Analysis system, analysis method, and program

Abstract

To provide an analytical system that can appropriately understand the communication status among members. [Solution] The analysis system according to this disclosure comprises a message acquisition unit that acquires messages sent and received between multiple members belonging to a group, a work history acquisition unit that acquires the work history of each of the multiple members, an analysis unit that analyzes the relationships between members based on the messages and work history, and a generation unit that generates a network diagram showing the relationships between members based on the analysis results.

Description

Technical Field

[0001] The present disclosure relates to an analysis system, an analysis method, and a program.

Background Art

[0002] In companies and other organizations, smooth communication among members constituting the organization is an important factor for improving work efficiency and organizational strength. In recent years, techniques for facilitating the understanding of the communication situation of an organization by visualizing the relationships among members are known.

[0003] As a related technique, Patent Document 1 discloses an information processing server capable of easily grasping the relationships of a plurality of management targets. In the information processing server, the control unit identifies the relationships of the management target users based on at least one of the content, number, and frequency of messages transmitted and received among the management target users.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In recent years, along with the diversification of work styles, not only the commuting work of going to the office but also the telework work style of performing work at home or in a co-working space without going to the office has been introduced. In a telework environment, it is assumed that communication deficiencies and weakening of cooperation relationships among members are likely to occur. Therefore, in order to correctly grasp the communication situation of the entire organization, it is desirable to take into account the influence of the work style.

[0006] The purpose of this disclosure is to provide an analysis system, analysis method, and program that can appropriately grasp the communication status among members, in light of the issues described above. [Means for solving the problem]

[0007] The analysis system related to this disclosure is A message acquisition unit that acquires messages sent and received between multiple members belonging to a group, A work history acquisition unit acquires the work history of each of the aforementioned multiple members, Based on the aforementioned messages and work history, an analysis unit analyzes the relationships between members, It comprises a generation unit that generates a network diagram showing the relationships between members based on the analysis results.

[0008] The analysis method related to this disclosure is: A message retrieval step that retrieves messages sent and received between multiple members belonging to a group, A work history acquisition step to acquire the work history of each of the aforementioned multiple members, Based on the aforementioned messages and work history, an analysis step is performed to analyze the relationships between members, This includes a generation step that generates a network diagram showing the relationships between members based on the analysis results.

[0009] The program related to this disclosure is A message retrieval step that retrieves messages sent and received between multiple members belonging to a group, A work history acquisition step to acquire the work history of each of the aforementioned multiple members, Based on the aforementioned messages and work history, an analysis step is performed to analyze the relationships between members, Based on the analysis results, the system generates a network diagram showing the relationships between members, and then has the computer perform this generation step. [Effects of the Invention]

[0010] The analysis system, analysis method, and program according to the present disclosure enable appropriate grasping of the communication status among members.

Brief Description of the Drawings

[0011] [Figure 1] FIG. 1 is a block diagram showing the configuration of the analysis system according to the present disclosure. [Figure 2] FIG. 2 is a flowchart showing the flow of processing performed by the analysis system. [Figure 3] FIG. 3 is a block diagram showing the overall configuration of the communication system. [Figure 4] FIG. 4 is a diagram showing an example of attribute information. [Figure 5] FIG. 5 is a diagram showing an example of work history information. [Figure 6] FIG. 6 is a block diagram showing the configuration of the analysis device. [Figure 7] FIG. 7 is a diagram showing an example of message log information, content category information, and evaluation category information. [Figure 8] FIG. 8 is a diagram showing an example of the network diagram generated by the generation unit. [Figure 9] FIG. 9 is a flowchart showing the flow of analysis processing for analyzing the relationship between employees. [Figure 10] FIG. 10 is a flowchart showing the flow of warning processing for warning the sender of a message. [Figure 11] FIG. 11 is a block diagram exemplifying the hardware configuration of a computer that realizes the analysis system and the like.

Embodiments for Carrying Out the Invention

[0012] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are denoted by the same reference numerals. For the sake of clarity of explanation, duplicate explanations are omitted as necessary.

[0013] <Embodiment 1> (Analysis System 100) FIG. 1 is a block diagram showing the configuration of an analysis system 100 according to the present disclosure. The analysis system 100 includes a message acquisition unit 101, a work history acquisition unit 102, an analysis unit 103, and a generation unit 104.

[0014] The message acquisition unit 101 acquires messages transmitted and received among a plurality of members belonging to a group. The work history acquisition unit 102 acquires the work history of each of the plurality of members. The analysis unit 103 analyzes the relationship between the members based on the messages and the work history. The generation unit 104 generates a network diagram showing the relationship between the members based on the analysis result.

[0015] The analysis system 100 includes a processor, a memory, and a storage device as components not shown in the figure. A computer program implementing the processing according to the present disclosure is stored in the storage device. The processor can read the computer program from the storage device into the memory and execute the computer program. Thereby, the processor realizes the functions of the message acquisition unit 101, the work history acquisition unit 102, the analysis unit 103, and the generation unit 104.

[0016] Alternatively, the message acquisition unit 101, the work history acquisition unit 102, the analysis unit 103, and the generation unit 104 may each be realized by dedicated hardware. Some or all of each component may be realized by general-purpose or dedicated circuitry, a processor, etc., or a combination thereof. These may be constituted by a single chip or by a plurality of chips connected via a bus. Some or all of each component may be realized by a combination of the above-described circuitry, etc. and a program.

[0017] (Processing of Analysis System 100) Refer to Figure 2 to explain the processes performed by the analysis system 100. Figure 2 is a flowchart showing the flow of processes performed by the analysis system 100.

[0018] First, the message acquisition unit 101 acquires messages sent and received between multiple members (S1). Next, the work history acquisition unit 102 acquires the work history of each of the multiple members (S2). Subsequently, the analysis unit 103 analyzes the relationships between members based on the messages and work history (S3). Finally, the generation unit 104 generates a network diagram based on the analysis results (S4).

[0019] As explained above, the analysis system 100 related to this disclosure analyzes the relationships between members based on messages sent and received between multiple members and the work history of multiple members, and generates a network diagram based on the analysis results. This enables the analysis system 100 to appropriately grasp the communication status between members.

[0020] <Embodiment 2> Next, Embodiment 2 will be described. Embodiment 2 is a specific example of Embodiment 1 described above. Figure 3 is a block diagram showing the overall configuration of the communication system 1 according to this disclosure.

