Information processing device and method

Abstract

An information processing device according to an embodiment includes a conversion unit that, on the basis of information pertaining to the speaker of a message sent between a plurality of personnel and information pertaining to the destination of the sent message, converts the message sent to each of the plurality of personnel into information in which an interaction relationship between the plurality of personnel is structured.

Description

Information processing device and method

[0001] FIELD Embodiments of the present invention relate to an information processing apparatus and method.

[0002] A company's operations are made up of elements such as employees, facilities, and business processes. Operations are designed to suit the business type, industry, and business model, and are improved daily. Employees are an organic function that plays a vital role in operations, providing flexible organizational support for uncertain and complex operations.

[0003] The performance of an organization has a significant impact on the stability of operations. The form that an organization can take varies depending on the robustness, creativity, or urgency required for this work, but in any case, the key is for employees to have roles and work together.

[0004] Hereafter, we will refer to a "team" as "a group of two or more people who work together or cooperate to achieve a shared goal or obtain value while dividing up roles," and the people (personnel) who belong to an organization as "members." An organization functions as a collection of multiple teams, and it is important to properly understand the formation status of these teams in accordance with the business situation, and to design and improve their operations.

[0005] Due to the decline in the working population, it is becoming increasingly common for a single member to belong to multiple teams and be involved in the work of each team. Because it is believed that members' attitudes and behaviors change depending on the situation of the work or the role they are assigned, there is a need for technology that can more objectively analyze the team formation situation based on information on the actual work situation.

[0006] Non-Patent Document 1 discloses analyzing how an organization actually functions through organizational network analysis. Non-Patent Document 2 discloses a method for more effectively implementing measures such as organizational restructuring, interdepartmental collaboration, onboarding of new employees, and early detection of employee turnover risk by visualizing relationships within an organization. Non-Patent Document 3 discloses an attempt to build an intra-company network using common business cards.

[0007] Non-Patent Document 4 discloses that the amount of communication and actions within a team are measured using business card-type sensor nodes, and an organizational network is constructed based on the communication.

[0008] Non-Patent Document 5 discloses a method for analyzing communication trends and relationships with groups by creating a graph structure of the spread and convergence of statements based on quotations, mention information, and contextual information about statements made within a group chat, and then using information on the in-degree and out-degree of the graph structure.

[0009] Complete Coherence, organizational network analysis solution <https: / / complete-coherence.com / complete-organisational-network-analysis-ona / > Link Arc <https: / / www.coacha.com / info / news / 20200914.html> The Potential of Organizational Network Analysis Using Business Card Data - A Case Study of SansanLabs' Business Panel Analysis <http: / / www.orsj.or.jp / archive2 / or64-11 / or64_11_655.pdf> Business Microscope <http: / / www.jfma.or.jp / award / 05 / pdf / paneldata07.pdf> Hiroki Saito, and Kazutaka Tanimori. "Evaluation of Productivity of Group Activity Based on Structural Analysis of Chat Communications." Transactions of the Information Processing Society of Japan 63.2 (2022): 694-703.

[0010] Communication between members of a team involves interaction relationships between members regarding (1) the destinations of members between messages and within messages, (2) reactions to messages, and (3) relationships between messages.

[0011] On the other hand, the method disclosed in Non-Patent Document 4 above only deals with the relationship of face-to-face actions between members using a business card sensor, and is unable to handle the interactive relationships between the destinations of members in messages, reactions to messages, and relationships between messages, and is therefore unable to analyze these structural features. Furthermore, the method disclosed in Non-Patent Document 5 above creates a graph structure for the spread and convergence of statements from quotations, mention information, and contextual information about the content of statements made in a group chat, but is unable to handle replies or reactions from other members to messages.

[0012] This invention has been made in light of the above circumstances, and its purpose is to provide an information processing device and method that can generate information in which interaction relationships based on messages between members are structured.

