JP7524123B2 - Injury and illness condition estimation device - Google Patents

Description

The present invention relates to an injury/illness condition estimation device that estimates injury/illness conditions.

Predicting infectious diseases such as influenza is an effective way to prevent these diseases. Patent Document 1 describes a technology for predicting diseases, which involves diagnosing mental illnesses based on daily activities.

JP 2018-15327 A

However, the technology described in Patent Document 1 is not targeted at infectious diseases and other injuries, and therefore cannot be used as is to estimate infectious diseases based on daily activities.

Therefore, in order to solve the above-mentioned problems, the objective is to provide an injury/illness condition estimation device that can estimate the injury/illness condition of a user.

The injury/illness state estimation device of the present invention includes a user information acquisition unit that acquires user information indicating at least one of the user's behavior or the user's state that changes when the user is injured or ill, and an injury/illness state output unit that outputs the injury/illness state of the user based on the user information.

According to the present invention, the user's injury or illness state can be determined by using user information indicating at least one of the user's behavior or the user's state, which changes when the user is injured or ill.

A diagram showing the system configuration of the infectious disease estimation system of the present disclosure. FIG. 2 is a diagram showing a specific example of a user information DB 300. 11 is a diagram showing a specific example of information stored in a purchase history DB 400. FIG. FIG. 2 is a diagram showing a specific example of a restaurant DB 500. FIG. 13 is a diagram showing a specific example of an infection area DB 600. FIG. 2 is a block diagram showing the functional configuration of the infection estimation device 100. FIG. 2 is a block diagram showing a functional configuration of a mobile terminal 200 according to the present disclosure. 4 is a flowchart showing the operation of the infection estimation device 100. FIG. 7 is a diagram showing a system configuration of a machine learning system including a prediction model learning device 700. FIG. 2 is a diagram showing a specific example of an infected person DB 800. FIG. 7 is a block diagram showing the functional configuration of a prediction model learning device 700. FIG. 1 is a diagram illustrating explanatory variables and target variables for machine learning. FIG. 7 is a schematic diagram of a prediction model 703 (or a prediction model 102). FIG. 1 is a diagram illustrating an example of the hardware configuration of an infectious disease estimation device 100 and a prediction model learning device 700 according to an embodiment of the present disclosure.

Embodiments of the present disclosure will be described with reference to the accompanying drawings. Where possible, identical parts will be designated by the same reference numerals, and duplicate explanations will be omitted.

Figure 1 is a diagram showing the system configuration of the infectious disease estimation system of the present disclosure. As shown in the figure, the infectious disease estimation system includes an infectious disease estimation device 100, a mobile terminal 200, a user information DB 300, a purchase history DB 400, a food and beverage store DB 500, and an infected area DB 600.

The infectious disease estimation device 100 communicates with the user information DB 300, purchase history DB 400, food and beverage store DB 500, and infected area DB 600, and determines whether the user of the mobile terminal 200 has contracted a specific infectious disease based on the information stored in each DB.

The user information DB300 is a database that stores user information. This user information includes location information, vital sign information, web communication information, call information, and sensor values detected on the mobile terminal 200.

Figure 2 is a diagram showing a specific example. As shown in the diagram, the user information DB 300 stores, for each user ID, the measurement date and time, location information, vital information, web communication information, call information, and sensor values in association with each other. The measurement date and time indicates the date and time when the location information, vital information, web communication information, call information, and sensor value were acquired.

The location information is, for example, information measured by GPS. Note that it is not limited to GPS positioning, and may be approximate location information using mobile phone base stations.

Vital information is information indicating body temperature, blood pressure, pulse rate, biological gases (aldehydes released from the skin, etc.), and brain waves. The mobile device 200 has a function for measuring this vital information. If the mobile device 200 is a wearable device, this information can be acquired automatically. Of the vital information, brain waves indicate frequencies within a specified range based on the date and time of measurement. Other vital information indicates values at the date and time of measurement.