[0021] (Communication System 1) Communication system 1 comprises an analysis device 10, an employee management system 20, and multiple terminal devices 30. Each of the analysis device 10, the employee management system 20, and the multiple terminal devices 30 can communicate with each other via network N. Although Figure 3 shows three terminal devices 30, the number of terminal devices 30 is arbitrary. Although Figure 3 shows three terminal devices 30, the number of terminal devices 30 is arbitrary.

[0022] Each of the analytical device 10, the employee management system 20, and the multiple terminal devices 30 is, for example, a PC (Personal Computer), a smartphone, or a tablet device, but is not limited to these.

[0023] Communication System 1 is a system that analyzes the communication status among multiple members belonging to a group. In Communication System 1, the analysis device 10 functions as a message server that manages the sending and receiving of messages. The analysis device 10 also functions as an analysis device that acquires the sent and received messages and analyzes the messages using technologies such as AI (Artificial Intelligence).

[0024] The analysis device 10 analyzes the relationships between members based on messages sent and received between multiple terminal devices 30 and work history stored in the employee management system 20. The analysis device 10 can analyze the content of messages and message transmission patterns by executing a program including, for example, a natural language processing (NLP) algorithm on its processor. The analysis device 10 also generates a network diagram showing the relationships between members based on the analysis results.

[0025] The following describes an example in which the analysis device 10 has functions as both a message server and a message analysis device, but the configuration of the analysis device 10 is not limited to this. For example, the analysis device 10 may have only the function of an analysis device. In that case, the communication system 1 may have a message server for sending and receiving messages separately from the analysis device 10.

[0026] Messages sent and received in communication system 1 may include, but are not limited to, email, chat, SMS (Short Message Service), SNS (Social Networking Service) messaging functions, or online meeting system messaging functions. Messages only need to be sent and received in a format that allows the sender and recipient to be identified. Messages are not limited to text data; they may also include image data and audio data.

[0027] A group is an entity that is the subject of analysis in this disclosure. Examples of groups include companies, departments, project teams, academic research groups, volunteer organizations, clubs, non-profit organizations, local communities, student clubs, or joint ventures. However, the types of groups are not limited to these. A group can be any type of organization composed of multiple members.

[0028] A member is a person who makes up a group. Members may include, but are not limited to, employees of a company, members of a project team, members of a department, or members of an academic research group.

[0029] The following describes an example of how communication system 1 is used in a company. Each of the multiple members is an employee working for the company. In the following, the entire company is used as an example of a group, but for example, a single department or project team may also be used as a group.

[0030] Next, we will explain the various components of the communication system 1. Note that we will assume that each of the multiple terminal devices 30 has the same configuration.

[0031] (Terminal device 30) Terminal device 30 is a terminal used by employees belonging to a company. Employees operate terminal device 30 to exchange messages with other employees. For example, terminal device 30 sends a message to another terminal device 30. Terminal device 30 also receives messages from other terminal devices 30. In this way, employees send and receive messages with other employees.

[0032] The terminal device 30 includes a communication unit (not shown). This communication unit is a communication interface for wired or wireless communication. This communication unit transmits and receives data between the analysis device 10, the employee management system 20, and other terminal devices 30. For example, the terminal device 30 transmits and receives messages via the analysis device 10, which functions as a message server.

[0033] (Employee Management System 20) The employee management system 20 is a system for managing employees. For example, the employee management system 20 manages employee attribute information. The employee management system 20 includes a storage unit 29. The storage unit 29 stores attribute information 291 and work history information 292.

[0034] Attribute information 291 is information that manages the attributes of an employee. Figure 4 shows an example of attribute information 291. Attribute information 291 includes employee ID, employee name, university attended, and year of joining the company, which identify the employee. The information stored as attribute information 291 is not limited to these. Attribute information 291 may include various other information about the employee.

[0035] For example, attribute information 291 may include the following information: • Position, years of service • Work experience (past job titles, departments, and project experience) • Skill set (technical skills, qualifications, and expertise) • Language proficiency (languages ​​used and their level) • Work location / office (current work location, past work history) • Mentor-mentee relationships (history of official and unofficial mentoring relationships) • History of participation in internal and external activities (information on participation in internal and external events, committees, volunteer activities, etc.) • Evaluation and Award History (Past performance evaluations, awards received) • Areas of interest (interests and concerns both inside and outside of work) • Whether or not you have childcare or eldercare responsibilities. • Whether or not you commute long distances

[0036] Work history information 292 is information that shows an employee's work performance. Figure 5 is a diagram showing an example of work history information 292. Work history information 292 includes employee ID, work date, and work style information. Work style information includes whether the work was done in the office or remotely. For example, if an employee goes to the company office to work, the work style is "in-office work". Also, if an employee works from home or a co-working space, the work style is "remote work".

[0037] The information stored as work history information 292 is not limited to these. Work history information 292 may include various types of information related to work. For example, work history information 292 may include information about the work location within the office.

[0038] The employee management system 20 includes a communication unit (not shown). This communication unit transmits and receives data between the analysis device 10 and the multiple terminal devices 30. This communication unit is a communication interface for wired or wireless communication. This communication unit transmits and receives data between the analysis device 10 and the multiple terminal devices 30.

[0039] (Analyzer 10) Figure 6 is a block diagram showing the configuration of the analysis device 10. The analysis device 10 is an example of the analysis system 100 described above. The analysis device 10 comprises a message acquisition unit 11, a work history acquisition unit 12, an analysis unit 13, a generation unit 14, a warning unit 15, a summarization unit 16, a memory control unit 17, a communication unit 18, and a memory unit 19. The analysis device 10 acquires data from the employee management system 20 and multiple terminal devices 30, and uses the acquired data to analyze the relationships between employees. The analysis device 10 also outputs a network diagram based on the analysis results.

[0040] The analysis device 10 includes a processor and memory, although these are not shown in the diagram. The storage unit 19, which is a storage device, stores a computer program on which the processing described herein is implemented. The processor can load the computer program from the storage unit 19 into memory and execute the computer program. As a result, the processor realizes the functions of the message acquisition unit 11, the work history acquisition unit 12, the analysis unit 13, the generation unit 14, the warning unit 15, the summarization unit 16, and the memory control unit 17.

