Information processing unit, information processing system, information processing method and program

Abstract

To predict a condition of a subject by using chaotic index values.SOLUTION: An information processing unit according to an embodiment includes: a voice acquisition part; a chaos analysis part; a normal range calculation part; and a tendency prediction part. The voice acquisition part acquires plural voice data uttered by a subject in a predetermined period and satisfying a predetermined condition. The chaos analysis part executes a chaos analysis of the sequential plural voice data and calculates respective chaotic index values. The normal range calculation part statistically processes the chaotic index values and calculates a normal range of the chaotic index values. The tendency prediction part predicts a condition of the subject on the basis of transition of the normal range.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to an information processing device, an information processing system, an information processing method, and a program. [Background technology]

[0002] Patent Document 1 discloses an autonomic nervous state evaluation system that evaluates the state of a subject's autonomic nervous system from a CEM value, which is a chaos theoretical index value calculated from the subject's voice data. In Patent Document 1, collected voice data of the subject is converted into digital voice data, and the digital voice data in the pitch frequency band is extracted using a filter to calculate the CEM value. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 5812265 Summary of the Invention [Problem to be solved by the invention]

[0004] In recent years, the number of patients with mental illnesses has been steadily increasing, and a shift from "treatment after onset of illness" to "preventive medicine at the pre-disease stage" has attracted attention in various industries. In addition to an ultra-aging society and a decrease in the working population, chronic stress caused by infectious diseases and other factors is a disease risk that cannot be ignored. For this reason, it is desirable to predict the condition of subjects using chaos theoretical index values.

[0005] In view of the above-mentioned problems, an object of the present disclosure is to provide an information processing device, an information processing system, an information processing method, and a program capable of predicting the state of a subject by using a chaos theoretical exponent value. [Means for solving the problem]

[0006] An information processing device according to one embodiment of the present disclosure includes a voice acquisition unit that acquires a plurality of pieces of voice data uttered by a subject, which satisfy a predetermined condition and are generated during a predetermined period of time; a chaos analysis unit that performs chaos analysis of the plurality of pieces of time-series voice data and calculates chaos theoretical exponent values, respectively; a normal range calculation unit that performs statistical processing of the chaos theoretical index values ​​and calculates a normal range of the chaos theoretical index values; and a tendency prediction unit that predicts a state of the subject based on a transition of the normal range.

[0007] An information processing system according to one embodiment of the present disclosure includes a voice acquisition unit that acquires a plurality of pieces of voice data uttered by a subject, which satisfy a predetermined condition and are generated during a predetermined period of time; a chaos analysis unit that performs chaos analysis of the plurality of pieces of time-series voice data and calculates chaos theoretical index values, respectively; a normal range calculation unit that performs statistical processing of the chaos theoretical index values ​​and calculates a normal range of the chaos theoretical index values; and a tendency prediction unit that predicts a state of the subject based on a transition of the normal range.

[0008] An information processing method according to one aspect of the present disclosure includes a process in which a computer acquires a plurality of pieces of voice data uttered by a subject, which satisfy a predetermined condition and are generated during a predetermined period of time, a process in which a chaos analysis is performed on the plurality of pieces of time-series voice data to calculate respective chaos theoretical exponent values, a process in which a statistical process is performed on the chaos theoretical exponent values ​​to calculate a normal range of the chaos theoretical exponent values, and a process in which a state of the subject is predicted based on a transition of the normal range.

[0009] A program according to one embodiment of the present disclosure causes a computer to execute the following processes: acquiring a plurality of pieces of voice data uttered by a subject, satisfying a predetermined condition, and generated during a predetermined period of time; performing chaos analysis of the plurality of pieces of time-series voice data to calculate respective chaos theoretical exponent values; performing statistical processing of the chaos theoretical exponent values ​​to calculate a normal range of the chaos theoretical exponent values; and predicting a state of the subject based on a transition of the normal range. Effect of the Invention

[0010] According to the present disclosure, it becomes possible to predict the state of a subject using chaos theoretical index values. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating a configuration of an information processing device according to the present disclosure. [Diagram 2] 1 is a flow diagram illustrating the flow of an information processing method according to the present disclosure. [Diagram 3] FIG. 1 is a diagram illustrating a configuration of an information processing system according to the present disclosure. [Figure 4] 1 is a diagram illustrating an overall configuration of an information processing system according to the present disclosure. [Diagram 5] FIG. 5 is a diagram showing a configuration of an employee terminal in FIG. [Figure 6] FIG. 5 is a diagram illustrating a configuration of a server in FIG. [Figure 7] 1 is a graph illustrating the normal range of CEM values. [Figure 8] 13 is a graph illustrating prediction of a subject's condition based on the transition of the normal range of CEM values. [Figure 9] 1 is a graph illustrating the deviation rate calculated from the normal range of CEM values. [Figure 10] 5 is a diagram showing a flow of information processing by the information processing system of FIG. 4. [Figure 11] 1 is a diagram illustrating an overall configuration of an information processing system according to the present disclosure. [Figure 12] FIG. 12 is a diagram showing the configuration of an employee terminal in FIG. [Figure 13] 12 is a diagram illustrating a configuration of a disclosure destination terminal in FIG. 11. [Figure 14] FIG. 12 is a diagram illustrating a configuration of a server in FIG. [Figure 15] FIG. 2 is a diagram showing a flow of outsourcing a delivery operation requested from a first carrier by a shipper to a second carrier in the information processing system of the present disclosure. [Figure 16] 1 is a diagram illustrating an overall configuration of an information processing system according to the present disclosure. [Figure 17]FIG. 17 is a diagram illustrating a functional configuration of the employee terminal of FIG. 16. [Figure 18] FIG. 17 is a diagram illustrating a functional configuration of the management terminal of FIG. 16. [Figure 19] FIG. 17 is a diagram illustrating a functional configuration of the server in FIG. 16. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[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, and duplicated descriptions will be omitted as necessary for clarity of explanation.

[0013] The number of patients with mental illness is steadily increasing, and there is a need to shift from "treatment medicine after onset" to "preventive medicine at the pre-illness stage." Mental illnesses are preventable through lifestyle habits and appropriate stress care, but because they are invisible diseases, it is extremely difficult to make the affected person, their superiors, and other related parties aware of them at the pre-illness stage. People involved in staff care, such as corporate human resources and general affairs, industrial physicians, and public health nurses, have also pointed out that it is difficult to shift from treatment therapy to preventive therapy.

[0014] As we enter a super-aging society, this issue is not limited to companies, but is also a familiar issue in the lives of ordinary consumers. For example, there is a need for preventive medical care for mental illnesses in elderly people living alone, single-person households, and families who look after elderly family members far away.

[0015] In Patent Document 1, a feature (CEM value) indicating the activity of the cerebral neocortex is extracted from a spoken voice or a recorded voice. Since the cerebral neocortex is closely related to the control of the autonomic nervous system (sympathetic nerves / parasympathetic nerves), its activity state is useful information for understanding the state of the autonomic nervous system.

[0016] Because the relationship between autonomic nervous system disorders and mental illness is already known, we believe that by utilizing voice, a simple technology that does not require specialized measuring equipment, it is possible to easily learn one's own condition and that it can be applied to assessing the risk of developing mental illness at the pre-illness stage.

[0017] However, since CEM values ​​vary greatly from person to person and are affected by sound collection devices such as microphones in addition to the activity of the neocortex, there is no standard value that is common to everyone. Therefore, it was difficult to determine the level of brain activity from the CEM value and predict the condition of the subject using only the prior art. The present inventors have devised the following configuration example in order to realize "preventive medicine at the pre-disease stage" using chaos theoretical index values.

[0018] An example of the configuration of the information processing device 1 will be described with reference to Fig. 1. The information processing device 1 calculates a chaos theoretical index value using voice data collected from a subject, and predicts and evaluates the state of the subject using the chaos theoretical index value. The information processing device 1 first acquires a plurality of voice data and performs a process of calculating a normal range of the chaos theoretical index value (normal range calculation process). After that, the information processing device 1 performs a process of predicting the state of the subject using the transition of the normal range of the calculated chaos theoretical index value (trend prediction process).

[0019] As shown in FIG. 1, the information processing device 1 includes a voice acquisition unit 2, a chaos analysis unit 3, a normal range calculation unit 4, and a trend prediction unit 5. First, to execute the normal range calculation process, voice data of the subject is acquired. The voice acquisition unit 2 acquires a plurality of voice data uttered by the subject, which satisfy a predetermined condition and are generated during a predetermined period. The predetermined condition may include, for example, an environmental condition when the voice data is collected, a condition related to the content of the subject's utterance collected as voice data, and a time condition for acquiring the voice data.