[0013] An information processing device according to one embodiment of the present invention includes a conversion unit that converts messages sent between each of a plurality of personnel into information in which the interaction relationships between the plurality of personnel are structured, based on information about the sender of the message sent between the plurality of personnel and information about the recipient of the message sent.

[0014] An information processing method according to one embodiment of the present invention is a method performed by an information processing device, and includes a conversion unit of the information processing device converting messages sent between each of a plurality of personnel into information in which the interaction relationships between the plurality of personnel are structured, based on information about the sender of the message sent between the plurality of personnel and information about the recipient of the message sent.

[0015] According to the present invention, it is possible to generate information in which the interaction relationships based on messages between members are structured.

[0016] FIG. 1 is a diagram showing an application example of a structural information acquisition system according to an embodiment of the present invention. FIG. 2 is a diagram showing an example of the result of converting a communication log into a graph structure of interaction relationships between members. FIG. 3 is a diagram explaining an example of expression rules for the graph structure of interaction relationships between members. FIG. 4 is a diagram showing an example of various information within a message. FIG. 5 is a diagram showing an example of various information between messages. FIG. 6 is a flowchart showing an example of a processing procedure for converting a communication log on a thread into a graph structure of interaction relationships between members. FIG. 7 is a block diagram showing an example of the hardware configuration of a structural information acquisition system according to an embodiment of the present invention.

[0017] An embodiment of the present invention will be described below with reference to the drawings. A structural information acquisition system according to one embodiment of the present invention converts a communication log between team members, such as voice or chat content, into information (sometimes referred to as a graph structure of interaction relationships) in which interaction relationships between team members are structured as a graph, including (1) the destinations of members between messages and within messages, (2) reactions to messages, and (3) relationships between messages. This information is information in which interaction relationships regarding actions performed by each of multiple members are structured.

[0018] 1 is a diagram showing an application example of a structural information acquisition system according to an embodiment of the present invention. As shown in FIG. 1, the structural information acquisition system (structural information acquisition device) 100 includes an input unit 10 and a structural information conversion unit 20.

[0019] <Input> The input unit 10 of the structural information acquisition system 100 inputs a communication log between members belonging to a team. <Output> FIG. 2 is a diagram showing an example of the result of converting the communication log into a graph structure of the interaction relationships between members. FIG. 3 is a diagram explaining an example of a rule for expressing the graph structure of the interaction relationships between members. The structural information conversion unit 20 of the structural information acquisition system 100 converts the communication log input by the input unit 10 into information showing the graph structure of the interaction relationships between members, as shown in FIG. 2, and outputs this to, for example, a display device (not shown). That is, the structural information conversion unit 20 converts messages sent between each of the multiple members into information in which the interaction relationships between the multiple members are structured, based on information about the senders of the messages sent between the multiple members and information about the recipients of the messages.

[0020] 2 and 3, the conversion results of the structural information acquisition system 100 may include (1) the message of the new topic, which is the first message, and (2) messages of each thread that are lower in the hierarchy than the message of the new topic, i.e., messages that are children in a parent-child relationship. The conversion results include (1) a message with a mention from one member to another, (2) a reaction from one member to another, for example, a message with a stamp-like mark, and (3) the relationship between a message sent from one member and a message from another member.

[0021] The above-mentioned messages with mentions and reactions are information in which the relationships within messages between members are structured, and the above-mentioned message relationships are information in which the parent-child relationships between messages are structured.

[0022] This allows the present embodiment to structurally handle interaction relationships between members regarding (1) the destinations of members between messages and within messages, (2) reactions to messages, and (3) relationships between messages.

[0023] Next, a mathematical representation of the graph-structured information will be described. The structural information conversion unit 20 acquires the following information (1), (2), and (3) contained in the communication log input by the input unit 10: (1) member i∈set of members N (2) message set k∈set of messages M from a member (3) parent-child relationship y between multiple messages ｋｊ The parent-child relationship is the relationship when the parent message is message j and the child message is message k. Here, if message j and message k do not have a parent-child relationship, then "y ｋｊ If message j and message k have a parent-child relationship, then it is written as "y ｋｊ =1".

