Behavioral pattern discrimination device, mobile terminal program, and server program

Abstract

To provide a behavior pattern determination apparatus, a portable terminal program, and a server program capable of improving a way to work.SOLUTION: A behavior pattern determination apparatus 100 includes a plurality of USB beacon communication units 200 mounted on a ceiling or floor, a portable terminal 400 capable of receiving beacons of the USB beacon communication units 200, and a server 500 that acquires reception information on the beacons from the portable terminal 400. The server 500 includes a calculation unit 510 that calculates a position of an owner of the portable terminal 400 from the reception information, and a division unit 520 that performs division into six or more patterns based on a location log which is positional information on the portable terminal 400 calculated by the calculation unit 510.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a behavior pattern discrimination device, a mobile terminal program, and a server program. [Background technology]

[0002] For example, Patent Document 1 (Japanese Patent Application Laid-Open No. 2018-92445) discloses a prediction system and method that can minimize errors in predicted values ​​compared to conventional systems.

[0003] The prediction system and method described in Patent Document 1 is a prediction system that calculates a predicted value related to a prediction target to which prediction for an arbitrary period is applied, and includes a storage device that records multiple pieces of data used to calculate the predicted value, and a control device that has a predetermined calculation model and calculates the predicted value by applying the multiple pieces of data to the calculation model, and the control device changes the calculation model using data determined based on information on the time attributes of each of the multiple pieces of data.

[0004] Furthermore, Patent Document 2 (JP Patent Publication No. 2005-122438) discloses a prediction method, a prediction device, a prediction program, and a recording medium that improve prediction accuracy by processing multiple pieces of prediction data to generate highly accurate prediction data.

[0005] The prediction method described in Patent Document 2 is a prediction method for calculating prediction data relating to future predictions, and includes a prediction procedure for performing predictions using n different prediction methods to calculate n types of prediction data, and a prediction data processing procedure for calculating the average of the n types of prediction data as prediction data.

[0006] Furthermore, Patent Document 3 (JP 2015-46093 A) discloses a system, device, method, program, and recording medium on which the program is recorded that can predict a subject's behavior earlier and more accurately than conventional methods using a simple configuration.

[0007] The behavior prediction system described in Patent Document 3 is a behavior prediction system that predicts the behavior of a subject, and is equipped with a signal receiving means that receives a signal that changes depending on the behavior of the subject, and a behavior prediction means that notifies that the frequency at which the magnitude of the signal received by the signal receiving means or the magnitude of the change in the signal exceeds a predetermined first threshold value has reached or exceeded a predetermined second threshold value.

[0008] Patent Document 4 (Japanese Patent Laid-Open Publication No. 2013-186556) discloses a behavior prediction device that can predict a person's behavior while reflecting the characteristics of each individual.

[0009] The behavior prediction device described in Patent Document 4 is equipped with a video analysis unit that inputs video data of an object, identifies the person, extracts identification information that represents the person's characteristics, analyzes the person's behavior and state from the video data, associates the identifier assigned to the person with the behavior and state and outputs it as analysis information, and associates the person's identifier with the identification information and outputs it as person information, a person information storage unit that stores the person information, an information collection unit that collects condition information that indicates the situation in which the person was photographed and analysis information, an observation information storage unit that stores the condition information and analysis information in association with each other, a rule generation unit that creates rules regarding the person's behavior based on the condition information and analysis information, a rule storage unit that stores the rules, and a rule matching unit that compares the condition information and analysis information collected for a specific person by the information collection unit with pre-created rules related to the person, and generates behavior prediction information using the rules based on the matching results.

[0010] Patent Document 5 (JP Patent Publication No. 2009-151359) predicts the movement of a person in the actual environment, reduces the number of iterations required until the prediction result stabilizes, and achieves both high tracking accuracy and low calculation costs. A moving object tracking device, a moving object tracking method, a moving object tracking program, and a recording medium on which the moving object tracking program is recorded are disclosed.