[0020] The environmental conditions may include a sound collecting device such as a microphone, and the surrounding environment when the subject speaks. It is preferable that the voice data is collected using the same sound collecting device such as a microphone. This makes it possible to suppress the deviation of the chaos theoretical index value due to the difference in the sound collecting device. Note that the voice data is not limited to the same sound collecting device, and may be collected using sound collecting devices having similar characteristics.

[0021] The information processing device 1 shown in FIG. 1 can perform various communications with external devices via a network. Specifically, the information processing device 1 can be connected to a terminal device (not shown) equipped with the above-mentioned sound collecting device via a communication line such as the Internet. However, the communication line is not limited to the Internet, and may be a combination of the Internet and other communication lines, or may be a communication line other than the Internet. As a communication method, for example, wireless communication or wired communication such as 4G (Generation), 5G, local 5G, Wi-Fi (registered trademark), and LTE (Long Term Evolution) may be used. Note that the communication method is not limited to these examples.

[0022] In addition, it is preferable that the voice acquisition unit 2 acquires a plurality of voice data of the same utterance contents uttered by the subject. This can reduce the fluctuation of the chaos theoretical exponent value, and it becomes possible to calculate the normal range more accurately. However, as long as it is possible to acquire a sufficient amount of voice data for calculating the normal range, the utterance contents do not necessarily have to be the same, and may be different.

[0023] The time for acquiring the voice data may be a specific time period when the body is not under stress, such as before work starts (morning), during a break (afternoon), or after work ends (evening). Note that these time periods are merely a guideline, and the voice acquisition unit 2 may acquire voice data uttered at any number of different times. It is known that the chaos theoretical index value varies depending on the subject's degree of fatigue, etc., so the subject may appropriately change the time for inputting the voice data, taking into account his or her own degree of fatigue, etc.

[0024] Furthermore, the voice acquisition unit 2 acquires voice data generated during a predetermined period. The multiple voice data acquired by the voice acquisition unit 2 become basic data for calculating the normal range, so it is necessary to have the amount of data necessary for analysis. When acquiring voice data for the first time without any accumulated voice data of the subject, the voice acquisition unit 2 can acquire multiple voice data three times a day, in the morning, afternoon, and evening, for about two weeks, for example. The period for acquiring voice data can be changed as appropriate.

[0025] The chaos analysis unit 3 performs chaos analysis on a plurality of pieces of time-series voice data and calculates the chaos theoretical exponent value for each piece. For the calculation of the chaos theoretical exponent value, for example, the technique described in Patent Document 1 can be used. For example, the chaos analysis unit 3 can convert the input analog voice data into digital voice data, extract voice data in the pitch frequency band from the digital voice data, and process the extracted voice data to calculate the chaos theoretical exponent value.

[0026] The pitch frequency is a frequency determined by the vibration of the subject's vocal cords, and is information excluding the influence of the shape of the vocal tract from the vocal cords to the lips. The filter for extracting the voice data in the pitch frequency band may use any principle, such as a filter that passes only data in the pitch frequency band or a filter that attenuates data outside the pitch frequency band.

[0027] The chaos theory index value is an index value representing the spread of an attractor created from chaotic time series data. The chaos theory index value may be, for example, the maximum Lyapunov exponent described in M. Sano, Y. Sawada, “Measurement of the Lyapunov Spectrum from a Chaotic Time Series”, The American Physical Society, USA, 1985, Vol. 55 No. 10, pp. 1082-1085. The chaos theory index value may also be a macro brain activity index value calculated by the SiCECA algorithm described in Kakuichi Shiomi, “Brain Function Model Considered from Speech Analysis”, Collection of Research Papers on Kansei Engineering, Japan, Japan Society of Kansei Engineering, February 2004, Vol. 4, No. 1, pp. 3-12.

[0028] In the following description, the chaos theoretical index value is assumed to be a CEM value defined by the SiCECA algorithm. The chaos analysis unit 3 calculates the CEM value from the voice data of the pitch frequency band based on a calculation procedure for calculating the macro brain activity index by the SiCECA algorithm. The chaos analysis unit 3 outputs the calculated CEM value to the normal range calculation unit 4. The chaos analysis unit 3 can output data in an extraction format (for example, CSV format) including the date and time when the voice data for each subject was collected and the calculated CEM value to the normal range calculation unit 4.

[0029] The normal range calculation unit 4 performs statistical processing of the CEM values ​​to calculate the normal range of the CEM values. The method of calculating the normal range will be described in detail later. The information on the normal range includes the "average value" and "standard deviation" of the CEM values ​​for two weeks used to calculate the normal range. The information on the normal range is input to the trend prediction unit 5.

[0030] The trend prediction unit 5 predicts the subject's condition based on the transition of the normal range. The trend prediction unit 5 can, for example, calculate a moving average of the time series normal range and linearly approximate the moving average to calculate the future normal range. In the present disclosure, since the normal range is calculated from two weeks (14 days) of voice data, the trend prediction unit 5 can, for example, calculate a 14-day moving average of the upper and lower limits of the time series normal range. Note that the moving average of the normal range can be calculated by adding a CEM value calculated from new voice data and removing the oldest CEM value.

[0031] Furthermore, the trend prediction unit 5 can predict the future state of the subject by linearly approximating the moving average of the time series average value of the CEM value for one day (daily average) and comparing it with the future normal range. As an example, the trend prediction unit 5 can classify the subject into three classes: "normal state," "tension state," and "fatigue state." If the CEM value for judgment is within the "normal range," i.e., if the CEM value is a value between the lower limit and the upper limit of the normal range, the trend prediction unit 5 judges that the subject is in the "normal state."

[0032] It is known that the heart rate, pulse rate, sweat rate, and eye movement increase when the sympathetic nerves of the autonomic nerves are dominant, and decrease when the parasympathetic nerves are dominant. In contrast, according to Patent Document 1, it is known that the CEM index value CEM decreases when the sympathetic nerves are dominant, and increases when the parasympathetic nerves are dominant. Therefore, for example, after calculating the normal range, if the newly calculated CEM value for judgment is smaller than the lower limit of the normal range and is equal to or larger than a predetermined threshold value smaller than the lower limit, it may be determined that the subject is in a "stressed state." Also, if it is smaller than the predetermined threshold, it may be determined that the subject is in a "fatigued state." Note that the present invention is not limited to this example, and the subject's state may be predicted based on other criteria.

[0033] Next, the processing performed by the information processing device 1 will be described with reference to Fig. 2. First, the information processing device 1 acquires a plurality of pieces of voice data uttered by the subject, which satisfy a predetermined condition and are generated during a predetermined period (S11). Next, the information processing device 1 performs chaos analysis on the plurality of pieces of time-series voice data and calculates the CEM values ​​for each (S12). Then, the information processing device 1 performs statistical processing on the CEM values ​​and calculates the transition of the normal range of the CEM values ​​(S13). After that, the information processing device 1 predicts the state of the subject based on the transition of the normal range (S14).

[0034] In this way, according to the present disclosure, by collecting a predetermined amount of voice data that meets a predetermined condition, it is possible to calculate a normal range specific to an individual. Furthermore, it is possible to predict the state (normal state / stress state / fatigue state) of the subject using this normal range.

[0035] The information processing device 1 includes a processor, a memory, and a storage device, which are not shown in the figure. The storage device stores a program that causes a computer to execute each of the above-mentioned processes. The processor loads the program from the storage device into the memory and executes the program. In this way, the processor realizes the functions of the voice acquisition unit 2, the chaos analysis unit 3, the normal range calculation unit 4, and the trend prediction unit 5.

[0036] Each of the components of the information processing device 1 may be realized by dedicated hardware. Also, some or all of the components of each device may be realized by a general-purpose or dedicated circuit, processor, or a combination of these. These may be configured by a single chip, or may be configured by multiple chips connected via a bus. Some or all of the components of each device may be realized by a combination of the above-mentioned circuits, etc., and a program. Also, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field-Programmable Gate Array), a quantum processor (quantum computer control chip), etc. may be used as a processor.

[0037] In addition, when some or all of the components of the information processing device 1 are realized by a plurality of devices, circuits, etc., the plurality of devices, circuits, etc. may be centrally arranged or distributed. FIG. 3 is a block diagram showing the configuration of an information processing system 101 according to the first embodiment. As shown in FIG. 3, the information processing system 101 includes a voice acquisition unit 102, a chaos analysis unit 103, a normal range calculation unit 104, and a trend prediction unit 105. As described above, the detailed operation of each component of the information processing system 101 corresponds to the operation of each component of the information processing device 1. The devices, circuits, etc. that realize each component of FIG. 3 may be realized as a client-server system, a cloud computing system, etc., each of which is connected via a communication network. In addition, the function of the information processing device 1 may be provided in a SaaS (Software as a Service) format.