[0041] The message acquisition unit 11 is an example of the message acquisition unit 101 described above. The message acquisition unit 11 acquires messages sent and received between multiple employees (members) belonging to a company (group). The messages are sent and received by the company's employees using email or chat. The messages are sent and received via the terminal device 30.

[0042] The message acquisition unit 11 may acquire messages at predetermined time intervals. The message acquisition unit 11 may acquire messages in real time, for example. The message acquisition unit 11 also identifies the sender and recipient of the acquired messages. The message acquisition unit 11 stores the acquired information as message log information 191 in the storage unit 19.

[0043] For example, the predetermined time interval may be determined as follows: The message acquisition unit 11 may acquire messages at short time intervals (e.g., every 5 minutes) during business hours (e.g., 9:00 AM to 11:00 AM, 1:00 PM to 3:00 PM, etc.) and at longer time intervals (e.g., every hour) outside of business hours. The message acquisition unit 11 reduces the frequency of acquisition or temporarily suspends acquisition during times when it may affect an individual's privacy (e.g., lunch break or outside of working hours). The message acquisition unit 11 immediately starts acquiring messages when it detects specific keywords or messages of high urgency, and acquires them at short time intervals. The message acquisition unit 11 connects with other internal systems (e.g., project management tools, attendance management systems) via API (Application Programming Interface) and automatically adjusts the frequency of message acquisition according to important events (such as before deadlines or before and after large meetings). The message acquisition unit 11 acquires messages more frequently (e.g., every minute) for high-priority targets such as specific project teams, or during periods of legal compliance or audit response. The message acquisition unit 11 dynamically adjusts the acquisition interval according to the system's processing load. The message acquisition unit 11 widens the interval when the load is high and narrows it when the load is low.

[0044] The processing performed by the message acquisition unit 11 may include data acquisition and message parsing based on a communication protocol. The communication protocol may be, for example, SMTP (Simple Mail Transfer Protocol) or IMAP (Internet Message Access Protocol), but is not limited to these. Any protocol corresponding to the message sending and receiving method may be used.

[0045] Figure 7 shows an example of message log information 191, content category information 192 and evaluation category information 193, which will be described later. The message log information 191 is information that associates the message ID that identifies the message, the date and time it was sent, the date and time it was received, the sender, the recipient, and the content of the message.

[0046] For example, the content of the message may be encrypted using a strong encryption algorithm to protect privacy. Specifically, the content of the message may be encrypted and then managed as message log information 191. For example, homomorphic encryption techniques may be used to perform data analysis while the data remains encrypted.

[0047] Returning to Figure 6, the work history acquisition unit 12 is an example of the work history acquisition unit 102 described above. The work history acquisition unit 12 acquires the work history of multiple employees (members). For example, the work history acquisition unit 12 acquires the employee ID of the employee to be analyzed. The work history acquisition unit 12 refers to the employee management system 20 and searches the work history information 292 stored in the storage unit 29 using the employee ID as a key, and extracts the work history of the employee in question. The work history acquisition unit 12 acquires the extracted work history. The work history acquisition unit 12 performs these processes by executing a database search algorithm.

[0048] The analysis unit 13 is an example of the analysis unit 103 described above. The analysis unit 13 analyzes the relationships between employees based on the messages acquired by the message acquisition unit 11 and the work history acquired by the work history acquisition unit 12. For example, the analysis unit 13 may be composed of a processing module that takes messages and work history as input and outputs data showing the relationships between employees.

[0049] The analysis unit 13 may perform rule-based analysis or analysis using a pre-trained model. When performing rule-based analysis, the analysis unit 13 analyzes the relationships between employees based on the set rules. When using a pre-trained model, the analysis unit 13 executes a pre-trained model (not shown) stored in the memory unit 19 to analyze the relationships between employees.

[0050] The messages used as input information may include, for example, the content, sender, recipient, date and time of sending, date and time of receiving, or title of messages sent and received using email software, as shown in the message log information 191 in Figure 7. Messages are not limited to those sent and received using email software; they may also include those sent and received via chat on a web conferencing tool. Messages may also include information about the meeting location.

[0051] The work history used as input information may include the work day and the employee's work style on that day, as shown in the work history information 292 in Figure 5. The analysis unit 13 can determine whether or not employees worked at the same location based on the employee's work style for each work day.

[0052] Generally, working in the office provides many opportunities for face-to-face interaction with other employees. Therefore, employees who primarily work in the office tend to build trust with colleagues through casual conversations and collaborative work within the office. On the other hand, teleworking involves less direct interaction and more online communication. Consequently, employees who primarily telework find it more difficult to share nonverbal information and subtle nuances, and tend to take longer to build trust with colleagues compared to those who work in the office.

[0053] Due to these environmental differences, it is expected that in-office work environments, spontaneous communication is more active, leading to better relationships among employees. On the other hand, in telework environments, it may be difficult to encourage active communication, and building relationships among employees may become a challenge. Thus, it is expected that differences in communication opportunities and the quality of communication due to work styles will affect relationships among employees. Therefore, the analysis unit 13 can analyze employee relationships by using a combination of messages and work history, taking these correlations into consideration.

[0054] For example, the analysis unit 13 uses messages and work history as input information to perform statistical analysis methods such as regression analysis and clustering. Through this, the analysis unit 13 identifies correlations between, for example, attendance rates and the number of messages, and relationships between employees. The analysis unit 13 can obtain analysis results such as, "Employees with high attendance rates build better relationships with other employees compared to employees with low attendance rates," and "Employees with high attendance rates build better relationships with each other than when one of them is an employee with a low attendance rate."

[0055] The analysis unit 13 may further analyze the relationships between employees based on the individual attributes of multiple employees. In this case, the analysis unit 13 may further use employee attributes as input information. Employee attributes may include, for example, an employee's job title, length of service, or alma mater. The analysis unit 13 may further use organizational information as input information. Organizational information is information that shows the internal structure of a company. Organizational information may include, for example, information such as the division of roles among departments and teams, or the chain of command.

[0056] The analysis unit 13 analyzes the relationships between employees based on the input information described above and outputs the analysis results. For example, the analysis unit 13 analyzes the communication situation between employees using rule-based processing or a trained model and outputs data indicating the relationships between employees as output information. The analysis unit 13 outputs, for example, the amount of communication, the form of communication, the content category of the message, or the evaluation category of the message.

