminal UT1 to UTn.

[0043] Furthermore, it is not always necessary to obtain attribute information of the person in charge as the person in charge information; instead, information representing the correspondence between the person in charge and the user terminal used by that person in charge may be obtained and stored in the person in charge information storage unit 31.

[0044] Furthermore, in step S11, the control unit 1A of the consultation support control device SV, under the control of the screen data acquisition processing unit 12, accesses the user terminals UT1 to UTn of the corresponding personnel based on the personnel information stored in the personnel information storage unit 31, and acquires multiple screen data that the personnel have handled over a certain period from the past to the present from the user terminals UT1 to UTn. The acquired multiple screen data are then stored in the screen data storage unit 32, associated with the personnel ID and screen data ID.

[0045] Furthermore, the screen data may be configured so that only the text information contained in each screen data is acquired. Also, the process of acquiring the above screen data may be performed only once when the system starts operation, or it may be performed periodically at predetermined intervals during operation, or whenever an employee displays or operates a screen (window) in the course of their work.

[0046] (2) Calculation of recommendation scores for each screen data based on problem keywords When a user encounters a problem while working remotely, they send a problem-related word to the consultation support control device SV from their user terminal UT1-UTn.

[0047] In response, the control unit 1A of the consultation support control device SV, under the control of the problem word acquisition processing unit 13, receives the problem word via the communication I / F unit 4 in step S12, associates the received problem word with the consultant ID, and temporarily stores it in the problem word storage unit 33.

[0048] When the above-mentioned problem word is received, the control unit 1A of the consultation support control device SV, under the control of the screen data recommendation calculation processing unit 14, first reads each screen data sequentially from the screen data storage unit 32 in step S13. Then, for each screen data read, it determines the frequency of occurrence of the above-mentioned problem word and calculates the recommendation level based on this frequency.

[0049] The frequency of occurrence of the above-mentioned problem words is calculated, for example, by decomposing the text information of the screen data using morphological analysis to extract terms or strings corresponding to the above-mentioned problem words, and then counting the extracted terms or strings. Furthermore, as a method for calculating the recommendation score, for example, a method in which the frequency of occurrence is used directly as the recommendation score may be used, or a method in which the value obtained by multiplying the frequency of occurrence by a predetermined coefficient or a value obtained by determining the frequency of occurrence using multiple thresholds may be used, or any other arbitrary method may be used.

[0050] This embodiment reflects the extent to which multiple problem words are simultaneously included in the same screen data in the recommendation score for each person in charge. For example, as will be described later, when the recommendation score calculated for each problem word is summed up to determine the recommendation score for that screen data, if there are two problem words, A and B, the recommendation score must satisfy the condition that "the recommendation score for screen data containing only problem word A is lower than the recommendation score for screen data containing both problem words A and B." A possible method for calculating the recommendation score that satisfies this condition is to represent whether the problem word appeared or not as 1 or 0, rather than using the frequency of occurrence of the problem word itself.

[0051] Next, in step S14, the screen data recommendation calculation processing unit 14 sums up the recommendation scores of the problem words calculated above for each screen data, and sets this sum of recommendation scores of problem words as the recommendation score for that screen data. Then, the calculated recommendation scores for each screen data are associated with the screen data ID and the ID of the person in charge who obtained it, and stored in the screen data recommendation storage unit 34.

[0052] Figure 7 shows an example of the screen data recommendation calculation process described above. In this example, screen data A-1, A-2, B-1, B-2, and B-3 are obtained from staff members A and B, and a recommendation score W is calculated for each of these screen data for each problem word S1 and S2. s1 ,W s2 And these recommendation ratings W s1 ,W s2 The recommendation score W for each screen data, which is calculated by summing the values ​​within the screen data. s1+W s2 This shows an example of the calculation result.

[0053] Specifically, indicators such as "tf·idf" and "BM25" can be applied to determine the recommendation level based on screen data.