[0038] A configuration example of the information processing system 100 will be described with reference to Fig. 4. Here, as an example, an example will be described in which the information processing system 100 provides preventive medical care to employees at the pre-disease stage by using voice data acquired from employees belonging to a company as subjects. As shown in Fig. 4, the information processing system 100 includes a server 10 and an employee terminal 20. The server 10 and the employee terminal 20 are each connected via a network N. Here, the network N is a wired or wireless communication line, for example, the Internet.

[0039] Here, the information processing system 100 has (1) a function to calculate the normal range of an employee's CEM value (normal range calculation function), and (2) a function to predict the subject's condition using the trend of the calculated normal range of the CEM value (trend prediction function).

[0040] <Employee terminal 20> The employee terminal 20 is an information terminal used by an employee to transmit and receive data to and from the server 10 via the network N by wireless communication. The employee terminal 20 is, for example, a personal computer, a tablet, a smartphone, etc. As described above, the employee terminal 20 is capable of acquiring voice data of the employee. FIG. 5 is a block diagram showing the configuration of the employee terminal 20 in FIG. 4.

[0041] The employee terminal 20 includes a microphone 21, a storage unit 22, a memory 23, a communication unit 24, an input / output unit 25, and a processing unit 26. The microphone 21 is a sound collection device that collects voice data of employees in response to the control of the processing unit 26. The voice data is collected when the employee speaks into the microphone 21. As described above, it is desirable for an employee to satisfy certain conditions when collecting voice data.

[0042] The predetermined conditions may include environmental conditions when collecting voice data, conditions related to the contents of the subject's speech collected as voice data, and time conditions for acquiring the voice data. It is preferable that employees use the same microphone 21 provided on the employee terminal 20. When collecting the voice data, the employees can utter the same contents. The time for acquiring the voice data may be a specific time period when the body is not under strain, such as before work starts (morning), during a break (afternoon), or after work ends (evening). In addition, the employees can collect the voice data multiple times, for example, three times a day in the morning, afternoon, and evening, for about two weeks. The conditions for collecting the voice data may be changed as appropriate.

[0043] The storage unit 22 is an example of a storage device including a non-volatile memory such as a flash memory or a solid state drive (SSD), etc. The storage unit 22 stores a program in which processes including a process of transmitting voice data for predicting the state of an employee are implemented.

[0044] The memory 23 is a volatile storage device such as a RAM (Random Access Memory), and is a storage area for temporarily holding information during operation of the processing unit 26. The communication unit 24 is a communication interface with the network N. The communication unit 24 may establish a short-range wireless communication connection and perform communication. Here, various standards such as Bluetooth (registered trademark), BLE (Bluetooth Low Energy), and UWB (Ultra-Wide Band) can be applied to the short-range wireless communication.

[0045] The input / output unit 25 may include a display device such as a screen, and an input device such as a keyboard. The input / output unit 25 may be a touch panel in which the display device and the input device are integrated.

[0046] The processing unit 26 is a processor that controls the hardware of the employee terminal 20. The processing unit 26 loads a program from the storage unit 22 into the memory 23 and executes it. As a result, the processing unit 26 realizes the functions of a generation processing unit 261 and a transmission processing unit 262.

[0047] The generation processing unit 261, for example, records the voice of an employee for a predetermined period of time and generates voice data for providing preventive medical care. The generation processing unit 261 may perform processing such as converting input analog voice data into digital voice data and extracting voice data in a pitch frequency band from the digital voice data. The generation processing unit 261 can record the collection time of the voice data together with the voice data. The transmission processing unit 262 transmits the voice data generated by the generation processing unit 261 to the server 10. The transmission processing unit 262 may transmit the terminal ID of the employee terminal 20 and the employee ID together with this information. In the following description, it is assumed that the employee ID and the voice data are linked.

[0048] <Server 10> The server 10 is an information processing device that realizes a normal range calculation function and a trend prediction function. The server 10 may be composed of multiple servers, and each functional block may be realized by multiple computers. FIG. 6 is a block diagram showing the configuration of the server 10 in FIG. 4. The server 10 includes a storage unit 11, a memory 12, a communication unit 13, and a processing unit 14. The storage unit 11 is an example of a storage device such as a hard disk or a flash memory. The storage unit 11 stores a program 111 and an employee information DB 112. The program 111 is a computer program in which some of the normal range calculation function, trend prediction function, etc. are implemented.

[0049] The employee information DB 112 is a database that manages various information including voice data of employees belonging to a company. In the example shown in Fig. 6, the employee information DB 112 manages employee IDs and voice data of employees in association with each other.

[0050] The memory 12 is a volatile storage device such as a RAM, and is a storage area for temporarily holding information when the processing unit 14 is operating. The communication unit 13 is a communication interface with the network N. The processing unit 14 is a processor that controls each component of the server 10. The processing unit 14 loads a program 111 from the storage unit 11 into the memory 12, and executes the program 111. In this way, the processing unit 14 realizes the functions of a voice acquisition unit 141, a chaos analysis unit 142, a normal range calculation unit 143, a trend prediction unit 144, a deviation rate calculation unit 145, a graph generation unit 146, and a transmission processing unit 147.

[0051] The voice acquisition unit 141 acquires a plurality of voice data generated over a predetermined period from the employee terminal 20 described above. An employee may speak to the employee terminal 20 at any time, such as before starting work, to generate voice data including spoken voice. The voice data generated by the employee terminal 20 is registered in the employee information DB 112 together with the employee ID. The voice acquisition unit 141 may also sequentially acquire voice data measured at a predetermined cycle.

[0052] The chaos analysis unit 142 performs chaos analysis on multiple pieces of time-series voice data and calculates the CEM value for each. For the calculation of the CEM value, for example, the technique described in Patent Document 1 can be used. As a result, CEM values ​​for two weeks are obtained three times a day in advance. Since CEM values ​​vary from person to person, it is not possible to tell whether something is normal or abnormal by looking at the CEM value alone. Therefore, in the daily analysis, the normal range of the CEM value for the past 14 days is estimated and normal / abnormal is visualized.

[0053] The normal range calculation unit 143 performs statistical processing of the CEM values ​​for two weeks and calculates the normal range for each subject. Fig. 7 is a graph explaining the normal range of the CEM value. Here, in order to calculate the normal range, the CEM values ​​calculated from the voice data three times a day for two weeks from January 1st to January 14th are used.

[0054] In the graph of Figure 7, the average of the CEM values ​​taken three times a day (daily average) is indicated by the legend ●. If the average of the CEM values ​​from January 1st to January 14th is μ and the standard deviation of the CEM values ​​from January 1st to January 14th is σ, the normal range NR on January 15th can be estimated using the following formula. NR = μ ± k × σ Here, k is an arbitrary coefficient. The coefficient k can be determined, for example, based on the results of a verification test carried out in advance. For example, the results of a verification test carried out on the amount of decrease in CEM value when an employee stays up all night show that the amount of decrease in CEM value is 1.5 standard deviations.

[0055] So, as an example, NR=μ±1.5×σ It can be said that: That is, the upper limit of the normal range on January 15th is μ+1.5×σ, and the lower limit is μ-1.5×σ. In FIG. 7, the upper limit of the normal range is indicated by the legend ■, and the lower limit of the normal range is indicated by the legend ▲. Information about the normal range on January 15th is output to the trend prediction unit 144, the deviation rate calculation unit 145, and the graph generation unit 146. The output information about the normal range includes the "average value" and "standard deviation" of the CEM values ​​when the normal range was calculated.

[0056] -Daily analysis processing From the third week (the 15th day) onwards, it is possible to judge the level of brain activity of an employee. For example, on January 15th, the employee speaks at any time to generate voice data for judgment. Chaos analysis unit 142 calculates a CEM value from the voice data for judgment. The CEM value calculated here is used as data for calculating a new normal range and data for judging the state of the employee on January 15th. The CEM value for judgment is input to normal range calculation unit 143, trend prediction unit 144, deviation rate calculation unit 145 and graph generation unit 146.

[0057] The graph generating unit 146 plots the CEM value for judgment on a graph showing the normal range, and visualizes whether the employee belongs to a normal state, a stressed state, or a fatigued state class. If an employee is at high risk of developing an abnormal state, the transmission processing unit 147 can transmit information about preventive medical care to the employee terminal 20 of the employee in question, which promotes care in advance.

[0058] The normal range calculation unit 143 can update the normal range by using the CEM values ​​for judgment. For example, the normal range calculation unit 143 can calculate the normal range for January 16th by using the CEM values ​​for January 2nd to January 15th.

[0059] -Trend prediction processing The trend prediction unit 144 predicts the state of the employee based on the transition of the normal range. For example, the CEM value one week later can be predicted from the trend of the CEM value over two weeks, and the risk of the employee falling into an abnormal state (fatigue or tension) can be determined. The trend prediction unit 144 calculates the moving averages of the daily average and the upper and lower limits of the normal range shown in FIG. 7. Methods for calculating the moving average include the simple moving average method, the weighted moving average method, and the exponential smoothing method. By the trend prediction unit 144 calculating the moving average in this way, the graph can be smoothed, and the prediction accuracy can be improved.