[0011] The moving object tracking device described in Patent Document 5 is a device that tracks the three-dimensional position, size, and other conditions of a moving object using one or more image input devices such as cameras, and a three-dimensional environment information database storing the three-dimensional structure of the real world measured in advance, the internal and external parameters of the imaging means disposed in the real world, and the behavior history distribution of the target object in the environment; a means for estimating a probability distribution of the target state at each time using the information in the three-dimensional environment information database and the silhouette image; a target state distribution storage means for storing the probability distribution of the target state estimated by the estimation means at each time and the target state with the maximum probability; a means for calculating the target state with the maximum probability at each time from the probability distribution of the target state stored in the target state distribution storage means; and a means for calculating a behavior history distribution from the behavior history distribution stored in the three-dimensional environment information database and the target state calculated by the target state calculation means, and updating the target state distribution at the previous time stored in the target state distribution storage means to the target state distribution at the current time and to the target state with the maximum probability calculated by the target state calculation means, respectively.

[0012] Patent Document 6 (JP Patent Publication No. 2012-43043) discloses an information processing device that prevents seating arrangements that gather together people from the same organization, including people who belong to the same organization but have different behaviors.

[0013] The information processing device described in Patent Document 6 comprises a classification means for classifying personnel in an organization into a first set and a second set based on behavioral information, which is a record of the past behavior of personnel within the organization; a similarity acquisition means for acquiring first sets of other organizations having similar behavioral records of personnel in the first set classified by the classification means; and an arrangement means for arranging seats so that personnel in the similar first sets acquired by the similarity acquisition means are gathered together.

[0014] Patent Document 7 (WO2012 / 096175) discloses a behavior pattern analysis device in which a location information plotting means 81 plots a location information log including a user's measured location and the date and time of measurement in a multidimensional space defined by numerical information representing the measured location and time. A staying point cluster extraction means 82 weights the location information log so that the Euclidean distance in the time direction relative to the location information space is likely to be determined to be close, and clusters the weighted location information logs to extract staying points where the user frequently stays. A movement path cluster extraction means 84 weights the location information log of non-measured points so that the Euclidean distance in the time direction relative to the location information space is likely to be determined to be long, and extracts the user's movement path by clustering the weighted location information logs.

[0015] The behavior pattern analysis device described in Patent Document 7 comprises a location information plotting means for plotting a location information log, which is information including a user's positioning location and positioning date and time, in a multidimensional space defined by numerical information representing the positioning location and time; a stay point cluster extraction means for applying weighting to the location information log so that it is more likely to be determined that the Euclidean distance in the time direction to the location information space, which is a space defined by numerical information representing the positioning location in the multidimensional space, is close, and clustering the weighted location information logs to extract stay points, which are locations where users frequently stay; a non-stay point location information log extraction means for extracting, as non-stay points, a set of location information logs obtained by excluding the location information logs extracted as stay points from the location information logs plotted by the location information plotting means; and a movement path cluster extraction means for applying weighting to the non-stay point location information logs so that it is more likely to be determined that the Euclidean distance in the time direction to the location information space is far, and clustering the weighted location information logs to extract the user's movement path.

[0016] Patent Document 8 (WO2018 / 235361) discloses a mobile terminal that can detect its current indoor location even in an environment where indoor positioning using indoor wireless signals compatible with GPS signals cannot be performed satisfactorily.

[0017] The mobile terminal described in Patent Document 8 is a mobile terminal capable of communicating with at least one indoor location information transmitter that transmits a wireless signal including indoor location information, and at least one access point that emits a beacon signal at regular intervals, and is equipped with a movement distance calculation unit that calculates the distance traveled by the mobile terminal from its own position last detected by the received wireless signal, and an indoor positioning unit that, when the electric field strength when the wireless signal is received is less than a predetermined threshold, transmits the reception strength of the beacon signal received from the access point together with its own movement distance calculated by the movement distance calculation unit to the access point, and sets the location information of the access point received from the access point located near the mobile terminal as its current location. [Prior art documents] [Patent documents]