[0054] (3) Setting recommendation levels by person in charge In step S15, the control unit 1A of the consultation support control device SV sets the recommendation level for each person in charge under the control of the person in charge recommendation level calculation processing unit 15 as follows. Figure 5 is a flowchart showing an example of the processing procedure and content of the recommendation level setting process for each person in charge, which is executed by the person in charge recommendation level calculation processing unit 15.

[0055] The 담당자 Recommendation Score Calculation Processing Unit 15 focuses on the distribution of recommendation scores in each screen data and first selects screen data with a recommendation score greater than "0" in step S151. The denominator for this selection is the screen data held by all 담당자. Next, in step S152, the 담당자 Recommendation Score Calculation Processing Unit 15 calculates the average recommendation score for the selected set of screen data.

[0056] Next, in step S153, the 담당자 Recommendation Score Calculation Processing Unit 15 selects any screen data from the above screen data set, and in step S154, it determines whether the recommendation score of the screen data is higher or lower than the above average value. If the result of this determination is that the recommendation score of the screen data is higher than the above average value, in step S155, the 담당자 Recommendation Score Calculation Processing Unit 15 selects the screen data as the target data to be used in calculating the recommendation score of the 담당자, and adds its recommendation score to the recommendation score of the 담당자 from whom the screen data was obtained.

[0057] On the other hand, if the recommendation score of the screen data is below the average value mentioned above, the person in charge recommendation score calculation processing unit 15, in step S157, will not include the recommendation score of the corresponding screen data in the calculation of the person in charge recommendation score, but will instead select the next screen data from the set of screen data and perform a similar comparison process in step S154.

[0058] Further, after the addition processing in step S155, the person-in-charge recommendation degree calculation processing unit 15 determines in step S156 whether or not the selection of all screen data in the screen data set has been completed. As a result of this determination, if unselected screen data remains, the person-in-charge recommendation degree calculation processing unit 15 selects the unselected screen data in step S157, and similarly performs comparison processing in step S154.

[0059] In contrast, when the selection of all screen data in the screen data set is completed, the person-in-charge recommendation degree calculation processing unit 15 proceeds to step S158. Then, the final recommendation degree calculated in step S155 described above is output to the pairing processing unit 16 together with the person-in-charge ID as the recommendation degree of the relevant person in charge. In this way, a recommendation degree is set for each person in charge.

[0060] Figure 6 is a diagram for explaining the above-described processing for setting the recommendation degree for each person in charge, and shows an example of the distribution of the recommendation degree for each screen data for each of persons A and B in charge. In this example, a larger number of screen data exceeding the average recommendation degree per screen data are selected for person A in charge than for person B in charge. For this reason, the recommendation degree of person A in charge is set to a higher value than that of person B in charge.

[0061] That is, since person A in charge handles a large number of screen data containing many of the consultant's trouble keywords, a high recommendation degree is set for person A in charge. In contrast, regarding person B in charge, although there are many pieces of screen data in which the trouble keywords input by the consultant appear, there are few pieces of screen data with a high recommendation degree, i.e., screen data in which a plurality of trouble keywords appear at the same time. By setting the recommendation degree lower than that of person A in charge, the recommendation degree is also lowered in order to increase the recommendation degree of person A in charge, who is determined to have more work experience related to the troubles.

[0062] Figure 7 shows an example of the recommendation degree W set for the above persons A and B in charge A W B . In this example, first, for person A in charge, the recommendation degree W for that person in charge AThe recommendation score W is for each problem word S1 and S2 included in screen data A-1. s1,A-1 +W s2,A-1 Therefore, as an example, it is calculated as "40". On the other hand, for person in charge B, the recommendation score for that person in charge W B This is the recommendation score W based on the problem word S1 in screen data B-1. s1,B-1 This is the only result. Therefore, as an example, it is calculated as "25".