[0024] Then, the structural information conversion unit 20 obtains the following information (1) to (4) from the obtained information: (1) Destination member V of message k ｋ (2) Message k's sender H ｋ (3) Member R who reacted to message k ｋ (4) New topic set S (= {k | Σ ｊ∈Ｍ y ｋｊ = 0})

[0025] 4 is a diagram showing an example of various information in a message. In the example shown in Fig. 4, the sender of message k is "member A," the recipients of message k are "member B," "member C," and "member D," and the member who reacted to message k is "member D."

[0026] 5 is a diagram showing an example of various types of information between messages. The example shown in Fig. 5 shows (1) multiple threads, where a set of messages starting from a message in a new topic is considered to be one thread, (2) each message in each thread, and (3) messages j and k, which have a parent-child relationship within the thread. As described above, message j is the parent message from the perspective of message k.

[0027] 6 is a flowchart showing an example of a processing procedure for converting a communication log on a thread into a graph structure of interaction relationships between members. The structural information conversion unit 20 converts the following information contained in the communication log input by the input unit 10: (1) member i∈member set N, (2) message k∈message set M from a member, and (3) parent-child relationships y between multiple messages. ｋｊ , is used as input information, the number of acquired messages is substituted into variable m, and 1 is substituted into variable k (S11).

[0028] When the currently set value of k is equal to or less than the value of m (Yes in S12), the structural information conversion unit 20 determines from the input information that the sender H of the message k ｋ In this embodiment, the input information includes the sender H of the message k. ｋ It is assumed that the following information is inherent.

[0029] The structural information conversion unit 20 converts the input information into the ｋ The destination member V of message k sent from ｋ In this embodiment, when the input information includes information of the destination member V of the message k, this information is acquired (S14). ｋ If the information is not included, the acquisition in S14 is not performed.

[0030] The structural information conversion unit 20 converts the input information into the ｋ Member R reacted to message k sent by ｋ In this embodiment, if the input information includes the member R ｋ If the information is not included, the acquisition in S15 is not performed.

[0031] If the input information includes information indicating that message k is a message of a new topic (Yes in S16), the structural information conversion unit 20 determines that message k is a message of a new topic (S17).

[0032] On the other hand, if the input information includes information indicating that message k is not a message of a new topic (No in S16), the structural information conversion unit 20 determines that message k is not a message of a new topic, and obtains message j from the input information, which is a message related to message k and was generated at a time earlier than the time when message k was generated, and is the so-called parent message (S18).

[0033] After S17 or S18, the structural information conversion unit 20 updates the variable k by incrementing it by 1 (S19) and returns to S12. When the currently set value of k is no longer equal to or less than the value of m (No in S12), the series of processes by the structural information conversion unit 20 ends.

[0034] 7 is a block diagram showing an example of the hardware configuration of a structural information acquisition system 100 according to one embodiment of the present invention. In the example shown in FIG. 7, the structural information acquisition system 100 according to the embodiment is configured, for example, by a server computer or a personal computer, and has a hardware processor 111A such as a CPU. A program memory 111B, a data memory 112, an input / output interface 113, and a communication interface 114 are connected to this hardware processor 111A via a bus 115.

[0035] The communication interface 114 includes, for example, one or more wireless communication interface units, and enables transmission and reception of information to and from a communication network NW. As the wireless interface, for example, an interface that adopts a low-power wireless data communication standard such as a wireless LAN (Local Area Network) is used.

[0036] An input device 300 and an output device 400 used by a user or the like are connected to the input / output interface 113. The input / output interface 113 receives operation data input by a user or the like through the input device 300, such as a keyboard, touch panel, touchpad, or mouse, and outputs the output data to an output device 400, which may include a display device using a liquid crystal or organic electroluminescence (EL) display, for display. The input device 300 and the output device 400 may be devices built into the structural information acquisition system 100, or may be input devices and output devices of other information terminals that can communicate with the structural information acquisition system 100 via the network NW.