[0060] Here, the trend prediction unit 144 calculates a simple moving average of the CEM values ​​for the most recent 14 days. Fig. 8 is a graph for explaining prediction of a subject's condition based on the transition of the normal range of the CEM value. In Fig. 8, the 14-day moving average of the daily average shown in Fig. 7 is indicated by the legend ●, the 14-day moving average of the upper limit of the normal range is indicated by the legend ■, and the 14-day moving average of the lower limit of the normal range is indicated by the legend ▲.

[0061] By performing linear regression analysis on the moving average of the daily average and the upper and lower limits of the normal range, it is possible to extend the approximation curve of the graph beyond the actual measured value and predict future values. In this way, by predicting future CEM values ​​from the calculated normal range, it is possible to visualize symptoms of illness in employees and determine risk at the pre-illness stage.

[0062] -Comparison process Since the CEM value varies greatly from person to person, the CEM value itself is not suitable for comparison with others. Therefore, the deviation rate calculation unit 145 calculates a deviation rate indicating "how much the CEM value of each individual deviates from the normal range." The deviation rate calculation unit 145 calculates the deviation rate from the normal range of the CEM value of the subject's voice data generated at a predetermined time point after the period when the voice data for calculating the normal range was acquired.

[0063] For example, the CEM value on January 15 is c, and the upper limit of the normal range on January 15 is th. max , the lower limit of the normal range on January 15th is th min If the standard deviation of the CEM values ​​from January 1st to January 14th is σ, the deviation rate DR on January 15th can be calculated using the following formula.

number

[0064] Figure 9 is a graph that explains the deviation rate calculated from the normal range of CEM values. In Figure 9, Person A's deviation rate is indicated by the legend ■, and Person B's deviation rate is indicated by the legend ●. Figure 9 shows that Person A was closer to the lower limit of the normal value on January 15th, and therefore was relatively more tired than Person B. In this way, by calculating the deviation rate of CEM values, it is possible to compare an employee's condition with others, making it easier to identify employees who should be given priority support.

[0065] 10 is a diagram showing the flow of an information processing method by the information processing system 100. First, the employee terminal 20 generates a plurality of voice data from the contents of an employee's speech for a predetermined period that satisfies a predetermined condition (S101), and outputs the plurality of voice data to the server 10 (S102). The server 10 performs chaos analysis on the plurality of acquired time-series voice data, and performs calculation processing of the respective CEM values ​​(S103). The server 10 also performs statistical processing of the CEM values, and calculates the normal range (S104).

[0066] After the normal range is calculated, the employee terminal 20 generates voice data for determination (S105) and outputs the voice data for determination to the server 10 (S106). The server 10 calculates a CEM value from the voice data for determination (S107). Thereafter, the server 10 performs a daily analysis process (S108), a trend prediction process (S109), and a comparison process (S110).

[0067] In the daily analysis process, the server 10 plots the CEM values ​​for judgment on a graph showing normal ranges to visualize the employee's condition. In the daily analysis process, the server 10 can also update the normal ranges using the CEM values ​​for judgment.

[0068] In the trend prediction process, the condition of an employee can be predicted based on the transition of the normal range. In the comparison process, the deviation rate of each employee's CEM value from the normal range can be calculated, and the conditions of the employees can be compared. The order in which the daily analysis process, trend prediction process, and comparison process are performed is not particularly limited, and they may be performed simultaneously. If an employee is at high risk of developing an abnormal condition, information on preventive medical care to encourage care in advance can be sent to the employee terminal 20 of the employee (S111).

[0069] According to the present disclosure, it is possible to realize the following items. (1) By collecting voice data that meets certain conditions, it is possible to calculate a normal range that is optimized for each individual. (2) Based on the normal range calculated in (1), each time the CEM value is measured, it becomes possible for the employee to recognize his or her own state (normal state / stressed state / fatigued state, etc.). (3) The state of an employee can be predicted based on the normal range and daily changes in the CEM value in (2). For example, if the normal range shows a downward trend, the information processing system 100 can inform the employee that he or she is becoming fatigued and encourage him or her to take a break, etc.

[0070] In this way, the information processing system 100 can use voice data caused by vital signs and evaluate the state of mental illness or fatigue based on the normal range optimized for each individual, making it possible to encourage awareness through daily condition management. The information processing system 100 can also be applied to detecting symptoms of illness at the pre-disease stage. The information processing system 100 can make it possible to view CEM values ​​that are difficult to interpret as graphical information, making it possible to give employees an opportunity to change their behavior.

[0071] 11 is a configuration example for selecting a disclosure destination of a report on an employee's status predicted from voice data acquired from the employee. For an example of selecting a disclosure destination of a report, refer to the contents described in Patent Application No. 2023-014929.

[0072] The information processing system 100 shown in FIG. 11 can have the following functions. (1) A function for managing the health status of employees (health management function) (2) A function to grasp employees' engagement, such as their motivation, attachment, and feelings toward their work (this will be referred to as the "engagement grasping function") (3) A function for generating financial soundness information about the company to which an employee belongs based on the reports of multiple subjects (hereinafter referred to as a financial soundness evaluation function)

[0073] The health management function may include the following functions: (a) A function for generating advice information according to an employee's health condition (referred to as an advice information generation function) (b) A function for creating reports linking employee health status with information about employees (report creation function) (c) A function to allow employees to choose to whom the report will be disclosed (this will be called the disclosure permission function) (d) A function to notify employees of the recommendation for consultation based on the report (recommended function)

[0074] Here, the employee's health status includes the employee's status predicted using the CEM value calculated from the above-mentioned voice data. Engagement is based on the employee's subjective mental and psychological state, and is quantified and visualized by an engagement survey that is periodically administered to employees. The engagement survey covers such items as relationships with colleagues, relationships with superiors, recognition and interest, health, self-growth, philosophy / strategy / business, and job duties.

[0075] In the following, an example will be described in which the health of employees is managed comprehensively, that is, from both the physical and mental aspects, and a disclosure destination for reports on employees is selected, using the health management function of the information processing system 100. In addition, the information processing system 100 can provide the management of a company with health information that allows them to get an overview of the health of the company to which the employees belong, using the engagement understanding function and health evaluation function.

[0076] Here, as an example, the information processing system 100 manages work management information related to personnel affairs and attendance of employees, health check results and stress check results, physical condition management information including information related to the first employee's condition predicted based on the CEM value of the voice data, and the above-mentioned information related to engagement (referred to as engagement information). Note that health checks are, for example, periodically conducted for all employees belonging to a company, and the health check results are transmitted to the server 10.

[0077] Furthermore, stress checks may be conducted periodically for all employees belonging to a company, or for employees who have worked more than the prescribed overtime hours. Stress checks and engagement surveys may be conducted, for example, by an employee terminal 20, which will be described later. Response data for the stress checks and engagement surveys sent from the employee terminal 20 is sent to the server 10 and stored.

[0078] In the following description, an employee who selects a disclosure destination of a report including his / her personal information is referred to as a "first employee". A plurality of disclosure destination terminals 30a to 30n are connected to this information processing system 100. The disclosure destination terminals 30a to 30n are used by candidates for disclosure destinations, such as, for example, management, industrial doctors, public health nurses, human resources, other employees, and third-party organizations. The disclosure destination of the report of the first employee may be employees other than the first employee, such as a superior, a senior employee, or a colleague. For this reason, the disclosure destination terminals include terminals used by other employees. For the sake of explanation, the other employees are referred to as "second employees". Note that the disclosure destinations may include those inside the company (management, industrial doctors, public health nurses, human resources, and the second employee) as well as those outside the company (third-party organizations). When it is not necessary to distinguish between the disclosure destination terminals 30a to 30n, they are referred to as disclosure destination terminals 30.

[0079] <Employee terminal 20> The employee terminal 20 shown in FIG. 12 is an information terminal used by the first employee and transmits and receives data to and from the server 10 via the network N by wireless communication. The employee terminal 20 is, for example, a personal computer, a tablet, a smartphone, etc., and is capable of acquiring biometric information including the speech and facial expressions of the first employee while working. FIG. 12 is a block diagram showing the configuration of the employee terminal 20 in FIG. 11. In FIG. 12, the same components as those in FIG. 5 are assigned the same reference numerals, and descriptions thereof will be omitted as appropriate.

[0080] 5, the employee terminal 20 includes a biometric information acquisition unit 27. The biometric information acquisition unit 27 is a biometric information measuring device that measures biometric information such as body temperature, heart rate, and blood pressure at set intervals. The biometric information acquisition unit 27 may record the measurement time together with the measured biometric information. The biometric information acquisition unit 27 may also include a function of taking a facial image of the first employee under the control of the processing unit 26.