[0057] The volume of communication indicates the amount of communication between employees based on the messages sent and received. The analysis unit 13 may output the volume of communication between employees on an individual basis, an organizational basis such as a department, or a job title basis. For example, the analysis unit 13 may output the volume of communication by executing an arbitrary data aggregation algorithm and analyzing the number and frequency of messages sent and received between employees. The form of communication indicates the means of communication. Examples of forms of communication include email, chat, or phone calls.

[0058] The analysis unit 13 may identify the strength of relationships between employees based on the amount of communication. For example, the analysis unit 13 may identify the strength of relationships between employees based on the number of times messages are sent and received between employees over a predetermined period. For example, the analysis unit 13 may express the strength of relationships between employees as a numerical value from 0 to 100 or as a five-level scale, depending on the number of messages sent and received. For example, the analysis unit 13 may express these values ​​such that the stronger the relationship between employees, the higher the numerical value or the higher the level.

[0059] Furthermore, the analysis unit 13 may express the strength of relationships between employees in writing. For example, the analysis unit 13 may describe employees who have sent and received messages more than a predetermined number of times as having "strong relationships with each other," and employees who have sent and received messages less than a predetermined number of times as having "weak relationships with each other."

[0060] The analysis unit 13 may determine the strength of relationships between departments based on the strength of relationships among employees. For example, the analysis unit 13 may determine the strength of relationships between departments in such a way that the stronger the number of employees with strong relationships, the stronger the relationship between departments becomes.

[0061] The message content category is a classification set up to categorize the content of a message. The analysis unit 13 classifies messages into content categories based on their content. For example, the analysis unit 13 analyzes the content of messages using natural language processing technology and classifies them into categories such as "business troubles," "business communications," "reports on business results," and "private communications."

[0062] The analysis unit 13 stores the classification results as content category information 192 in the storage unit 19. An example of content category information 192 is shown in Figure 7 above. For example, the analysis unit 13 stores the content category information 192 by associating message IDs with content categories. This allows the analysis unit 13 to remember what kind of messages are being sent and received between employees. In this way, the generation unit 14 can generate a detailed network diagram based on the content category information 192.

[0063] The analysis unit 13 may also classify messages into evaluation categories based on their content. A message evaluation category is a classification set up to determine whether a message is positive or negative. For example, the analysis unit 13 may use natural language processing techniques to analyze the message text and identify positive or negative content.

[0064] Furthermore, "a message being positive" means that the message contains positive content or favorable intentions towards the recipient. The analysis unit 13 determines whether the message contains expressions that have a positive impact on the recipient, such as encouragement, gratitude, praise, or cooperative suggestions. If the analysis unit 13 determines that such expressions are included in the message, it classifies the message as positive.

[0065] Conversely, "a message is negative" means that the message contains negative content or critical intent towards the recipient. The analysis unit 13 determines whether the message contains expressions that cause discomfort or stress to the recipient, such as criticism, negative opinions, accusations, or aggressive language. If the analysis unit 13 determines that such expressions are contained in the message, it classifies the message as negative.

[0066] The analysis unit 13 stores the classification results as evaluation category information 193 in the storage unit 19. An example of evaluation category information 193 is shown in Figure 7 above. For example, the analysis unit 13 associates message IDs with evaluation categories and stores the evaluation category information 193. This allows the analysis unit 13 to store what kind of evaluation messages are being sent and received between employees. In this way, the generation unit 14 can generate a detailed network diagram based on the evaluation category information 193.

[0067] These classifications are performed based on established rules and algorithms of trained models. Furthermore, the criteria for determining whether a message is positive or negative may be adjusted as appropriate depending on the specifications and operational objectives of communication system 1. For example, in addition to "positive" and "negative," evaluation categories such as "neither" may be set.

[0068] The analysis unit 13 may classify messages into evaluation categories not only based on message content but also on the manner in which the messages are sent. For example, the analysis unit 13 analyzes the frequency and pattern of message transmission between the sender and receiver. For instance, if a predetermined number of messages are sent unilaterally within a predetermined period, the analysis unit 13 may classify the series of messages as negative.

[0069] Furthermore, the analysis unit 13 may determine whether a negative message may constitute harassment of the recipient. For example, the analysis unit 13 may determine whether the message contains elements that may constitute harassment. Elements included in the message may be, for example, text, images, audio, or the manner of transmission. For example, if the message contains intimidating, insulting, or other inappropriate language, the analysis unit 13 may determine that the message may constitute harassment.

[0070] For example, the analysis unit 13 may make the determination by analyzing the text data within the message using natural language processing technology. The analysis unit 13 divides the text data of the message into words or phrases and performs grammatical and semantic analysis. The analysis unit 13 may also analyze the context, tone, or vocabulary used in the message and perform sentiment analysis. This allows the analysis unit 13 to determine whether the message is positive or negative, and whether the message may constitute harassment.

[0071] Furthermore, the analysis unit 13 may determine whether the content of the message may violate laws and regulations. For example, the analysis unit 13 analyzes the text data in the message using natural language processing technology. The analysis unit 13 detects predefined keywords and phrases related to legal violations from the message. Based on this, the analysis unit 13 determines whether the message contains words that may violate, for example, the Personal Information Protection Act, or words that may constitute defamation or libel. If such words are contained in the message, the analysis unit 13 determines that the message may violate laws and regulations.

[0072] Returning to Figure 6, the generation unit 14 is an example of the generation unit 104 described above. Based on the analysis results in the analysis unit 13, the generation unit 14 generates a network diagram showing the relationships between employees. For example, the generation unit 14 processes data showing the relationships between employees (e.g., the amount of messages sent and received) and executes an algorithm to visualize the relationships between employees using a network diagram. In this way, the generation unit 14 visualizes the communication situation between employees using a network diagram.

[0073] The network diagram illustrates the relationships between employees. The network diagram may, for example, represent employees as nodes and relationships between employees as edges. For instance, the generation unit 14 generates the network diagram based on the analysis results when it obtains the analysis results from the analysis unit 13. However, the generation unit 14 may also generate the network diagram according to the requests of the users of the communication system 1. The users of the communication system 1 are, for example, company managers (administrators).