[0037] The program memory 111B is a non-transitory tangible storage medium that is a combination of a non-volatile memory that can be written to and read from at any time, such as a hard disk drive (HDD) or a solid state drive (SSD), and a non-volatile memory such as a read only memory (ROM), and stores programs necessary to execute various control processes, etc., according to one embodiment.

[0038] The data memory 112 is a tangible storage medium that is a combination of, for example, the above-mentioned nonvolatile memory and a volatile memory such as RAM (Random Access Memory), and is used to store various data acquired and created during various processing steps.

[0039] A structural information acquisition system 100 according to one embodiment of the present invention may be configured as a data processing system or information processing device having a software-based processing function unit. The storage system used as a work memory or the like by the structural information acquisition system 100 may be configured using the data memory 112 shown in FIG. 7. However, these configured storage areas are not essential components within the structural information acquisition system 100, and may be areas provided in a storage system such as an external storage medium such as a USB (Universal Serial Bus) memory, or a database server located in the cloud.

[0040] The processing function unit can be realized by having the hardware processor 111A read and execute a program stored in the program memory 111B. However, the processing function unit may also be realized in various other forms, including an integrated circuit such as an application specific integrated circuit (ASIC (Application Specific Integrated Circuit) or FPGA (Field-Programmable Gate Array)).

[0041] The methods described in each embodiment may be stored as a program (software means) that can be executed by a computer on a recording medium such as a magnetic disk (e.g., a floppy disk, a hard disk, etc.), an optical disk (e.g., a CD-ROM, a DVD, an MO, etc.), or a semiconductor memory (e.g., a ROM, a RAM, a flash memory, etc.), or may be transmitted and distributed via a communication medium. The program stored on the medium also includes a configuration program that configures the software means (including not only executable programs but also tables and data structures) that the computer executes. The computer that realizes this device reads the program stored on the recording medium and, in some cases, configures the software means using the configuration program, and executes the above-described processing by having the operation controlled by this software means. The term "recording medium" as used herein is not limited to a storage medium for distribution, but also includes a storage medium such as a magnetic disk or semiconductor memory installed inside the computer or in a device connected via a network.

[0042] The present invention is not limited to the above-described embodiments, and various modifications can be made in the implementation stage without departing from the spirit of the invention. Furthermore, the embodiments may be implemented in appropriate combinations, in which case the combined effects can be obtained. Furthermore, the above-described embodiments include various inventions, and various inventions can be extracted by combining selected elements from the disclosed elements. For example, if the problem can be solved and the desired effect can be obtained even if some elements are deleted from all elements shown in the embodiments, the configuration from which these elements are deleted can be extracted as an invention.

[0043] 100... structural information acquisition system 10... input unit 20... structural information conversion unit

Claims

1. An information processing device having a conversion unit that converts a message sent between each of a plurality of people into information in which the interaction relationships between the plurality of people are structured, based on information on the sender of the message sent between the plurality of people and information on the destination of the message sent.

2. The information processing device according to claim 1, wherein the conversion unit converts, when the sent message is a new message between the plurality of personnel, the message sent between the plurality of personnel into information including structured information regarding the relationship between the new message and a message generated by a person who referenced the message.

3. The information processing device according to claim 1, wherein the conversion unit converts messages sent between the plurality of personnel into information in which the interaction relationships between the plurality of personnel are structured based on information on the sender of the message sent between the plurality of personnel, information on the destination of the message sent, and information on the personnel who responded to the message sent.

4. A method performed by an information processing device, comprising: a conversion unit of the information processing device converting a message sent between each of a plurality of persons into information in which the interaction relationships between the plurality of persons are structured, based on information on the sender of the message sent between the plurality of persons and information on the destination of the message sent.

Images