[0081] As described above, the generation processing unit 261, for example, records the speech of the employee for a predetermined period that satisfies a predetermined condition, and generates voice data for providing preventive medical care. Note that the generation processing unit 261 may, for example, record the speech and facial expressions of the first employee during an online conference, and generate one of the pieces of biometric information for health management. The input / output unit 25 may include a display device such as a screen, and an input device such as a keyboard. The first employee can use the input device to select and input the disclosure destination of a report that links his / her health condition with information about himself / herself.

[0082] <Disclosure destination terminal 30> The disclosure destination terminal 30 is operated by each of a plurality of disclosure destination candidates. The disclosure destination terminal 30 is, for example, a personal computer, a tablet, a smartphone, etc. The disclosure destination terminal 30 transmits and receives data to and from the server 10 via the network N. FIG. 13 is a block diagram showing the functional configuration of the disclosure destination terminal 30 in FIG. 11. As shown in FIG. 13, the disclosure destination terminal 30 includes an input / output unit 31, a communication unit 32, a storage unit 33, a memory 34, and a processing unit 35.

[0083] The input / output unit 31 may include a display device such as a screen and an input device such as a keyboard. The communication unit 32 is a communication interface with the network N. The storage unit 33 stores a program in which various processes for executing information transmission processing and display processing, which will be described later, are implemented. The processing unit 35 is a processor that controls the hardware of the disclosure destination terminal 30. The processing unit 35 loads the program from the storage unit 33 into the memory 34 and executes it. In this way, the processing unit 35 realizes the functions of an access processing unit 351 and a display processing unit 352.

[0084] When the first employee selects, for example, an industrial physician as the disclosure destination, access to the report of the first employee on the server 10 is permitted from the disclosure destination terminal 30a used by the industrial physician. The access processing unit 351 can access the server 10 and receive the report of the first employee. The display processing unit 352 causes the input / output unit 31 to display a screen generated by the execution of a program. The display processing unit 352 can, for example, display that the first employee has selected an industrial physician as the disclosure destination, or display the contents of the received report of the first employee.

[0085] <Server 10> The server 10 is an information processing device that realizes a health management function, an engagement recognition function, and a health assessment function. Fig. 14 is a block diagram showing the configuration of the server 10 in Fig. 11. The server 10 includes a storage unit 11, a memory 12, a communication unit 13, and a processing unit 15. The storage unit 11 stores a program 111 and an employee information DB 112. The program 111 is a computer program in which some of the health management function, the engagement recognition function, the health assessment function, etc. are implemented.

[0086] The employee information DB 112 is a database that manages various information including information related to the health management of employees belonging to the company. In the example shown in Fig. 14, the employee information DB 112 manages employee IDs, employee biometric information, work management information, health management information, and engagement information in association with each other. The employee biometric information includes the employee's voice data.

[0087] The processing unit 15 loads the program 111 from the storage unit 11 into the memory 12, and executes the program 111. In this way, the processing unit 15 realizes the functions of an acquisition unit 151, a determination unit 152, a report creation unit 153, a reception unit 154, a permission unit 155, a notification unit 156, an advice information generation unit 157, and a soundness evaluation unit 158.

[0088] The acquisition unit 151 acquires biometric information from the employee terminal 20 described above. When the first employee speaks to or holds his / her face over the employee terminal 20 before starting work or at any time, biometric information including a facial image and spoken voice can be generated. In order to calculate the normal range of the CEM value, the acquisition unit 151 acquires in advance a plurality of voice data that meets a predetermined condition and is generated during a predetermined period. When acquiring voice data for the first time in a state where there is no accumulated voice data of the subject, the acquisition unit 151 can acquire a plurality of voice data three times a day, in the morning, afternoon, and evening, for example, for about two weeks.

[0089] The biometric information generated by the employee terminal 20 is transmitted to the server 10 together with the employee ID. The acquisition unit 151 links the received biometric information to the employee ID and registers it in the employee information DB 112. The acquisition unit 151 may sequentially acquire biometric information measured at a predetermined period.

[0090] The determination unit 152 determines the health condition of the employees based on the acquired biometric information. For example, the determination unit 152 can digitize the health condition (fatigue, tension, etc.) of the first employee from the registered biometric information. The determination unit 152 can also include the functions of the chaos analysis unit 142, normal range calculation unit 143, trend prediction unit 144, deviation rate calculation unit 145, and graph generation unit 146 shown in FIG. 4 for calculating a CEM value from the voice data of the first employee and predicting the condition of the first employee.

[0091] The advice information generating unit 157 can generate advice information according to the health condition of the first employee based on the determination result by the determining unit 152. Here, the advice information is, for example, information that suggests a method for maintaining health, a method for improving symptoms, a method for prevention, etc. The advice information can be automatically generated based on, for example, information that is the cause of the health condition of the first employee. The advice information can be stored in a storage unit (not shown) in association with the information that is the cause.

[0092] The cause information may include, for example, excessive working hours, lack of exercise, lack of sleep, changes in the work environment, etc. The advice information may include, for example, information recommending rest, going to bed early and getting up early, moderate exercise, etc., and information suggesting skills and mindsets that should be acquired, such as communication and ways of thinking in the workplace. The advice information to be presented may be determined based on the attributes of the user (gender, new employee, etc.). In addition, for employees who are determined to have a high tendency to fatigue, a notice of the high tendency to fatigue may be sent to the employee terminal 20, and a suggestion to take a break or leave may be made. This makes it possible to encourage behavioral changes in the first employee who received the advice information.

[0093] The report creation unit 153 creates a report linking the health condition of the first employee determined by the determination unit 152 with information about the first employee. The information about the first employee includes information about personnel affairs of employees belonging to the company, information about attendance, information about medical examination results, and information about stress check results. The information about the employee may include information about company events such as joining the company, transfer, and promotion, and information about private events such as marriage, divorce, childbirth, and nursing care. The physical condition management information includes information about the condition of the first employee predicted based on the CEM value of the voice data. The advice information generated by the advice information generation unit 157 may also be registered in the employee information DB 112 as information about the first employee.

[0094] The personnel information may include groups that cross departments or organizations, such as project teams, and groups of workers that are grouped under certain conditions, such as "new employee groups." This makes it possible to understand, for example, the workload of employees in each project team and trends in the working hours of new employees. The attendance information may include, for example, quantitative data such as the total number of working days, total working hours, number of business trips, arrival time, and departure time, as well as data on how the workload of the employee is occurring.

[0095] Information on health check results may include, for example, the results of each examination item, such as weight, height, waist circumference, X-rays such as chest X-rays, MRI scans of the brain, etc., and ultrasound scans of the liver, kidneys, prostate, uterus, etc. Stress checks are a system that is required by the Industrial Safety and Health Act to be carried out according to the number of workers. Stress check questions include questions about causes of work stress (stressors), questions about mental and physical reactions and subjective symptoms due to stress, and questions about support for workers from those around them. Information on stress check results may include results of items such as the results of work load assessment, work resource assessment, and overall assessment.

[0096] Job resources refer to factors within the organization that reduce work burden, mitigate the negative effects of work burden, and increase motivation. Specifically, they are expressed as scores based on the evaluation of questions such as "Is there support from your supervisor?", "Is there support from your colleagues?", and "Are you respected as an individual?"

[0097] Therefore, the report generated by the report generation unit 153 indicates the correlation between the health condition of the first employee, information on personnel and attendance, health management information such as medical checkups, and engagement information. The generated report can be registered in the employee information DB 112 in association with the employee ID.

[0098] This report may include advice information according to the first employee's health condition and a memo recommending consultation (referred to as a consultation recommendation memo). Unlike advice information that is automatically generated according to causal information, the consultation recommendation memo is information that recommends a personalized suggestion specialized for the first employee by referring to information about the first employee. The consultation recommendation memo may be automatically generated by the information processing system 100, or may be created by a care staff member selected by the first employee as a disclosure destination, as described below. Adding a consultation recommendation memo can encourage the employee to become aware of the condition and improve self-care awareness. In addition, if the first employee has a problem such as poor health, the report disclosed to the first employee may include a request for staff intervention depending on the first employee's health condition.

[0099] The report created by the report creation unit 153 is transmitted to the employee terminal 20 used by the first employee, and the contents are disclosed to the first employee. At this time, the server 10 can transmit a request to select a disclosure destination of the report to the employee terminal 20 used by the first employee. In response to the selection request, the first employee can input the selection information of the disclosure destination to which the first employee wishes to disclose his / her report from among multiple disclosure destinations. The disclosure destination desired by the first employee may be one or multiple. The option of not disclosing the report can also be selected according to the first employee's wishes. In addition, the first employee does not need to select a disclosure destination for an interview, and may select a disclosure destination for sending a kind of SOS, such as "I want you to know" or "I want you to understand."