[0074] For example, the generation unit 14 generates a network diagram based on the attributes of multiple employees. The generation unit 14 may also extract only employees with attributes selected by a manager or other person, and generate a network diagram showing only the relationships of the extracted employees. The generation unit 14 displays the generated network diagram on a display unit (not shown). The display unit is a display device such as a display. The generation unit 14 may also transmit the network diagram to a terminal device 30 used by a manager, and display the network diagram on a display unit (not shown) of the terminal device 30.

[0075] This allows managers to understand interpersonal relationships within the organization. For example, managers can find out which employees in their own department have many acquaintances in other departments. They can also find out which employees get along well with each other and which do not. Furthermore, managers can understand the relationships between different departments.

[0076] Figure 8 shows an example of a network diagram 141 generated by the generation unit 14. The network diagram 141 shows the relationships between departments A to F. In Figure 8, departments A to F are represented by elliptical nodes ND1 to ND6. The connections between departments are represented by straight edges ED1 to ED9 connecting the nodes. The shape of the nodes is not limited to ellipses and can be arbitrary. For example, the shape of the nodes may be circular, polygonal, or star-shaped. Also, the edges are not limited to straight lines but may be curved.

[0077] The generation unit 14 can generate a network diagram in any manner. For example, the generation unit 14 may represent the amount of communication between departments by the thickness of the edges. The generation unit 14 generates the network diagram 141 such that the thicker the edges connecting the nodes corresponding to a department, the greater the amount of communication between departments.

[0078] For example, the generation unit 14 may represent the amount of communication using four types of edges with different thicknesses, as shown in Figure 8. In the example in Figure 8, four levels of edge thickness are used: dashed, thin solid, thick solid, and extra-thick solid. The generation unit 14 identifies which of the four levels of strength the relationship between departments is and connects the nodes using edges of the thickness corresponding to the strength of that relationship.

[0079] For example, edges ED3 and ED9 are shown with dashed lines indicating the weakest relationship. Edges ED1 and ED6 are shown with thin solid lines indicating a stronger relationship than the dashed lines. Edges ED5 and ED7 are shown with thick solid lines indicating a stronger relationship than the thin solid lines. Edges ED2, ED4, and ED8 are shown with extra-thick solid lines indicating the strongest relationship. Note that the generation unit 14 may also indicate the strength of the relationship numerically or otherwise in the network diagram 141.

[0080] The generation unit 14 may represent whether the communication status between departments is positive or negative using edges of different colors. For example, the generation unit 14 may represent the edges connecting departments in blue when the communication status between departments is positive, and in red when the communication status between departments is negative. The generation unit 14 may also vary the shades of blue or red depending on the level of positive or negative.

[0081] In the example in Figure 8, a manager looking at network diagram 141 can see that departments A and C are connected by a thick solid edge, indicating a strong relationship, while departments A and D are connected by a dashed edge, indicating a weak relationship. Alternatively, if many negative messages are being sent and received between departments, and the edges connecting those departments are shown in red, a manager can sense that there may be a problem within the organization.

[0082] The generation unit 14 may generate the network diagram 141 to display not only relationships between departments, but also relationships combining, for example, departments and job titles. For example, the generation unit 14 places checkboxes that accept selections such as "department," "job title," and "employee" near the network diagram 141. The generation unit 14 generates the network diagram 141 so that these combinations can be switched according to the selection results of the checkboxes.

[0083] When generating a network diagram showing relationships between employees, the generation unit 14 can generate the network diagram in the same manner as the interdepartmental network diagram 141. For example, the generation unit 14 may display employee names or employee IDs on the nodes. The generation unit 14 may also represent the strength of relationships between employees using edge thickness or color based on the amount of messages sent and received. The generation unit 14 is not limited to this and may also represent the strength of relationships between employees using numerical values ​​or other methods.

[0084] Furthermore, the generation unit 14 may generate the network diagram by excluding messages whose volume or transmission / reception frequency is less than a predetermined value. This allows the generation unit 14 to generate a network diagram that only includes relationships between departments or employees where there is a reasonable amount of message transmission and reception.

[0085] The generation unit 14 may generate a network diagram based on the classification results into content categories in the analysis unit 13. For example, the generation unit 14 can select a predetermined content category (e.g., "business report") and generate a network diagram related to the selected content category. This allows managers who view the network diagram to understand the communication status for each content category.

[0086] The generation unit 14 may also generate a network diagram based on the classification results into evaluation categories in the analysis unit 13. For example, the generation unit 14 may select a predetermined evaluation category (e.g., "negative") and generate a network diagram related to the selected evaluation category. This allows managers who view the network diagram to understand the communication situation for each evaluation category. For example, managers can easily identify departments or employees where positive messages are being sent and received, and departments or employees where negative messages are being sent and received. This allows managers to easily grasp the overall atmosphere of the organization and specific problems, which can be used to improve organizational management.

[0087] Furthermore, the generation unit 14 may select a predetermined work schedule (for example, "working in the office") and generate a network diagram relating to the selected work schedule. This allows managers to understand the differences in relationships among employees due to differences in work schedules.

[0088] Return to Figure 6. The warning unit 15 issues a warning to the sender of a message if the message meets the warning criteria, which indicate that the message may worsen relationships between employees. The warning criteria may include, for example, that the content or manner of sending the message may constitute harassment of the recipient. The warning criteria may also include that the content or manner of sending the message may violate laws and regulations. The warning unit 15 may use an algorithm to analyze the text content of the message to determine whether it may constitute harassment or violate laws and regulations.

[0089] The warning unit 15 issues a warning via the sender's terminal device 30 if the message meets the conditions for a warning. For example, the warning unit 15 issues a warning by notifying the sender's terminal device 30 that the message may constitute harassment or a violation of the law.

[0090] The warning unit 15 may suggest to the sender that they modify the content of the message if the message meets the conditions for a warning. For example, the warning unit 15 may send a message to the sender's terminal device 30 such as, "The message you sent to E1 on X month Y day may constitute harassment. Please modify the content of the message." In this way, the sender can review the content of the message and consider making corrections.

[0091] The warning unit 15 may suggest revisions to messages that meet the warning criteria. The warning unit 15 sends a message such as "We suggest revising the message to something like this" to the sender's terminal device 30. In this way, the warning unit 15 can send advice to employees to improve communication, thereby supporting communication throughout the organization. This also makes it possible to address communication problems at an early stage.