[0018] [Patent Document 1] JP 2018-92445 A [Patent Document 2] Japanese Patent Application Laid-Open No. 2005-122438 [Patent Document 3] Japanese Patent Application Laid-Open No. 2015-46093 [Patent Document 4] Japanese Patent Application Laid-Open No. 2013-186556 [Patent Document 5] Japanese Patent Application Laid-Open No. 2009-151359 [Patent Document 6] Japanese Patent Application Laid-Open No. 2012-43043 [Patent Document 7] International Publication No. 2012 / 096175 [Patent Document 8] International Publication No. 2018 / 235361 Summary of the Invention [Problem to be solved by the invention]

[0019] The prediction devices described in Patent Documents 1 to 3 are basically for performing prediction calculations. The behavior prediction devices of Patent Documents 4 and 5 only detect and predict personal movements. Patent Document 6 divides the seats into two categories, but this creates a problem because even if the seating arrangement is improved by dividing the seats into two categories, the behavioral patterns are not improved. Patent Document 7 discloses that it generates clusters in which logs with similar times tend to be grouped together, but it has the problem of being unable to classify each individual's location information log and extract their movement routes. As a result, it is impossible to determine how to improve work styles. Regarding Patent Document 8, it is also not possible to determine how working styles should be improved.

[0020] A main object of the present invention is to provide a behavioral pattern discrimination device, a mobile terminal program, and a server program that can improve work styles. [Means for solving the problem]

[0021] (1) According to one aspect, a behavioral pattern discrimination device includes a plurality of beacon transmitting devices installed on a ceiling, a desk, a wall, or a floor, a mobile terminal capable of receiving beacons from the beacon transmitting devices, and a server that acquires received information of the beacons from the mobile terminal, wherein the server has a calculation unit that calculates the location of the owner of the mobile terminal from the received information, and a classification unit that classifies the received information into six or more patterns based on a location log, which is the location information of the mobile terminal calculated by the calculation unit.

[0022] In this case, the behavioral patterns can be divided into six or more types based on the location log, and the working style of the mobile device owner can be determined. In particular, in recent years, there has been a demand for improvements in working styles, and this can be used to improve such working styles.

[0023] (2) In a behavior pattern discrimination device according to a second aspect of the present invention, the classification unit may include at least six types: an office-specialized type, a random office type, an internal movement type, an internal / external balance type, a meeting-specialized type, and an external-specialized type.

[0024] In this case, the owner of the mobile device can easily determine which pattern of working style is closest to them or which pattern they fit into, and can improve their working style.

[0025] (3) The behavior pattern discrimination device according to the third aspect of the present invention is the behavior pattern discrimination device according to the one aspect or the second aspect of the present invention, wherein the server may further include a recording unit that records information on any one of the performance, sales, or achievements of the team to which the owner of the mobile terminal belongs, and a suggestion unit that suggests a behavior pattern to the owner based on the information from the recording unit.

[0026] In this case, if the information on the track record, sales, or achievements of the mobile terminal owner is not good, the suggestion unit can suggest the behavioral pattern of an owner with good information on the track record, sales, or achievements.

[0027] (4) The behavior pattern discrimination device according to the fourth aspect of the present invention is the behavior pattern discrimination device according to the third aspect of the present invention, wherein the calculation unit of the server may further calculate the repetitive behavioral patterns, the continuous stay time in the office area, and the travel distance of the mobile terminal owner.

[0028] As a result, the behavioral patterns of the mobile terminal owner can be determined in more detail.

[0029] (5) The behavior pattern discrimination device according to the fifth aspect of the present invention is the behavior pattern discrimination device according to the fourth aspect of the present invention, wherein the server may further include a selection unit that selects a location from which to acquire a location log, which is location information of the mobile device calculated by the calculation unit.

[0030] In this case, the administrator can set the location where the location log is to be taken. That is, the administrator can select multiple beacon transmitting devices from the map. As a result, the administrator can reliably obtain the information they want.

[0031] (6) A mobile terminal program according to another invention includes, in the behavior pattern discrimination device described in claim 1, a beacon reception process for receiving a beacon from a beacon transmission device, and a received information transmission process for transmitting received information to a server.