[0100] When the receiving unit 154 receives the selection information of the disclosure destination of the first employee's report, the permission unit 155 permits the disclosure of the report to the disclosure destination selected by the first employee. The notification unit 156 can notify the disclosure destination terminal 30 selected as the disclosure destination that the first employee's report can be disclosed.

[0101] For example, when an industrial physician is selected as the disclosure destination, the disclosure destination terminal 30a used by the industrial physician is given access rights to the report of the first employee stored in the server 10. The industrial physician who receives the notification can view the report of the first employee from the disclosure destination terminal 30a to which the access rights have been granted. This allows the industrial physician to check the condition of the first employee based on the evidence in the report of the first employee and his / her own knowledge, and to interview and provide care. In addition, the first employee can share his / her own condition by selecting a third party such as the employee's doctor or a family member as the disclosure destination. This allows the first employee to build an optimal safety net for himself / herself.

[0102] If the first employee wishes, he / she can have an interview with the selected disclosure recipient. Note that the first employee is not required to have an interview, and does not have to have an interview. However, as mentioned above, if the report includes a request for intervention from the care staff, the care staff may request an interview.

[0103] The health evaluation unit 158 ​​processes the personal information of the employee so that the employee cannot be identified, for example, as "Employee XX," and aggregates the data of all employees in the organization to which the employee belongs, thereby creating health information summarized by organization. This makes it possible to create reports on the employee's health status, attendance information, physical condition management information, engagement information, and the like. This health information can be disclosed to the management of the company as an "organizational health report." This allows the management of the company to have an overview of the health of the company to which the employee belongs. By using the organizational health report in this way, it is possible to more effectively grasp the health of the organization, which would be difficult to grasp using engagement information alone, and to promote beneficial health management.

[0104] As described above, according to the embodiment, in addition to the stress check required by law, employees themselves can understand their own health conditions from daily biological information, and each employee's awareness of self-care can be improved. Also, through advice information and counseling recommendations from the information processing system 100, it is possible to encourage behavioral changes in employees and promote health.

[0105] Furthermore, according to the embodiment, the employee can select the disclosure destination of the report linking the employee's health condition with information about the employee. In this way, by employees freely and willingly disclosing their own information, it is possible to create a situation in which the employee and the disclosure destination, for example, staff (industrial physician / public health nurse / human resources / labor, etc.), can work directly together to ensure that consultations can be received. In particular, public health nurses who conduct health interviews can conduct the interviews based on the evidence disclosed by the employee, making it possible to provide care that is tailored to each individual employee.

[0106] In addition to collaboration with industrial physicians and public health nurses, the disclosure destination can also be set to collaborate with a community of one's choice. For example, an employee can choose to disclose information to a related superior or line care manager, rather than to their direct superior. This allows employees to check the health status of employees through horizontal and diagonal collaboration, even if the line care in the organization they belong to does not function, and a health safety net can be set up within the company. It also allows employees to receive care customized for each individual. If an employee chooses an external third party as the disclosure destination, information can also be disseminated to the outside. This allows collaboration with buffer personnel (trusted superiors and related parties, etc.) to be formed, and mental illnesses can be detected and cared for at the pre-symptomatic stage, thereby reducing the number of people who develop mental illness.

[0107] Furthermore, according to the embodiment, the information processing system 100 can summarize information on the health condition resulting from the biometric information of an individual to a certain level and process it into a state in which the individual cannot be identified. This allows the state of an organization to be viewed as summary information based on the biometric information, making it possible to correctly show the degree of fatigue of the organization to the management of the company.

[0108] Furthermore, by cross-analyzing such emotion-free biometric information with engagement information based on engagement surveys to create information on the health of an organization, it will be possible to respond to the mandatory disclosure of human capital information.

[0109] Figure 15 is a configuration example regarding the arrangement of replacement personnel for work that outsources work requested from a first contractor by a client to a second contractor. Note that the configuration example regarding the arrangement of replacement personnel for work can be found in the contents of Japanese Patent Application No. 2023-009060.

[0110] Fig. 15 is a diagram showing, as an example, a flow of outsourcing a transport task requested by a shipper to a first transport company to a second transport company in the information processing system 100. The information processing system 100 is a system that outsources the transport task of a package requested by a shipper to a first transport company to a second transport company different from the first transport company depending on the health condition of a first driver belonging to the first transport company that has undertaken the transport task. That is, in the information processing system 100, the first transport company is the "consignor" and the second transport company is the "consignee".

[0111] Fig. 16 is a diagram showing the overall configuration of the information processing system 100 of Fig. 15. As shown in Fig. 5, the information processing system 100 includes a server 10, an employee terminal 20, management terminals 50a to 50n, and an authentication device 40. The server 10, the employee terminal 20, the management terminals 50a to 50n, and the authentication device 40 are each connected via a network N.

[0112] Here, the information processing system 100 includes a function for authenticating the identity of the first driver (hereinafter referred to as the roll call function), a function for managing the health condition of the first driver (hereinafter referred to as the health management function), and a function for outsourcing transportation work requested by the shipper to other transportation companies (hereinafter referred to as the outsourcing function).

[0113] In the following description, it is assumed that the first transport company uses the roll call function, health management function, and consignment function of the information processing system 100 to perform roll calls of its drivers, manage the health of the drivers, and consign transportation work when the driver's health condition is poor. As described above, the health management function includes a function to predict the condition of the first employee based on the CEM value of the voice data.

[0114] In this information processing system 100, a plurality of transport companies can be registered as candidates for contractors. Here, it is assumed that n companies, from the first transport company to the nth transport company, are registered as contractors. That is, each transport company can be a contractor for a transport work requested by a shipper, or a contractor that undertakes the transport work from a contractor. Among the plurality of transport companies registered, there may be a transport company that is only capable of undertaking the transport work from a contractor. The first transport company to the nth transport company are provided with management terminals 50a to 50n, respectively.

[0115] The information processing system 100 can perform identity authentication by, for example, performing biometric authentication of a first driver who belongs to a first transport company. Biometric authentication information used in biometric authentication is information for uniquely identifying an individual. Here, the biometric authentication information will be described as a face authentication, which is an example of biometric authentication, and as a face image.

[0116] <Employee terminal 20> The employee terminal 20 is an information terminal carried and operated by the first driver, and transmits and receives data to and from the server 10 via the network N by wireless communication. The employee terminal 20 includes a biometric information acquisition unit 27 in addition to the components shown in FIG. 5. However, although the input / output unit 25 is not shown in FIG. 17, the employee terminal 20 may include an input / output unit 25 including a display device such as a touch panel and an input device. FIG. 17 is a block diagram showing the configuration of the employee terminal 20 in FIG. 16.

[0117] The employee terminal 20 further includes a biometric information acquisition unit 27. The biometric information acquisition unit 27 is a biometric information measuring device that measures biometric information such as body temperature, heart rate, and blood pressure at a set period. The biometric information acquisition unit 27 may record the measurement time together with the measured biometric information. The biometric information acquisition unit 27 may also include a function of photographing the first driver under the control of the processing unit 26.

[0118] The processing unit 26 is a processor that controls the hardware of the employee terminal 20. The processing unit 26 loads a program from the storage unit 22 into the memory 23 and executes it. As a result, the processing unit 26 realizes the functions of a registration processing unit 263 and a transmission processing unit 264.

[0119] The registration processing unit 263 performs a pre-registration process of a facial image. This facial image is used for identity authentication of the first driver. Specifically, the registration processing unit 263 transmits a registration request for a facial image photographed by the first driver to the server 10 via the network N. As will be described later, the facial image of the first employee may be registered in the face information DB 41 of the authentication device 40.

[0120] The transmission processing unit 262 transmits a face image as biometric authentication information and biometric information for managing the physical condition of the first driver to the server 10. As described above, the transmission processing unit 262 records, for example, the employee's speech sound that satisfies a predetermined condition for a predetermined period of time, and transmits the voice data for providing preventive medical care to the server 10. The transmission processing unit 262 may transmit the terminal ID of the employee terminal 20 and the employee ID together with this information.

[0121] <Administration terminal 50> The management terminal 50 is installed at the base of each transport company and operated by an operation manager. The management terminal 50 transmits and receives data to and from the server 10 via the network N. FIG. 18 is a block diagram showing the functional configuration of the management terminal 50 in FIG. 16. As shown in FIG. 18, the management terminal 50 includes an input / output unit 51, a communication unit 52, a storage unit 53, a processing unit 54, and a notification unit 55.

[0122] The input / output unit 51 includes a display device (display unit) such as a screen and an input device (input unit), and may be, for example, a touch panel. The communication unit 52 is a communication interface with the network N. The storage unit 53 stores a program in which various processes for executing information transmission processing and display processing, which will be described later, are implemented. The processing unit 54 is a processor that controls the hardware of the management terminal 50. The processing unit 54 loads the program from the storage unit 53 into a memory (not shown) and executes it. In this way, the processing unit 54 realizes the functions of a transmission processing unit 541 and a display processing unit 542.