[0092] The warning unit 15 may also temporarily retrieve the content of a message before it is sent to the recipient and determine whether the message meets the conditions for a warning that could worsen relationships between employees. If the warning unit 15 determines that the message does not meet the conditions for a warning, it proceeds to deliver the message to the recipient; if it determines that the conditions for a warning are met, it cancels sending the message. In this way, the warning unit 15 can prevent the sending of messages that may constitute harassment.

[0093] The summarization unit 16 generates a summary of the message. The summarization unit 16 may generate the summary using technologies such as AI. For example, the summarization unit 16 analyzes the message data using natural language processing technology, generates summaries of messages classified into a predetermined content category (e.g., "business troubles"), and provides the generated summaries to the manager. The summarization unit 16 may also generate summaries of messages classified into a predetermined evaluation category (e.g., "negative"), and provide the generated summaries to the manager.

[0094] The summarization unit 16 can identify important messages that have been categorized from among many messages and generate a summary. This allows managers to respond quickly to communication problems among employees. For example, managers can identify signs of harassment and evaluate relationships among employees as needed, enabling them to give necessary instructions and take action early.

[0095] The memory control unit 17 causes the memory unit 19 to store information related to the message. The memory control unit 17 selects the content of the message information to be stored in the memory unit 19. Specifically, the memory control unit 17 stores information in the memory unit 19, excluding the content of the message from the storage target, and including information of categories corresponding to the content of the message from the storage target. The categories may be the content categories and evaluation categories described above, or both. If the content of the message is temporarily stored, the memory control unit 17 may measure the elapsed time since the message was acquired and delete the content of the message after a predetermined time has elapsed.

[0096] In this way, the memory control unit 17 can store only category information corresponding to the message content or evaluation, without storing the actual message content in the memory unit 19. This allows the memory control unit 17 to store data that helps improve relationships among employees while protecting the sender's privacy. Furthermore, the memory control unit 17 can minimize the amount of data stored in the memory unit 19.

[0097] The memory control unit 17 may store in the memory unit 19 the number of times warnings or suggestions for message corrections have been issued to an employee, associated with the employee ID. The memory control unit 17 may also provide the number of warnings issued to managers. This allows managers to take measures such as individually interviewing employees who have received many warnings.

[0098] The communication unit 18 is a communication interface for communication via wired or wireless means. The communication unit 18 transmits and receives data between the employee management system 20 and each of the multiple terminal devices 30.

[0099] The storage unit 19 stores various types of data and programs. For example, the storage unit 19 stores a computer program on which the processing related to this disclosure is implemented. At least a portion of the storage unit 19 is composed of non-volatile memory so that data is retained even when the power to the analyzer 10 is turned off. The storage unit 19 stores the message log information 191, content category information 192, and evaluation category information 193 described above.

[0100] The configuration of communication system 1 has been described above. The configuration of communication system 1 described above is merely an example and can be modified as appropriate. For example, if some or all of the components of the analysis device 10 and the employee management system 20 are implemented by multiple information processing devices or circuits, these multiple information processing devices or circuits may be centrally located or distributed. For example, the information processing devices or circuits may be implemented in a form in which each is connected via a communication network, such as a client-server system or a cloud computing system. Furthermore, the functions of the analysis device 10 and the employee management system 20 may be provided in SaaS (Software as a Service) format.

[0101] (Processing by analyzer 10) Next, the processes performed by the analysis device 10 will be explained with reference to Figures 9 and 10. Figures 9 and 10 are flowcharts showing the processing flow of the analysis device 10. Specifically, Figure 9 is a flowchart showing the flow of the analysis process that analyzes the relationships between employees. Figure 10 is a flowchart showing the flow of the warning process that issues a warning to the message sender.

[0102] (Analysis processing) First, the analysis process will be explained with reference to Figure 9. The message acquisition unit 11 acquires messages sent and received between multiple employees (S11). The messages may be sent and received using email or chat. The message acquisition unit 11 identifies the sender and recipient of the acquired messages and stores the acquired information in the storage unit 19 as message log information 191.

[0103] Next, the work history acquisition unit 12 acquires the work history and attributes of each of the multiple employees related to the acquired message from the employee management system 20 (S12). The work history and attributes are stored in the storage unit 29 of the employee management system 20 as work history information 292 and attribute information 291, respectively.

[0104] Next, the analysis unit 13 analyzes the acquired messages (S13). For example, the analysis unit 13 analyzes the messages using any technology such as AI. For example, the analysis unit 13 classifies the messages into content categories based on their content. The analysis unit 13 may classify the messages into categories such as "business troubles," "business communications," "reports on business results," and "private communications" based on their content.

[0105] The analysis unit 13 may also classify messages into evaluation categories based on their content or transmission method. For example, the analysis unit 13 may classify messages as either "positive" or "negative."

[0106] Next, the analysis unit 13 analyzes the relationships between employees based on the acquired messages, work history, and attributes (S14). For example, the analysis unit 13 is composed of a processing module that takes messages, work history, and attributes as input and outputs data indicating the relationships between employees. For example, the analysis unit 13 uses AI or the like to perform rule-based processing or processing using a trained model and outputs data indicating the relationships between employees. The analysis unit 13 may further analyze the relationships between employees based on content categories and evaluation categories.

[0107] Next, the generation unit 14 generates a network diagram showing the relationships between employees based on the analysis results from the analysis unit 13 (S15). For example, the generation unit 14 generates a network diagram in which employees are represented as nodes and the relationships between employees are represented as edges. The generation unit 14 can generate a network diagram in any manner. The generation unit 14 may generate a network diagram of only employees with predetermined attributes, or a network diagram of only employees with predetermined work arrangements, etc. The generation unit 14 may also represent the strength of the relationships between employees by the thickness or density of the edges, or by representing the strength of the relationships between employees with numerical values, etc. Furthermore, as explained using Figure 8, the generation unit 14 may also generate a network diagram showing the strength of the relationships between departments.

[0108] Next, the summarization unit 16 generates summaries of messages classified into predetermined categories (S16). The predetermined categories are those selected as targets for summary generation. The summarization unit 16 may select these categories based on the volume of messages, or it may accept the selection of these categories from a manager. The summarization unit 16 may generate summaries using AI.