[0063] (4) Pairing and notification of pairing information In step S16, the control unit 1A of the consultation support control device SV, under the control of the pairing processing unit 16, selects the person with the highest recommendation score for each person, based on the recommendation score for each person output from the person recommendation score calculation processing unit 15, as the person to consult about the problem. For example, in the example in Figure 7, person A is selected as the person to consult about the problem. The pairing processing unit 16 then associates the ID of the selected person with the consultant ID and stores this information in the pairing information storage unit 35. In addition to selecting the person with the highest recommendation score for each person, the system may also select a predetermined number of people in descending order of their recommendation scores as the person to consult.

[0064] In step S17, the control unit 1A of the consultation support control device SV, under the control of the pairing information notification processing unit 17, reads the attribute information of the person in charge and the attribute information of the person in charge from the person in charge information storage unit 31, based on the person in charge ID and the person in charge ID included in the pairing information stored in the pairing information storage unit 35. The pairing information notification processing unit 17 then includes the read person in charge attribute information in the pairing information and transmits it from the communication I / F unit 4 to the user terminals UT1 to UTn of the person in charge. Note that the attribute information of the person in charge does not necessarily have to be transmitted; for example, the person in charge ID or the ID of the user terminal used by the person in charge may be transmitted instead.

[0065] Therefore, from now on, the person seeking advice will be able to access the contact person's user terminal from their own user terminal based on the attribute information of the contact person that has been notified to them, and exchange information to discuss their problems.

[0066] (Effects / Actions) As described above, in the first embodiment, first, each person in charge calculates a recommendation score for each screen data based on the frequency of occurrence of problem words for the multiple screen data they have handled. Next, the person in charge recommendation score calculation processing unit 15 selects the screen data whose recommendation score exceeds the average value and calculates the recommendation score for each person in charge by adding up the recommendation scores for each person in charge. Then, the person in charge with the highest recommendation score is selected as the person to consult regarding the problem, and the result is notified to the person seeking advice.

[0067] Therefore, the more screen data containing multiple problem keywords from the user is handled, the higher the recommendation score will be. This makes it possible to pair the user with a user who has extensive experience in addressing their specific problem. Consequently, the user is more likely to contact a user with extensive experience in addressing their problem, thereby enabling them to resolve their problem efficiently and with a high probability.

[0068] [Second Embodiment] In the second embodiment of this invention, first, for each person in charge, the sum of the recommendation scores for each screen data, excluding screen data with a recommendation score of "0", is calculated and this value is used as the base value of the person in charge's recommendation score. Then, for each person in charge, the above base value of the person in charge's recommendation score is corrected based on a weight that reflects the ratio of the base value of the person in charge's recommendation score to the sum of the base values ​​of the recommendation scores of all people in charge, and the corrected value is used as the recommendation score for each person in charge.

[0069] (Example configuration) Figure 8 is a block diagram showing the software configuration of the consultation support control device SV according to the second embodiment of the present invention. In Figure 8, the same reference numerals are used for parts identical to those in Figure 3, and detailed explanations are omitted. Furthermore, the hardware configuration of the consultation support control device SV is the same as that shown in Figure 2, and therefore is not shown.

[0070] The control unit 1B of the consultation support control device SV is newly equipped with a recommendation base value calculation processing unit 21 and a recommendation level correction processing unit 22 as processing functions according to the second embodiment. These processing units 21 and 22 are also realized by causing the control unit 1B to execute an application program stored in the program storage unit 2.

[0071] The recommendation score base value calculation processing unit 21 calculates a base value for each recommendation score by summing the recommendation scores of each screen data handled by each person in charge.

[0072] The 담당자-specific recommendation score correction processing unit 22 first calculates the number of screen data for each 담당자, excluding screen data with a recommendation score of "0", and also calculates the total number of screen data with a recommendation score greater than "0". Then, it calculates the ratio of the number of screen data for each 담당자 to the total number of screen data, and normalizes the base value of each 담당자's recommendation score based on the calculated ratio of the number of screen data.