The web communication information indicates search keywords input by the user when performing a web search using the mobile device 200. It also includes words input to the SNS. In the SNS, it indicates words obtained by performing morphological analysis or the like on sentences input to the mobile device 200. In this disclosure, the words input for each time interval indicated by the measurement date and time are stored. Figure 2 shows words input to the mobile device 200 between times t1 and t2.

The call information is information indicating abnormal physical condition experienced by the user during a call, for example, information indicating whether or not the user coughed or sneezed during a call and the frequency of such coughing or sneezing. It is not limited to this, but also includes the call destination, etc. For example, if a call was made to a pharmacy, hospital, etc., the call destination is indicated. In this disclosure, the number of coughs detected, etc. are stored for each time interval indicated by the measurement date and time. Figure 2 shows the number of coughs and sneezes detected by the mobile device 200 between times t1 and t2.

The sensor values indicate various sensor values detected by the acceleration sensor, gyro sensor, pressure sensor, etc. provided in the mobile terminal 200. These sensor values indicate the user's movements; for example, when the user turns over in bed, that movement is represented by the sensor value. Also, if there is something wrong with the user's physical condition, there should be a slight change in the movement, and this information indicates that change.

This user information is periodically transmitted from the mobile device 200.

The purchase history DB 400 is a section that stores purchase history information when a user performs a purchasing process via the web on the mobile terminal 200 or another communication terminal. This purchase history DB 400 is constructed based on information sent from the mobile terminal 200 or information registered from a shopping site. This purchase history DB 400 is updated every time a user performs a purchasing process.

Figure 3 shows a specific example of information stored in purchase history DB 400. As shown in the figure, for each user ID, the store ID indicating the store where the purchase was made, the purchase date, and the purchased item are stored. In this disclosure, if the purchased item within a specified period from the date of infectious disease judgment is a specified item (e.g., medicine), the purchased item will affect the infectious disease judgment.

The restaurant DB500 is a database that stores information on restaurants and other establishments. As shown in FIG. 4, the restaurant DB500 stores a store ID, the date of infection, the store location, the infection level, and the infection control level in association with each other. The store ID is an ID for identifying the store. The store location indicates the location. The infection date indicates the date of infection if an infection occurred at the store. The infection level indicates the degree of infection based on the number of infected people. The infection control level indicates whether or not measures set by government authorities or the like were taken. The infection date, infection level, and infection control level in the restaurant DB500 are information registered by government authorities or the like, and are updated regularly. If a user visits a store where an infection occurred within a specified period after the infection date, this information such as the infection level will affect the determination of whether or not there is an infection.

The infected area DB 600 is a database that stores infected area information. This infected area information indicates areas such as cities, towns, villages, or prefectures, but is not limited to this. For example, an area may be an area divided into a mesh-like area in a predetermined unit.

As shown in FIG. 5, the infected area DB 600 stores infected area information, in which the infected area ID, infection degree, infected location, and infection onset date are associated with each other. The infected area ID is an ID for identifying the area. The infection degree indicates the level of infection, and indicates, for example, the number of infected people and the population density of infected people (number of infected people/population of the area or area of the area). The infected location indicates the location of the infected area. The infection onset date indicates the date and time when the infection occurred. This information is registered by government agencies, etc.

The infectious disease estimation device 100 in the infectious disease estimation system configured in this manner will be described. FIG. 6 is a block diagram showing the functional configuration of the infectious disease estimation device 100. As shown in the figure, the infectious disease estimation device 100 includes a user information acquisition unit 101, a prediction model 102, and an output unit 103.

The user information acquisition unit 101 is a part that acquires user information related to the user's behavior and status from the user information DB 300 and the purchase history DB 400. In this disclosure, the user information also includes the purchase of a specific item by a user stored in the purchase history DB 400.

Here, the user information acquisition unit 101 calculates the average value of the user information related to the user's behavior and state during a predetermined period of time in the past (which may include the present). For example, the user information acquisition unit 101 calculates the average value of the location information acquired as the user information. When calculating the average value of the location information, it is preferable to find the average value for a certain period of time. This is because the time period can change whether the user is near home or at work.