[0032] In this case, the received information can be reliably transmitted to the server by the mobile terminal program.

[0033] (7) A server program according to yet another invention is a behavior pattern discrimination device according to claim 1, which includes a received information acquisition process for acquiring received beacon information from a mobile terminal, a calculation process for calculating the location of the owner of the mobile terminal from the received information, and a classification process for classifying the mobile terminal into six or more patterns based on a location log, which is the location information of the mobile terminal calculated by the calculation process.

[0034] In this case, the behavioral patterns can be divided into six or more types based on the location log, and the working style of the mobile device owner can be determined. In particular, in recent years, there has been a demand for improvements in working styles, and this can be used to improve such working styles. [Brief explanation of the drawings]

[0035] [Figure 1] 1 is a schematic diagram illustrating an example of a behavior pattern discrimination device according to an embodiment; [Figure 2] FIG. 1 is a schematic diagram illustrating an example of a floor data collection device. [Figure 3] 10 is a schematic diagram illustrating an example of a communication state between a USB beacon communication unit and a portable terminal. FIG. [Figure 4]This is a schematic diagram for explaining the communication state between the USB beacon communication unit and the mobile terminal from the ceiling side. [Figure 5] FIG. 10 is a schematic diagram for explaining division by a division unit. [Figure 6] FIG. 10 is a schematic diagram for explaining division by a division unit. [Figure 7] FIG. 10 is a diagram showing the location log from the calculation unit divided into six types by the division unit. [Figure 8] FIG. 8 is a schematic diagram showing the state in which the results of the division section shown in FIG. 7 are expanded to each business section. [Figure 9] FIG. 6 is a schematic diagram showing the results of the sub-parameters shown in FIG. 5. [Figure 10] FIG. 2 is a schematic diagram showing an example of a behavior pattern in the behavior pattern discrimination device. [Figure 11] FIG. 10 is a schematic diagram showing an example of an average value of behavioral pattern characteristics. [Figure 12] FIG. 10 is a schematic diagram illustrating an example of an average continuous stay time. [Figure 13] FIG. 10 is a schematic diagram showing an example of an average value of movement distance. DETAILED DESCRIPTION OF THE INVENTION

[0036] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In the following description, the same components are denoted by the same reference numerals. The names and functions of the components are also the same. Therefore, detailed description thereof will not be repeated.

[0037] (Embodiment) FIG. 1 is a schematic diagram showing an example of a behavior pattern discrimination device 100 according to this embodiment, and FIG. 2 is a schematic diagram for explaining an example of a display unit 600 of the behavior pattern discrimination device 100 of FIG.

[0038] As shown in FIG. 1, the behavior pattern discrimination device 100 includes a plurality of USB beacon communication units 200, a recording unit 300, a mobile terminal 400, a server 500, and a display unit 600. The server 500 includes a calculation unit 510, a classification unit 520, a proposal unit 530, and a selection unit 540. The recording unit 300 records and stores performance information 310 of each employee and movement history information 320 of each employee (hereinafter simply referred to as a location log).

[0039] 1, in this embodiment, the server 500 is capable of communicating with the mobile terminal 400. The mobile terminal 400 is also capable of communicating with a plurality of USB beacon communication units 200. The server 500 may be capable of communicating with a plurality of USB beacon communication units 200. In this case, the calculation unit 510 of the server 500 recognizes the position of the mobile terminal 400 by reading the unique information of the plurality of USB beacon communication units 200.

[0040] 2, the mobile terminal 400 communicates with the USB beacon communication unit 200 placed on the ceiling, desk, wall, or floor indoors as needed, and transmits beacon reception information to the server 500. This allows the server 500 to display the location information of the mobile terminal 400 on the display unit 600. Here, when the mobile terminal 400 is moving, the server 500 performs smooth processing using the calculation unit 510 and displays the information on the display unit 600.