[0109] The summarization unit 16 provides the generated summary to the manager (S17). For example, the summarization unit 16 transmits the summary to the terminal device 30 used by the manager via the network N. The summarization unit 16 may also transmit a network diagram along with the summary. This allows the manager who receives the summary and network diagram to easily understand the relationships between employees.

[0110] Then, the memory control unit 17 causes the memory unit 19 to store information related to the message (S18). For example, the memory control unit 17 causes the memory unit 19 to store information in a category corresponding to the message content, but without including the message content itself as the item to be stored. In this way, the memory unit 19 can store information related to the message while protecting the sender's privacy.

[0111] (Warning processing) Next, the warning process will be explained with reference to Figure 10. The warning unit 15 issues a warning to the sender of a message if the message meets the conditions for a warning, which could worsen relationships between employees. In the following example, the conditions for a warning include the possibility that the content of the message constitutes harassment against the recipient.

[0112] The warning unit 15 may perform this warning process at any time. For example, the warning unit 15 may perform the warning process when the analysis unit 13 has finished analyzing the message, or it may perform the warning process periodically at predetermined time intervals. The warning unit 15 may target one message for warning processing, or it may target multiple messages for warning processing. Below, we will describe an example in which a warning process is performed for a single message when its analysis has finished.

[0113] First, the warning unit 15 determines whether the message's evaluation category is negative (S21). If it determines that the message's evaluation category is not negative (NO in S21), the process proceeds to step S24. If it determines that the message's evaluation category is negative (YES in S21), the warning unit 15 determines whether the message may constitute harassment (S22). If it determines that the message does not have a high probability of constituting harassment (NO in S22), the process proceeds to step S24.

[0114] If the warning unit 15 determines that the message may constitute harassment (YES in S22), it suggests to the sender that the message be modified (S23). The warning unit 15 may send a message to the sender's terminal device 30 prompting the user to modify the message, or it may send a suggested modification of the message. The memory control unit 17 stores the information regarding the message in the memory unit 19 (S24).

[0115] As explained above, in the communication system 1 related to this disclosure, the analysis device 10 acquires messages sent and received between multiple employees and the work history of each of the multiple employees, and analyzes the relationships between employees based on the acquired messages and work history. Based on the analysis results, the analysis device 10 generates a network diagram showing the relationships between employees and provides the network diagram to the manager.

[0116] This allows the analysis device 10 to visualize relationships between employees or departments in a network diagram and provide the results to managers. Furthermore, since the analysis device 10 can display information such as the amount of communication in the network diagram, managers can intuitively grasp the state of communication.

[0117] Furthermore, the analysis device 10 can analyze the relationships between employees based on the individual attributes of multiple employees. This allows managers to easily understand communication trends among employees who share common attributes, such as their alma mater or year of joining the company, and to utilize the findings for human resource management.

[0118] Furthermore, the analysis device 10 warns the sender of a message if it is potentially a message that constitutes harassment or violates the law. For example, the analysis device 10 suggests to the sender that they revise the content of the message. In this way, the analysis device 10 can reduce the risk of harassment occurring within the company.

[0119] Furthermore, since the analysis device 10 does not store the actual content of the messages but only the category information of the messages, it is possible to store data that can help improve relationships among employees while protecting employee privacy.

[0120] With this configuration, the communication system 1 related to this disclosure can appropriately grasp the communication status among members and contribute to the smooth operation of organizations such as companies.

[0121] <Example Hardware Configuration> Each functional component of the analysis system 100, analysis device 10, employee management system 20, and terminal device 30 (hereinafter referred to as "analysis system 100, etc.") may be implemented by hardware (e.g., hardwired electronic circuits) or by a combination of hardware and software (e.g., a combination of electronic circuits and programs that control them). The case in which each functional component of the analysis system 100, etc. is implemented by a combination of hardware and software will be further explained below.

[0122] Figure 11 is a block diagram illustrating the hardware configuration of a computer 900 that implements the analysis system 100, etc. The computer 900 may be a dedicated computer designed to implement the analysis system 100, etc., or it may be a general-purpose computer. The computer 900 may also be a portable computer such as a smartphone or tablet device.

[0123] For example, by installing a predetermined application on computer 900, various functions of the analysis system 100, etc., are realized on computer 900. The above application consists of a program for realizing the functional components of the analysis system 100, etc.

[0124] Computer 900 comprises a bus 902, a processor 904, memory 906, a storage device 908, an input / output interface 910, and a network interface 912. The bus 902 is a data transmission path for the processor 904, memory 906, storage device 908, input / output interface 910, and network interface 912 to send and receive data to and from each other. However, the method of connecting the processor 904 and other components to each other is not limited to bus connection.

[0125] The processor 904 is a variety of processors such as a CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (Field-Programmable Gate Array), or quantum processor (quantum computer control chip). The memory 906 is the main memory, implemented using RAM (Random Access Memory), etc. The storage device 908 is the auxiliary storage, implemented using a hard disk, SSD (Solid State Drive), memory card, or ROM (Read Only Memory), etc.

[0126] The input / output interface 910 is an interface for connecting the computer 900 with input / output devices. For example, input devices such as keyboards and output devices such as display devices are connected to the input / output interface 910.

[0127] The network interface 912 is an interface for connecting computer 900 to a network. This network may be a LAN (Local Area Network) or a WAN (Wide Area Network).

[0128] The storage device 908 stores programs that implement each functional component of the analysis system 100 (programs that implement the aforementioned applications). The processor 904 reads these programs into memory 906 and executes them to implement each functional component of the analysis system 100.

[0129] Each processor executes one or more programs containing a set of instructions for causing the computer to perform the algorithms described with reference to the drawings. These programs, when loaded into the computer, contain a set of instructions (or software code) for causing the computer to perform one or more of the functions described in the embodiments. The programs may be stored in various types of non-transitory computer-readable medium or tangible storage medium. Examples, but not limited to, include non-transitory computer-readable medium or tangible storage medium, such as RAM, ROM, flash memory, SSD or other memory technologies, CD-ROM, DVD (Digital Versatile Disc), Blu-ray® disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices. The programs may also be transmitted over various types of transient computer-readable medium or communication medium. Examples, but not limited to, include transient computer-readable medium or communication medium, such as electrical, optical, acoustic or other forms of propagating signals.