[0073] Furthermore, the individual recommendation score correction processing unit 22 calculates the ratio between the normalized base value of each individual's recommendation score and the total recommendation score obtained by summing the base values ​​of each individual's recommendation score before normalization for all individuals. Based on the calculated ratio of recommendation scores, the individual recommendation score is corrected by normalizing the base value of each individual's recommendation score before normalization.

[0074] (Example of operation) Next, we will explain the consultation support control operation using the consultation support control device SV configured as described above. Note that the process from acquiring staff information to calculating the recommendation score for each screen data is the same as in Figure 4, so we will omit that explanation.

[0075] Figure 9 is a flowchart showing an example of the processing procedure and content of the calculation process of the base recommendation score for each person in charge and the correction process of the base recommendation score, which are performed by the control unit 1B of the consultation support control device SV.

[0076] The control unit B of the consultation support control device SV first reads out the recommendation score for each screen data from the screen data recommendation score storage unit 34 one by one under the control of the recommendation score base value calculation processing unit 21 in step S250 and calculates the base value of the recommendation score for each person in charge. Then, it inputs the calculated base value of the recommendation score for each person in charge into the person in charge recommendation score correction processing unit 22.

[0077] The control unit 1B of the consultation support control device SV then performs the following process to correct the recommendation level for each person in charge, under the control of the person in charge recommendation level correction processing unit 22.

[0078] In other words, the individual employee recommendation correction processing unit 22 first calculates the total value of the base recommendation scores for all employees in step S251. The individual employee recommendation correction processing unit 22 then selects screen data from the screen data of each employee, excluding screen data where the recommendation score is "0". In this example, the case of selecting screen data excluding screen data where the base recommendation score is "0" is explained, but it is also possible to set a threshold greater than "0" arbitrarily and select screen data where the base recommendation score exceeds this threshold.

[0079] The 담당자-specific recommendation score correction processing unit 22 then calculates the number of selected screen data for each 담당자 in step S253, and also calculates the total number (sum) of selected screen data for all 담당자. The 담당자-specific recommendation score correction processing unit 22 then calculates a recommendation score for each 담당자, normalized by the total number of screen data for all 담당자, relative to the base recommendation score.

[0080] For example, if we consider the set of screen data excluding screen data where the base recommendation value is "0", what would be the base recommendation values ​​for staff members A and B? A ,W BAnd the number of screen data for person in charge A and B is L A ,L B The number of screen data for all staff members is L All Let's assume this definition applies. Under this definition, the above recommended base value W A ,W B and screen data count L A ,L B , in contrast to the total number of screen data L All When normalized, W A '=W A ×L All / L A W B '=W B ×L All / L B As shown above, the recommendation score W for each person in charge is normalized based on the ratio of the number of screen data points. A ′,W B ′ can be obtained.

[0081] The individual recommendation score correction processing unit 22 then, in step S254, selects any individual, and in step S255, calculates the ratio of the normalized recommendation score of each individual based on the ratio of the number of screen data items to the overall recommendation score of all individuals. Then, in step S256, the individual recommendation score correction processing unit 22 calculates the corrected recommendation score for each individual by multiplying the calculated ratio of recommendation scores by the base value of the recommendation score of the individuals before normalization.

[0082] For example, if person in charge A is selected, the person in charge recommendation correction processing unit 22 calculates the normalized recommendation score W for person in charge A. A ' and the overall recommendation score of staff members A and B W All Based on the ratio, the base recommendation value W before normalization A of W A ×W A ' / W All Correct it as shown.

[0083] Similarly, if person in charge B is selected, the person in charge recommendation correction processing unit 22 calculates the normalized recommendation score W for person in charge B. B ' and the overall recommendation score of staff members A and B W All Based on the ratio, the base recommendation value W before normalization B of W B ×W B ' / W All Correct it as shown.