[0041] FIG. 3 is a schematic diagram for explaining an example of a communication state between the USB beacon communication unit 200 and the mobile terminal 400. As shown in FIG. 3, multiple USB beacon communication units 200 are installed above the ceiling. The unique IDs (numbers, etc.) of the installed USB beacon communication units 200 are recorded in the recording unit 300. Therefore, the server 500 can recognize which USB beacon communication unit 200 is communicating with the mobile terminal 400 from the information in the recording unit 300.

[0042] Specifically, the USB beacon communication unit 200 is powered by USB and communicates with the mobile terminal 400 via Bluetooth (registered trademark). As a result, it is possible to recognize near which of the plurality of USB beacon communication units 200 the mobile terminal 400 is present. On the other hand, the server 500 may return position information to the mobile terminal 400 based on the radio wave intensity information between the USB beacon communication unit 200 and the mobile terminal 400. Further, as shown in FIG. 2, the server 500 performs display on the display unit 600 based on the radio wave intensity information.

[0043] FIG. 4 is a schematic diagram for explaining the communication state between the USB beacon communication unit 200 and the mobile terminal 400 from the back side of the ceiling.

[0044] As shown in FIG. 4, it is assumed that the USB beacon communication units 200A, 200B, 200C, 200D, 200E, and 200F of the USB beacon communication unit 200 are arranged.

[0045] In this case, the distance from the USB beacon communication unit 200A to the mobile terminal 400 is L2. The distance from the USB beacon communication unit 200B to the mobile terminal 400 is L1. The distance from the USB beacon communication unit 200D to the mobile terminal 400 is L4. The distance from the USB beacon communication unit 200E to the mobile terminal 400 is L3. Since the relationship of the distances is L1 < L2 < L3 < L4, the position of the employee who owns the mobile terminal 400 near the USB beacon communication unit 200B is determined.

[0046] Note that when the distance L is greater than or equal to the distance between adjacent USB beacon communication units 200, it is preferably not used for the determination. This is because the process becomes complicated if the distances between the USB beacon communication units 200C and 200F in FIG. 4 and the mobile terminal 400 are used for the determination.

[0047] (Explanation of parameters in the division unit 520) 5 and 6 are schematic diagrams for explaining the division by the division unit 520. FIG.

[0048] The classification unit 520 of the server 500 in FIG. 1 collected the location logs calculated by the calculation unit 510, converted the aggregated location logs into image data, clustered them using machine learning, and divided them into the following six groups. In this embodiment, the sample is divided into six categories, but the present invention is not limited to this and it is preferable to divide the sample into six or more categories. In other words, it is preferable to divide the sample into any number of categories equal to or greater than six.

[0049] As shown in Figures 5 and 6, if an employee who owns a mobile terminal 400 is in the office space 75% or more during regular working hours, they are set to be a "work-focused type," if they are in the office space 50% to 75% or more, they are set to be a "random work type," and if they are outside 25% to 50% or more and have a high proportion of time spent in conference rooms, they are set to be an "internal movement type."

[0050] In addition, if the proportion of people outside is between 25% and 50% and the proportion of people in conference rooms is low, the person is classified as a "balanced internal / external type." If the person is mostly in conference rooms, the person is classified as a "meeting-focused type." If the person is mostly outside, the person is classified as an "external-focused type." That is, as shown in FIG. 6, the judgment is made based on whether the proportion of conference areas is large or small, and whether the proportion of office areas is large or small. As described above, the dividing unit 520 divides the data into six divisions.

[0051] As shown in FIG. 5, the classification unit 520 may also classify based on patterns of behavior, continuous stay time in the office area, and travel distance. The pattern of behavior was calculated by calculating dissimilarity from the transition of location logs by time and day, and dividing the groups into two groups using the median. When a pattern exists, the dissimilarity is less than 0.6, and when a pattern does not exist, the dissimilarity is 0.6 or more. This median will be discussed later.

[0052] The continuous stay time in the work area was calculated by calculating the average continuous stay time in the work area and dividing it into two groups at the median. Short continuous work time is less than 64 minutes, and long continuous work time is 64 minutes or more. This median will be explained later.