[0130] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure are possible, as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0131] Each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated with one or more other embodiments rather than with only one specific embodiment. As those skilled in the art will understand, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings, for example, to create embodiments not explicitly shown or described. Not all features or steps shown in any one drawing to illustrate an exemplary embodiment are necessarily required, and some features or steps may be omitted. The order of steps shown in any of the drawings may be changed as appropriate.

[0132] Some or all of the above embodiments may also be described as follows, but are not limited to the following: (Note 1) A message acquisition unit that acquires messages sent and received between multiple members belonging to a group, A work history acquisition unit acquires the work history of each of the aforementioned multiple members, Based on the aforementioned messages and work history, an analysis unit analyzes the relationships between members, It comprises a generation unit that generates a network diagram showing the relationships between members based on the analysis results. Analysis system. (Note 2) The analysis unit further analyzes the relationships between the members based on the attributes of each of the members. The analysis system described in Appendix 1. (Note 3) The system further includes a warning unit that issues a warning to the sender of a message if the message meets the conditions for a warning that could worsen relationships between members. The analysis system described in Appendix 1 or 2. (Note 4) The aforementioned warning conditions include the possibility that the content or manner of sending the message constitutes harassment of the recipient. The warning unit, if the message meets the warning criteria, suggests to the sender that the message be modified. The analysis system described in Appendix 3. (Note 5) The system further comprises a summarization unit that generates a summary of the aforementioned message, The analysis unit classifies the message into a content category based on the content of the message. The summarization unit generates summaries of the messages classified into predetermined content categories and provides the generated summaries to the group administrator. The analysis system described in any one of the appendices 1 to 4. (Note 6) The analysis unit classifies the message into an evaluation category indicating whether the message is positive or negative, based on the content or transmission method of the message. The generation unit generates the network diagram based on the classification results into the evaluation categories. The analysis system described in any one of the appendices 1 to 5. (Note 7) The system further includes a storage control unit that stores information relating to the aforementioned message in a storage unit, The memory control unit stores the information without including the content of the message in the storage target, but including information of a category corresponding to the content of the message in the storage target. The analysis system described in any one of the appendices 1 to 6. (Note 8) A message retrieval step that retrieves messages sent and received between multiple members belonging to a group, A work history acquisition step to acquire the work history of each of the aforementioned multiple members, Based on the aforementioned messages and work history, an analysis step is performed to analyze the relationships between members, Includes a generation step that generates a network diagram showing the relationships between members based on the analysis results. Analysis method. (Note 9) A message retrieval step that retrieves messages sent and received between multiple members belonging to a group, A work history acquisition step to acquire the work history of each of the aforementioned multiple members, Based on the aforementioned messages and work history, an analysis step is performed to analyze the relationships between members, Based on the analysis results, the computer is instructed to perform a generation step that generates a network diagram showing the relationships between members. program.

[0133] Some or all of the elements (e.g., configuration and function) described in Appendices 2 to 7 that are dependent on Appendice 1 may also be dependent on Appendices 8 and 9 in the same way as those described in Appendices 2 to 7. Some or all of the elements described in any appendice may be applied to various hardware, software, recording means, systems, and methods for recording software. [Explanation of Symbols]

[0134] 1. Communication System 10 Analyzer 11 Message acquisition unit 12. Department for Acquiring Work History 13 Analysis Department 14 Generation part 15 Warning part 16 Summary Section 17 Memory Control Unit 18 Communications Department 19 Memory section 20 Employee Management System 29 Memory section 30 Terminal devices 100 Analysis Systems 101 Message Acquisition Unit 102 Employment History Acquisition Department 103 Analysis Department 104 Generation part 141 Network Diagram 191 Message log information 192 Content Category Information 193 Rating Category Information 291 Attribute information 292 Work History Information 900 Computers 902 Bus 904 Processor 906 memory 908 Storage Devices 910 Input / Output Interface 912 Network Interface ED1~ED9 Edge ND1~ND6 Nodes N Network

Claims

1. A message acquisition unit that acquires messages sent and received between multiple members belonging to a group, A work history acquisition unit acquires the work history of each of the aforementioned multiple members, Based on the aforementioned messages and work history, an analysis unit analyzes the relationships between members, It comprises a generation unit that generates a network diagram showing the relationships between members based on the analysis results. Analysis system.

2. The analysis unit further analyzes the relationships between the members based on the attributes of each of the members. The analysis system according to claim 1.

3. The system further includes a warning unit that issues a warning to the sender of a message if the message meets the conditions for a warning that could worsen relationships between members. The analysis system according to claim 1 or 2.

4. The aforementioned warning conditions include the possibility that the content or manner of sending the message constitutes harassment of the recipient. The warning unit, if the message meets the warning criteria, suggests to the sender that the message be modified. The analysis system according to claim 3.

5. The system further comprises a summarization unit that generates a summary of the aforementioned message, The analysis unit classifies the message into a content category based on the content of the message. The summarization unit generates summaries of the messages classified into predetermined content categories and provides the generated summaries to the group administrator. The analysis system according to claim 1 or 2.

6. The analysis unit classifies the message into an evaluation category indicating whether the message is positive or negative, based on the content or transmission method of the message. The generation unit generates the network diagram based on the classification results into the evaluation categories. The analysis system according to claim 1 or 2.

7. The system further includes a storage control unit that stores information relating to the aforementioned message in a storage unit, The memory control unit stores the information without including the content of the message in the storage target, but including information of a category corresponding to the content of the message in the storage target. The analysis system according to claim 1 or 2.

8. A message retrieval step that retrieves messages sent and received between multiple members belonging to a group, A work history acquisition step to acquire the work history of each of the aforementioned multiple members, Based on the aforementioned messages and work history, an analysis step is performed to analyze the relationships between members, Includes a generation step that generates a network diagram showing the relationships between members based on the analysis results. Analysis method.

9. A message retrieval step that retrieves messages sent and received between multiple members belonging to a group, A work history acquisition step to acquire the work history of each of the aforementioned multiple members, Based on the aforementioned messages and work history, an analysis step is performed to analyze the relationships between members, Based on the analysis results, the computer is instructed to perform a generation step that generates a network diagram showing the relationships between members. program.

Images