[0084] After performing the correction calculation in step S256, the individual employee recommendation score correction processing unit 22 determines in step S257 whether the selection of all employees has been completed. If, as a result of this determination, there are still unselected employees, the individual employee recommendation score correction processing unit 22 selects the unselected employees in step S258, and for these employees, in steps S255 and S256, it performs the process of calculating the ratio of the normalized individual employee recommendation score to the overall recommendation score of all employees, and the process of correcting the base recommendation score of the employees before normalization based on the calculated ratio of recommendation scores.

[0085] In response, once the selection of all personnel has been completed, the personnel-specific recommendation score correction processing unit 22 proceeds to step S259. Then, it outputs the final personnel-specific recommendation score calculated in step S256, along with the personnel ID, to the pairing processing unit 16. Thus, a corrected recommendation score is set for each personnel.

[0086] Figure 10 shows an example of the recommendation score distribution for personnel A and B. In this example, personnel A has the same recommendation score as personnel B with fewer screen data. Figure 11 shows the normalized recommendation score W for each personnel A and B. A ′,W B ' and the recommendation level of all staff members W All This is an example of the calculation result of the ratio.

[0087] Figure 12 shows the corrected recommendation score W assigned to personnel A and B, respectively. A ×W A ' / WAll And, W B ×W B ' / W All Here is an example. In this example, for person in charge A, the recommendation score for that person in charge is W. A This represents the recommendation score W for each problem word S1 and S2 included in screen data A-1. s1,A-1 +W s2,A-1 Therefore, the adjusted recommendation score is calculated to be "80". On the other hand, for person in charge B, the individual recommendation score W B The ratio of the number of screen data points L All / L B Recommendation score W normalized by B ' and the overall recommendation level of the person in charge W All Recommendation score W adjusted by the ratio of B ×W B ' / W All Therefore, the calculation is 80 / 3.

[0088] The pairing processing unit 16 selects the person with the highest corrected recommendation score for each person, based on the corrected recommendation score output from the person-specific recommendation score correction processing unit 22, as the person to consult with regarding the problem. For example, in the example shown in Figure 12, person A is selected. The pairing processing unit 16 then associates the ID of the selected person with the consultant ID and stores this information in the pairing information storage unit 35. In this example as well, in addition to selecting the person with the highest recommendation score for each person, a predetermined number of people may be selected as the person to consult with, for example, in descending order of their recommendation scores.

[0089] Finally, the pairing information notification processing unit 17 reads the attribute information of the person in charge and the attribute information of the person in charge from the person in charge information storage unit 31, based on the person in charge ID and the person in charge ID included in the pairing information stored in the pairing information storage unit 35. Then, it transmits the read attribute information of the person in charge, along with the pairing information, from the communication I / F unit 4 to the user terminals UT1 to UTn of the person in charge.

[0090] Therefore, from now on, the person seeking advice will be able to access the contact person's user terminal from their own user terminal based on the attribute information of the contact person that has been notified to them, and exchange information to discuss their problems.

[0091] (Effects / Actions) As detailed above, in the second embodiment, for each person in charge, the sum of the recommendation scores for each screen data, excluding screen data with a recommendation score of "0", is calculated and this value is used as the base value of the person in charge's recommendation score. For each person in charge, the above base value of the person in charge's recommendation score is corrected based on a weight that reflects the ratio of the base value of the person in charge's recommendation score to the sum of the base values ​​of the recommendation scores of all persons in charge, and the corrected value is used as the recommendation score for each person in charge.

[0092] Therefore, similar to the first embodiment described above, in the second embodiment as well, the more screen data containing multiple problem words from the user is handled, the higher the recommendation score will be set. This makes it possible to pair the user with a user who has extensive experience in dealing with the above-mentioned problems. As a result, the user is more likely to be able to contact a user who has extensive experience in dealing with their problems, thereby enabling them to resolve their problems efficiently with a high probability.