[0053] The average distance traveled per hour was calculated, and floor movement was converted to a 100m movement. The subjects were divided into two groups based on the median value. Light travel is less than 86 meters per hour, while heavy travel is greater than 86 meters per hour. This median is discussed below.

[0054] 7 is a diagram in which the location log from calculation unit 510 is divided into six types by division unit 520. The horizontal axis of FIG.

[0055] 7 shows the location selected by the selection unit 540. For example, the manager uses the selection unit 540 to arbitrarily select a common area of ​​the building, a lounge, a relaxation area, a conference room, an office space, the outside, a concentration booth, a conference room on an office floor, etc. (not shown).

[0056] FIG. 8 is a schematic diagram showing the state in which the results of the division unit 520 shown in FIG. 7 are distributed to each business division.

[0057] As shown in Figure 8, the location log shows that the six types of location data for Divisions 1 to 7 are different for each division: specialized office work, random office work, internal movement, balanced internal and external work, specialized meeting work, and specialized external work. For example, as shown in Figure 8, in Division 1, the specialized office work type is 20%, the random office work type is 45%, the internal movement type is 5%, the balanced internal and external work type is 20%, and the specialized external work type is 10%. In Division 2, the specialized office work type is 20%, the random office work type is 20%, the internal movement type is 40%, the balanced internal and external work type is 15%, and the specialized external work type is 5%.

[0058] Fig. 9 is a schematic diagram showing the results of the sub-parameters shown in Fig. 5. (a) shows whether there is a pattern in behavior, (b) shows whether there is continuous time spent in the office area, and (c) shows whether there is distance traveled. Furthermore, from Figure 9, the proportion of each of the patterns of behavior, continuous time spent in the office area, and distance traveled (taking into account floor changes) can be estimated by dividing them into whether or not they are above a predetermined value (1) or not (0).

[0059] Next, FIG. 10 is a schematic diagram showing an example of a behavior pattern in the behavior pattern discrimination device 100. As shown in FIG.

[0060] As shown in FIG. 10, (a) and (b) show low dissimilarity, while (c) shows high dissimilarity.

[0061] As shown in Figures 8 and 9, it can be seen that the distribution and subparameter trends differ for each business division. In this case, the suggestion unit 530 can compare the location log of a department with good performance with the location log of a department with poor performance from the location log and performance information 310, and give instructions for improvement so that the working style of the department with poor performance becomes similar to the location log of the department with good performance. Similarly, the suggestion unit 530 can compare the subparameters of a department with good performance with the subparameters of a department with poor performance from the subparameters and performance information 310, and give instructions for improvement so that the working style of the department with poor performance is similar to the subparameters of the department with good performance. In other words, we make a suggestion to improve the results of Figure 10(a) and (b), which show the relationship between departments with good and bad performance, to Figure 10(c), which shows the relationship between departments with good performance.

[0062] For example, in Figure 8, if we assume that the performance of the second business division is good and the performance of the third business division is poor, we can instruct the third business division to reduce the number of internal travel-type events, implement a small number of conference-focused events, and further increase the number of external-focused events. Similarly, the same instruction suggestions can be made according to the performance of each individual, ie, the owner of the mobile terminal 400 .

[0063] To determine the pattern of behavior, first, the data is compressed. For example, run-length coding is performed, and the data is coded by dividing it into zones every five minutes. Next, the dissimilarity of each user is calculated, for example, normalized according to the length of the Levenshtein distance.

[0064] FIG. 11 is a schematic diagram showing an example of an average value of behavioral pattern characteristics. As shown in Figure 11, sampling was performed to create a dissimilarity histogram for each day's timeline, which was then divided into two parts at the median.

[0065] FIG. 12 is a schematic diagram showing an example of the average value of the continuous stay time. As shown in Figure 12, sampling was performed to create a dissimilarity histogram for each day's timeline, which was then divided into two parts at the median.

[0066] FIG. 13 is a schematic diagram showing an example of an average value of the movement distance. As shown in Fig. 13, sampling was performed to create the travel distance and variance per hour for each day, and it was found that the median was approximately 86 m. Therefore, in this embodiment, the median was set to 86 m.