[0123] When there is an abnormality in the biological information of the first driver, that is, when the first driver's health condition is poor, the server 10 can output an alert to the management terminal 50. For example, after calculating the normal range of each CEM value based on a plurality of pieces of voice data, if the newly calculated CEM value for judgment is smaller than the lower limit of the normal range, the employee may be determined to be in a "fatigue state." In this case, the server 10 can output an alert to the management terminal 50.

[0124] As described above, the alert notifies the operations manager of the safety level of the first driver's transportation work. In response to the alert, the operations manager can use the input device to input the outsourcing conditions for outsourcing the transportation work to another carrier. The transmission processing unit 541 transmits the input outsourcing conditions to the server 10. The operations manager may contact the first driver to take appropriate measures, such as interrupting the work and returning to the base.

[0125] The display processing unit 542 displays a screen generated by the execution of the program on the input / output unit 51. The display processing unit 542 can display information to be notified to the operations manager regarding the outsourcing of the transportation work on the input / output unit 51. For example, the display processing unit 542 can display an input screen for the outsourcing conditions described above and an input screen for evaluating the transportation work performed by the outsourced operator.

[0126] The notification unit 55 notifies the operation manager of the alert by light emission or sound. Information regarding the alert may be displayed as characters on the input / output unit 51. When the display processing unit 542 receives information to be notified to the first driver regarding the outsourcing of the transport work from the server 10, the display processing unit 542 may output the information to the employee terminal 20. The information to be notified to the first driver may be, for example, information regarding actions after the work is suspended, which transport company has been decided as the outsourced party, and the like.

[0127] <Authentication device 40> Here, an authentication device 40 is provided to realize the roll call function of the information processing system 100. The roll call function performs identity verification and attendance management of drivers before they start work. The roll call may be a face-to-face roll call performed by the driver at a base, or a remote roll call performed at a remote location. The authentication device 40 is an information processing device that manages face images of multiple drivers belonging to the first transport company and performs face authentication. In addition, in response to an authentication request received from the outside, the authentication device 40 compares the face image included in the request with the face image of the first driver it manages, and returns the comparison result to the request source.

[0128] <Server 10> Server 10 is an information processing device that realizes a health management function and a commissioning function. Fig. 19 is a block diagram showing the configuration of server 10 in Fig. 16. Server 10 includes a storage unit 11, a memory 12, a communication unit 13, and a processing unit 16. Storage unit 11 is an example of a storage device such as a hard disk or flash memory. Storage unit 11 stores program 111 and health management DB 112. Program 111 is a computer program in which part of the health management function, commissioning function, etc. are implemented.

[0129] The physical condition management DB 112 is a database that manages information related to the physical condition management of drivers belonging to the first transport company. The physical condition management DB 112 manages employee IDs and biometric information of the drivers in association with each other. That is, in the second embodiment, the biometric information and the biometric authentication information are linked to the employee IDs, and can be managed for each transport company by the physical condition management DB 112 and the authentication device 40 of the server 10.

[0130] Further, the physical condition management DB 112 stores judgment conditions for judging the safety level of the driver. The judgment conditions may be, for example, a stepwise range and a safety level associated with each piece of biological information. For example, when the CEM value for judgment is smaller than the lower limit of the normal range and equal to or greater than a predetermined threshold value that is smaller than the lower limit, the safety level may be judged to be "medium (stressed)". When the CEM value is smaller than the predetermined threshold, the safety level may be judged to be "low (fatigued)". The judgment conditions for the safety level may be, for example, a judgment that is made by combining a plurality of pieces of biological information and the safety level associated with the judgment. For example, the judgment conditions may be set by combining body temperature, heart rate, and the like.

[0131] The safety level determination conditions may be different conditions set for each attribute of the driver. For example, different safety level determination conditions may be set for each predetermined age range or each gender. Also, the safety level determination conditions may be different conditions set for each driver.

[0132] The processing unit 16 is a processor that controls each component of the server 10. The processing unit 16 loads the program 111 from the storage unit 11 into the memory 12 and executes the program 111. In this way, the processing unit 16 realizes the functions of an authentication processing unit 161, an acquisition unit 162, a determination unit 163, a generation unit 164, a selection unit 165, and an output processing unit 166.

[0133] The authentication processing unit 161 realizes the roll call function described above. When the face authentication is successful, the authentication processing unit 161 can identify the driver associated with the collated face feature information and record that the identified driver has come to work. The acquisition unit 162 acquires biometric information of a first driver belonging to a first transport company before the first driver performs a transport operation.

[0134] The first driver may talk to the employee terminal 20 before starting work or at any time, so that biometric information including spoken voice may be generated. In order to calculate the normal range of the CEM value, the acquisition unit 162 acquires in advance a plurality of pieces of voice data that are generated during a predetermined period and that satisfy a predetermined condition. When acquiring voice data for the first time without any stored voice data of the subject, the acquisition unit 162 may acquire a plurality of pieces of voice data three times a day, in the morning, afternoon, and evening, for example, for about two weeks. The acquisition unit 162 registers the received biometric information in the physical condition management DB 112 by linking it to the employee ID. In addition, the acquisition unit 162 may acquire biometric information measured at a predetermined cycle in sequence.

[0135] The determination unit 163 uses the above-mentioned determination conditions to determine the safety level of the first driver for the transport work based on the biological information of the first driver. For example, the determination unit 163 can determine the influence on safe driving by detecting a sign of fatigue or determining the mental state from a change in the biological information of the first driver over time. In addition, the determination unit 152 can include functions of the chaos analysis unit 142, the normal range calculation unit 143, the trend prediction unit 144, the deviation rate calculation unit 145, and the graph generation unit 146 shown in FIG. 4 for calculating a CEM value from the voice data of the first employee and predicting the state of the first employee.

[0136] The generating unit 164 generates an alert to prompt the first driver to confirm whether he / she is capable of carrying out the transportation work according to the safety level. The operation manager calls the first driver again for whom the alert was issued, and if the first driver is determined to be unsuitable for the transportation work including driving, the operation manager stops the first driver's work. The operation manager can manage the physical condition of the first driver based not only on experience and visible information but also on biological information.

[0137] In response to the alert, the selection unit 165 acquires the consignment conditions for the transportation work, and selects a second transportation company that matches the consignment conditions from among a plurality of pre-registered transportation companies that can undertake the transportation work, and consigns the transportation work to the second transportation company that is different from the first transportation company. First, when the operation manager or the manager of the first transportation company determines that it is necessary to consign the transportation work in the case where the transportation work of the first driver is stopped, the operation manager or the manager of the first transportation company can input the consignment conditions using the management terminal 50a. This allows the selection unit 165 to select a transportation company that matches the input consignment conditions from among a plurality of registered transportation companies.

[0138] The selection unit 165 may select a candidate for the consignee based on an AI (Artificial Intelligence) recommendation function that calculates a score indicating the matching accuracy between the consignment conditions input by the first carrier and the consignment conditions of each of the other carriers, and selects a carrier with a high score. That is, the selection unit 165 may adopt a method of constructing a matching model by performing machine learning using past data summarizing the selection results of other registered carriers that will be matched as learning data, inputting the consignment conditions of the first carrier that is looking for a matching partner, and outputting a score using this matching model. It is also possible to directly specify a predetermined carrier as the consignee.

[0139] The output processing unit 166 can make an inquiry to the selected second carrier about the consignment of the transport work. Specifically, the output processing unit 166 can output information to the management terminal 50b of the second carrier that the first carrier has made an inquiry about the consignment. Since it is preferable to determine the consignee in a short time, when multiple carriers match the consignment conditions, information about the consignment inquiry may be sent simultaneously to the multiple carriers that match the consignment conditions. In this case, the carrier that responds the fastest to the consignment acceptance can be determined as the consignee. Alternatively, when the shipper wants to determine the consignee from multiple carriers that match the consignment conditions, it is also possible to notify the shipper of the candidates of carriers and have the shipper determine the consignee carrier. Furthermore, when a predetermined carrier is directly designated, the output processing unit 166 can directly output a message about the consignment to the management terminal 50 of the designated carrier. The second carrier that has been entrusted with the transport work from the consignor can call its second drivers and give the same work instructions as for normal transport work.

[0140] In the above examples, the program includes instructions (or software code) that, when loaded into a computer, causes the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, the computer-readable medium or tangible storage medium includes RAM, read-only memory (ROM), flash memory, SSD or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray® disk or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, the transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0141] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-mentioned embodiments. Various modifications that can be understood by a person skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be appropriately combined with other embodiments.