[0093] [Other embodiments] (1) In the embodiments described above, the invention was explained using as an example how it can be applied to businesses such as companies. However, it can also be applied to educational institutions such as schools and cram schools, as well as to workshops and exhibitions, where students or participants can choose someone to consult with about their problems from among other students or participants.

[0094] (2) In addition, the types of the first and second evaluation indicators, the installation location of the consultation support control device SV, the functional configuration, the procedures and content of the processing performed by each function, the method for calculating the recommendation level of the screen data, etc., can be modified in various ways without departing from the spirit of this invention.

[0095] (3) In each of the above embodiments, the case in which the person in charge information acquisition processing unit 11, screen data acquisition processing unit 12, problem word acquisition processing unit 13, screen data recommendation degree calculation processing unit 14, person in charge recommendation degree calculation processing unit 15, pairing processing unit 16, pairing information notification processing unit 17, recommendation degree base value calculation processing unit 21, and person in charge recommendation degree correction processing unit 22 are arranged on a consultation support control device SV consisting of a server computer has been described as an example. However, the above processing units 11 to 17, 21, and 22 may also be arranged on user terminals UT1 to UTn, or they may be configured to be distributed across multiple server computers or user terminals.

[0096] (4) In addition, at least one of the personnel information storage unit 31, screen data storage unit 32, problem word storage unit 33, screen data recommendation level storage unit 34, and pairing information storage unit 35 may be located on a server computer other than the consultation support control device SV, or on a user terminal, etc.

[0097] Although embodiments of this invention have been described in detail above, the above description is merely illustrative in all respects. It goes without saying that various improvements and modifications can be made without departing from the scope of this invention. In other words, when implementing this invention, specific configurations may be adopted as appropriate depending on the embodiment.

[0098] In short, this invention is not limited to the embodiments described above, and the components can be modified and implemented in practice without departing from the gist of the invention. Furthermore, various inventions can be formed by appropriately combining the multiple components disclosed in each embodiment. For example, some components may be deleted from all the components shown in each embodiment. Moreover, components from different embodiments may be appropriately combined. [Explanation of Symbols]

[0099] SV... Consultation and support control device UT1~UTn…User terminals NW...Network 1A, 1B... Control Units 2…Program memory 3…Data storage unit 4…Communication I / F section 5... Bus 11…Handling Process for Acquiring Personnel Information 12...Screen data acquisition processing unit 13... Problem-related word acquisition processing unit 14…Screen data recommendation calculation processing unit 15… Calculation and processing unit for employee recommendation score 16…Pairing Processing Unit 17…Pairing Information Notification Processing Unit 21…Recommendation Score Base Value Calculation Processing Unit 22…Recommendation score correction processing unit by person in charge 31... Personnel Information Storage Unit 32...Screen data storage unit 33...Trouble Word Memory Department 34…Screen data recommendation memory unit 35...Pairing information storage unit

Claims

1. A first processing unit that acquires, for each of several first users, several first data sets including terms that reflect the experience of the said first user, A second processing unit that acquires specific terms related to the second user's problem, A third processing unit calculates a first evaluation index representing the suitability of a company as a contact point for the aforementioned problem, based on the frequency of occurrence of the aforementioned specific term in each of the first data sets, A fourth processing unit that, as an indicator representing the distribution of the first evaluation indicator among a plurality of first data, calculates the average value of the first evaluation indicator among the first data, selects first data from the plurality of first data in which the first evaluation indicator is equal to or greater than the average value, further calculates the sum of the first evaluation indicators of the selected first data, and sets the calculated sum as the second evaluation indicator for the first user. A fifth processing unit selects a user from among the multiple first users to consult with the second user based on the second evaluation indicator. A consultation support control device equipped with the following features.