[0067] As described above, according to the present invention, by dividing behavioral patterns into six types based on the location log, it is possible to determine the working style of the owner of the mobile terminal 400. In particular, in recent years, there has been a demand for improvements in working styles, and this can improve such working styles. Furthermore, by comparing the behavioral patterns with the business performance, it is possible to give advice on how to work to departments or owners of mobile terminals 400 with poor performance.

[0068] In this embodiment, the plurality of USB beacon communication units 200 correspond to "plurality of beacon transmitting devices", the mobile terminal 400 corresponds to "mobile terminal", and the server 500 corresponds to "server". Furthermore, the calculation unit 510 corresponds to the "calculation unit", the division unit 520 corresponds to the "division unit", the behavior pattern discrimination device 100 corresponds to the "behavior pattern discrimination device", and the recording unit 300 corresponds to the "recording unit". Furthermore, the suggestion unit 530 corresponds to the "suggestion unit", the selection unit 540 corresponds to the "selection unit", the program built into the mobile terminal 400 corresponds to the "mobile terminal program", and the program of the server 500 corresponds to the "server program".

[0069] Although a preferred embodiment of the present invention has been described above, the present invention is not limited thereto. It will be understood that various other embodiments can be made without departing from the spirit and scope of the present invention. Furthermore, although the actions and effects of the configuration of the present invention are described in this embodiment, these actions and effects are merely examples and do not limit the present invention. [Explanation of symbols]

[0070] 100 Behavioral pattern discrimination device 200 Multiple USB beacon communication units 300 Recording Unit 400 mobile devices 500 servers 510 Calculation Unit 520 Division 530 Proposal Department 540 Selection Section

Claims

1. A plurality of beacon transmitting devices installed on a ceiling, a desk, a wall, or a floor; a mobile terminal capable of receiving a beacon from the beacon transmitting device; a server that acquires reception information of the beacon from the mobile terminal, the server includes a calculation unit that calculates the location of the owner of the mobile terminal from the received information; A behavioral pattern discrimination device having a classification unit that classifies patterns into at least six types, including office-specific type, random office type, internal movement type, balanced internal / external type, meeting-specific type, and external-specific type, based on a location log, which is the location information of the mobile terminal calculated by the calculation unit, and that classifies whether the behavior has a repetitive pattern, the length of continuous stay in the office area, and the length of travel distance, based on temporal and positional changes in the location log.

2. The server includes a recording unit that records information on the performance, sales, or achievements of the team to which the owner of the mobile device belongs; a suggestion unit that suggests a behavior pattern to the owner based on information from the recording unit, 2. The behavioral pattern discrimination device of claim 1, wherein the suggestion unit proposes improvements to working styles based on a correlation between the classification of each team based on the location log and the classification based on temporal and positional changes in the location log and any one of the information on performance, sales, or achievements.

3. 3. The behavior pattern discrimination device according to claim 1, wherein the server further includes a selection unit that selects a location from which a location log, which is the location information of the mobile device calculated by the calculation unit, is to be acquired.

4. 2. A mobile terminal program for causing a computer of a mobile terminal of the behavior pattern discrimination device according to claim 1 to execute the following processes, the following processes comprising: a beacon receiving process for receiving the beacon from the beacon transmitting device; a received information transmitting process for transmitting the received information to the server.

5. 2. A server program for causing a server computer of the behavior pattern discrimination device according to claim 1 to execute the following processes, the following processes comprising: a reception information acquisition process for acquiring the reception information of the beacon from the mobile terminal; a calculation process for calculating the location of the owner of the mobile terminal from the received information; A server program including a classification process for classifying into six or more patterns including at least six types, namely, office-specific type, random office type, internal movement type, balanced internal / external type, meeting-specific type, and external-specific type, based on a location log, which is the location information of the mobile terminal calculated by the calculation process, and for classifying whether or not there is a repetitive pattern of behavior, the length of continuous stay in the office area, and the length of travel distance, based on temporal and positional changes in the location log.

Images