The user information acquisition unit 101 calculates the average value of the vital information acquired as user information. For example, it calculates the average value of body temperature, the average value of blood pressure, etc. It is also advisable to calculate the average value of this vital information for each time period. The vital information changes depending on the time period.

The user information acquisition unit 101 also calculates the average value of the sensor values acquired as user information. For example, it calculates the average value of sensor values such as an acceleration sensor and a gyro sensor. It is also advisable to calculate the average value of these sensor values for each time period. The sensor values change depending on the time period.

Then, the user information acquisition unit 101 calculates the difference between these average values and the user information at the time of diagnosis. The user information at the time of diagnosis is, for example, current user information. Note that since the user information at the time of diagnosis is used to calculate the difference from the average value, information of the same items as the average value is acquired. In addition, when calculating the difference value, it is preferable to calculate it based on the numerical values combined for the time period.

On the other hand, the user information acquisition unit 101 retrieves web communication information from the user information DB 300 and acquires search keywords used by users within a specified period of time. The user information acquisition unit 101 has an infection risk keyword DB (not shown), and when a search keyword that matches an infection risk keyword is acquired, flag information indicating that there is an infection risk is acquired. For example, when the search keyword includes a keyword that indicates abnormality in physical condition (fever, fatigue, etc.), the user information acquisition unit 101 generates and acquires flag information indicating that there is an infection risk. The flag information may be expressed in stages according to the frequency of the search keyword that matches the infection risk keyword.

The user information acquisition unit 101 also acquires purchases made within a specified period from the purchase history DB 400. If the user has purchased a specified item (such as a specified medicine), flag information indicating that there is an infection risk is acquired. The flag information may be expressed in stages according to the number and frequency of the specified purchases.

If the item is one that the user normally purchases, the flag information is modified. For example, the flag information is changed to indicate that there is no risk of infection. If it can be determined from the purchase history DB400 that a certain item has been purchased continuously for a specified period of time, it can be determined that the purchasing behavior is based on normal behavior and does not affect the infection risk determination.

The user information acquisition unit 101 also references the food and beverage store DB 500 and the infected area DB 600 to acquire information on which infected area the user was in and which infected store the user was in based on the user's location information for a specified period of time. If the user was in an infected area or infected store, the user information acquisition unit 101 acquires flag information indicating that there is a risk of infection. The flag information may be expressed in stages according to the degree of infection and the level of infection countermeasures.

The user information acquisition unit 101 inputs the difference information and flag information indicating the risk of infection into the prediction model 102.

The prediction model 102 is a part that inputs predetermined information and outputs a judgment result according to the information. In the present disclosure, the prediction model 102 inputs the difference value of the user's state and behavior and flag information indicating the risk of infection, and outputs information indicating whether the user is infected with an infectious disease or what type of infectious disease the user has. This prediction model 102 is trained in the prediction model learning device 700 described below.

The output unit 103 is a part that outputs the infection result of the infection state output by the prediction model 102. The output unit 103 transmits the infection result to the mobile terminal 200, for example, via a network. Note that the output destination is not limited to the mobile terminal 200, and may be another device.

Next, the mobile terminal 200 will be described. The mobile terminal 200 of the present disclosure is equipped with various measuring means for detecting the user's state and user's behavior. FIG. 7 is a block diagram showing the functional configuration of the mobile terminal 200 of the present disclosure. This mobile terminal 200 is configured to include a communication control unit 201, a position measurement unit 202, a vital sign measurement unit 203, a communication information analysis unit 204, a voice analysis unit 205, and a sensor 206.

The communication control unit 201 is a part that transmits information measured by various measuring means that indicates the user's behavior or condition to the infectious disease estimation device 100 to the user information DB 300 along with the measurement date and time.