[0142] Each drawing is merely an example for describing one or more embodiments. Each drawing may relate not only to one particular embodiment, but to one or more other embodiments. As can be understood by those skilled in the art, various features or steps described with reference to any one drawing may be combined with features or steps shown in one or more other drawings to create an embodiment not explicitly shown or described, for example. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0143] A part or all of the above-described embodiments can be described as, but is not limited to, the following supplementary notes. (Appendix 1) a voice acquisition unit that acquires a plurality of voice data uttered by a subject, which satisfy a predetermined condition, and which are generated during a predetermined period of time; a chaos analysis unit that performs chaos analysis on the plurality of pieces of time-series voice data and calculates chaos theoretical index values ​​for each of the pieces of time-series voice data; a normal range calculation unit that performs statistical processing of the chaos theoretical exponent value and calculates a normal range of the chaos theoretical exponent value; A trend prediction unit that predicts a state of the subject based on a transition of the normal range; Equipped with Information processing device. (Appendix 2) The transition of the normal range is calculated by a moving average of the normal range. 2. An information processing device according to claim 1. (Appendix 3) A deviation rate calculation unit is further provided for calculating a deviation rate from the normal range for a chaos theoretical exponent value of the voice data of the subject generated at a predetermined time point after a period in which the voice data for calculating the normal range is acquired. 2. An information processing device according to claim 1. (Appendix 4) The period during which the voice data is acquired is determined based on the state that the subject recognizes. 2. An information processing device according to claim 1. (Appendix 5) The plurality of pieces of audio data are acquired under at least one identical sound collection condition. 2. An information processing device according to claim 1. (Appendix 6) The sound collection condition is a microphone that collects the sound data. 6. The information processing device according to claim 5. (Appendix 7) The chaos theoretical index value is a CEM value according to the SiCECA algorithm; 2. An information processing device according to claim 1. (Appendix 8) a report creation unit that creates a report linking a prediction result of the state of the subject with information about the subject; A reception unit that receives a selection of a disclosure destination of the report from the subject; a permission unit for permitting disclosure of the report to a disclosure destination selected by the subject; Further comprising: 2. An information processing device according to claim 1. (Appendix 9) A notification unit that notifies the subject of a recommendation for consultation based on the report. 9. The information processing device according to claim 8. (Appendix 10) An advice information generating unit that generates advice information according to the prediction result, The report includes the advice information. 9. The information processing device according to claim 8. (Appendix 11) A health assessment unit is further provided for generating health information regarding an organization to which the subjects belong based on the reports of the plurality of subjects. 9. The information processing device according to claim 8. (Appendix 12) an acquisition unit that acquires a prediction result of a state of a first worker belonging to a first business entity before the first worker performs a predetermined task; A generating unit that generates an alert based on the prediction result; A selection unit that acquires outsourcing conditions for the work in response to the alert, selects a second business operator that matches the outsourcing conditions and is different from the first business operator from among a plurality of businesses that are registered in advance and can undertake the work, and outsources the work; having 2. An information processing device according to claim 1. (Appendix 13) a voice acquisition unit that acquires a plurality of voice data uttered by a subject, which satisfy a predetermined condition, and which are generated during a predetermined period of time; a chaos analysis unit that performs chaos analysis on the plurality of pieces of time-series voice data and calculates chaos theoretical index values ​​for each of the pieces of time-series voice data; a normal range calculation unit that performs statistical processing of the chaos theoretical exponent value and calculates a normal range of the chaos theoretical exponent value; A trend prediction unit that predicts a state of the subject based on a transition of the normal range; Equipped with Information processing system. (Appendix 14) The computer A process of acquiring a plurality of pieces of voice data uttered by a subject, which satisfy a predetermined condition and are generated during a predetermined period of time; A process of performing chaos analysis on a plurality of pieces of time-series voice data and calculating chaos theoretical index values ​​for each of the pieces of time-series voice data; A process of performing statistical processing of the chaos theoretical exponent value and calculating a normal range of the chaos theoretical exponent value; A process of predicting a state of the subject based on a transition of the normal range; and Execute Information processing methods. (Appendix 15) A process of acquiring a plurality of pieces of voice data uttered by a subject, which satisfy a predetermined condition and are generated during a predetermined period of time; A process of performing chaos analysis on a plurality of pieces of time-series voice data and calculating chaos theoretical index values ​​for each of the pieces of time-series voice data; A process of performing statistical processing of the chaos theoretical exponent value and calculating a normal range of the chaos theoretical exponent value; A process of predicting a state of the subject based on a transition of the normal range; and to cause a computer to execute program.

[0144] Some or all of the elements described in Supplementary Notes 2 to 12 that are dependent on Supplementary Note 1 (information processing device) may also be dependent on Supplementary Note 13 (information processing system), Supplementary Note 14 (information processing method), and Supplementary Note 15 (program) in a similar dependent relationship to Supplementary Note 2 to Supplementary Note 12. Some or all of the elements described in any of the supplementary notes may be applied to various hardware, software, recording means for recording software, systems, and methods. [Explanation of symbols]

[0145] 1. Information processing device 2. Voice Acquisition Unit 3 Chaos Analysis Section 4. Normal range calculation section 5 Trend prediction section 10 Server 11 Storage section 111 Program 112 Employee Information DB 12. Memory 13. Communications Department 14 Processing section 141 Voice Acquisition Unit 142 Chaos Analysis Department 143 Normal Range Calculation Section 144 Trend Prediction Department 145 Deviation rate calculation section 146 Graph Generation Unit 147 Transmission Processing Unit 20 Employee terminals 21. Mike 22 Memory section 23 Memory 24 Communications Department 25 Input / output section 26 Processing section 261 Generation Processing Unit 262 Transmission Processing Unit 27 Measuring part 30 Disclosure destination terminal 31 Input / output section 32 Communications Department 33 Storage section 34 Memory 35 Processing section 351 Access Processing Unit 352 Display processing section 100 Information Processing Systems 101 Information Processing Systems 102 Voice Acquisition Unit 103 Chaos Analysis Department 104 Normal Range Calculation Section 105 Trend Prediction Department N Network

Claims

1. a voice acquisition unit that acquires a plurality of voice data uttered by a subject, which satisfy a predetermined condition, and which are generated during a predetermined period of time; a chaos analysis unit that performs chaos analysis on the plurality of pieces of time-series voice data and calculates chaos theoretical index values ​​for each of the pieces of time-series voice data; a normal range calculation unit that performs statistical processing of the chaos theoretical exponent value and calculates a normal range of the chaos theoretical exponent value; A trend prediction unit that predicts a state of the subject based on a transition of the normal range; Equipped with Information processing device.

2. The transition of the normal range is calculated by a moving average of the normal range. The information processing device according to claim 1 .

3. A deviation rate calculation unit is further provided for calculating a deviation rate from the normal range for a chaos theoretical exponent value of the voice data of the subject generated at a predetermined time point after a period in which the voice data for calculating the normal range is acquired. The information processing device according to claim 1 .

4. The period during which the voice data is acquired is determined based on the state that the subject recognizes. The information processing device according to claim 1 .

5. The plurality of pieces of audio data are acquired under at least one identical sound collection condition. The information processing device according to claim 1 .

6. The sound collection condition is a microphone that collects the sound data. The information processing device according to claim 5 .

7. The chaos theoretical index value is a CEM value by the SiCECA algorithm; The information processing device according to claim 1 .

8. a voice acquisition unit that acquires a plurality of voice data uttered by a subject, which satisfy a predetermined condition, and which are generated during a predetermined period of time; a chaos analysis unit that performs chaos analysis on the plurality of pieces of time-series voice data and calculates chaos theoretical index values ​​for each of the pieces of time-series voice data; a normal range calculation unit that performs statistical processing of the chaos theoretical exponent value and calculates a normal range of the chaos theoretical exponent value; A trend prediction unit that predicts a state of the subject based on a transition of the normal range; Equipped with Information processing system.

9. The computer A process of acquiring a plurality of pieces of voice data uttered by a subject, which satisfy a predetermined condition and are generated during a predetermined period of time; A process of performing chaos analysis on a plurality of pieces of time-series voice data and calculating chaos theoretical index values ​​for each of the pieces of time-series voice data; A process of performing statistical processing of the chaos theoretical exponent value and calculating a normal range of the chaos theoretical exponent value; A process of predicting a state of the subject based on a transition of the normal range; and Execute Information processing methods.

10. A process of acquiring a plurality of pieces of voice data uttered by a subject, which satisfy a predetermined condition and are generated during a predetermined period of time; A process of performing chaos analysis on a plurality of pieces of time-series voice data and calculating chaos theoretical index values ​​for each of the pieces of time-series voice data; A process of performing statistical processing of the chaos theoretical exponent value and calculating a normal range of the chaos theoretical exponent value; A process of predicting a state of the subject based on a transition of the normal range; and to cause a computer to execute program.

Images