2. A first processing unit that acquires, for each of several first users, several first data sets including terms that reflect the experience of the said first user, A second processing unit that acquires specific terms related to the second user's problem, A third processing unit calculates a first evaluation index representing the suitability of a company as a contact point for the aforementioned problem, based on the frequency of occurrence of the aforementioned specific term in each of the first data sets, A fourth processing unit selects the first data that satisfies pre-set priority conditions based on the distribution of the first evaluation index in a plurality of the first data, and sets a second evaluation index for each of the first users based on the first evaluation index corresponding to the selected first data, A fifth processing unit selects a user from among the multiple first users to consult with the second user based on the second evaluation indicator. Equipped with, The fourth processing unit is, A base value calculation processing unit calculates a base value for the second evaluation index corresponding to the first user for each of the first users, based on the first evaluation index corresponding to the first data, A correction processing unit sets the second evaluation index for the first user by weighting and correcting the base value of the second evaluation index for each first user based on the ratio of the base value of the second evaluation index for each first user to the total value of the second evaluation index obtained by summing the base values ​​for all first users. A consultation support control device equipped with the following features.

3. The correction processing unit, A normalization processing unit, for each of the first users, selects first data from a plurality of first data where the first evaluation index exceeds a preset threshold, and normalizes the base value based on the ratio of the number of selected first data to the total number of first data for all first users, A processing unit that corrects the unnormalized base value based on the ratio of the normalized base value of the first user to the sum of the unnormalized base values ​​of all the first users. A consultation support control device according to claim 2, comprising:

4. A consultation support control method executed by an information processing device, A process for obtaining multiple first data sets for each of multiple first users, including terms that reflect the experience of the said first user, The process of obtaining specific terms related to the second user's problem, For each of the first data mentioned above, a process is provided to calculate a first evaluation index representing the suitability of the service provider as a source for consultation regarding the aforementioned problems, according to the frequency of occurrence of the specific term. The process involves calculating the average value of the first evaluation index among the first data as an indicator representing the distribution of the first evaluation index among a plurality of the first data, selecting a first data from the plurality of the first data in which the first evaluation index is equal to or greater than the average value, further calculating the sum of the first evaluation index of the selected first data, and setting the calculated sum as the second evaluation index for the first user, Based on the second evaluation indicator, the process of selecting a user from among the multiple first users to consult with the second user, A consultation support control method comprising the following:

5. A consultation support control method executed by an information processing device, A process for obtaining multiple first data sets for each of multiple first users, including terms that reflect the experience of the said first user, The process of obtaining specific terms related to the second user's problem, For each of the first data mentioned above, a process is provided to calculate a first evaluation index representing the suitability of the service provider as a source for consultation regarding the aforementioned problems, according to the frequency of occurrence of the specific term. A process of selecting first data that satisfies pre-set priority conditions based on the distribution of the first evaluation indicator in a plurality of first data, and setting a second evaluation indicator for each of the first users based on the first evaluation indicator corresponding to the selected first data, Based on the second evaluation indicator, the process of selecting a user from among the multiple first users to consult with the second user, Equipped with, The process for setting the second evaluation indicator is as follows: For each of the first users, the process of calculating the base value of the second evaluation index corresponding to the first user based on the first evaluation index corresponding to the first data, The process of setting the second evaluation index for the first user by weighting and correcting the base value of the second evaluation index for each first user based on the ratio of the base value of the second evaluation index for each first user to the total value of the second evaluation index obtained by summing the base values ​​for all first users, and A consultation support control method comprising the following:

6. A program that causes a processor in the consultation support control device to perform processing performed by the first to fifth processing units in the consultation support control device according to any one of claims 1 to 3.

Citation Information

Patent Citations

  • Expert information retrieval device, expert information retrieval method and program

    JP2008234550A

  • Expert search apparatus, expert search method, and expert search program

    JP2016045620A

  • Expert website searching system using internet and method thereof

    KR1020110056602A

  • Methods and systems for retrieval of experts based on user customizable search and ranking parameters

    US20140181098A1

  • Information processing device, information processing method, and program

    WO2022091281A1