The position measurement unit 202 is a part that measures the position of the mobile terminal 200. For example, it measures its own position using GPS.

The vital sign measurement unit 203 is a part that measures information indicating the user's condition, such as the user's body temperature, blood pressure, pulse rate, biogas, and brain waves.

The communication information analysis unit 204 is a part that analyzes keywords searched by the user and sentences entered into a social network service (SNS) to obtain keywords.

The voice analysis unit 205 is a part that analyzes the user's coughing, sneezing, etc. during a call. The voice analysis unit 205 analyzes the frequency of the analyzed coughing, etc. It is preferable to calculate the frequency per unit time.

The sensor 206 is at least one sensor such as an acceleration sensor, a gyro sensor, or a pressure sensor. This sensor 206 detects the user's actions.

The mobile terminal 200 can register the acquired information in the user information DB 300 together with the date and time of detection.

Next, the operation of the infectious disease estimation device 100 of the present disclosure will be described. FIG. 8 is a flowchart showing the operation of the infectious disease estimation device 100. When there is no direct infectious disease diagnosis information of the user who is the subject of diagnosis (S101: NO), the user information acquisition unit 101 of the infectious disease estimation device 100 acquires user information of the diagnosed subject for a predetermined period from the user information DB 300. In addition, the user information acquisition unit 101 references the purchase history DB 400, the food and beverage store DB 500, and the infection area DB 600 for the predetermined period to acquire information on the areas or stores where the user stayed and the products purchased (S102). The above-mentioned predetermined period is, for example, about one week based on the diagnosis estimation process, but is of course not limited to this.

The user information acquisition unit 101 calculates the average value for each item of user information for a predetermined period (S103). The user information acquisition unit 101 then calculates a difference value between the average value and the user information (e.g., the most recent user information) at the time of the diagnostic estimation process (S104).

The user information acquisition unit 101 acquires flag information indicating an infection risk when a specific search keyword or the like is present in the communication information and when a specific product is purchased. The user information acquisition unit 101 also references the food and beverage store DB 500 and the infection area DB 600 to acquire the infection risk of the area or store to which the user has traveled, and acquires the corresponding flag information (S105). In this disclosure, multiple pieces of flag information are acquired, but any one of them may be sufficient. Also, the flag information is not necessarily required.

The user information acquisition unit 101 inputs the difference value and flag information to the prediction model 102 (S106). The prediction model 102 outputs an infection score according to the difference value and flag information (S107). The output unit 103 transmits the infection score to the mobile terminal 200. The user of the mobile terminal 200 can judge his/her own infection status by looking at the infection score.

Next, the machine learning processing by the predictive model learning device 700 will be described. Figure 9 is a diagram showing the system configuration of a machine learning system including the predictive model learning device 700. As shown in the figure, this machine learning system is configured to include a user information DB 300, a purchase history DB 400, a food and beverage store DB 500, an infected area DB 600, the predictive model learning device 700, and an infected person DB 800. The user information DB 300, the purchase history DB 400, the food and beverage store DB 500, and the infected area DB 600 are as described above.

The infected person DB800 is a database that stores infected person information that associates the presence or absence of infection with each user ID that indicates an infected person. Figure 10 is a diagram showing a specific example. The user ID is a common ID with the user ID in the user information DB300, making it possible to perform linking processing via the user ID.

The prediction model learning device 700 is a device that learns a prediction model using user information, etc. FIG. 11 is a block diagram showing the functional configuration of the prediction model learning device 700. As shown in the figure, it is configured to include a user information acquisition unit 701, a learning unit 702, and a prediction model 703.

The user information acquisition unit 701 is a part that acquires user information, purchase history information, store information, and infected area information from the user information DB 300, purchase history DB 400, food and beverage store DB 500, and infected area DB 600, respectively, as data for machine learning. The user information acquisition unit 701 has the same function as the above-mentioned user information acquisition unit 101, and calculates the average value of user information over a specified period of time, and calculates the difference between this average value and the user information at the time of diagnosis processing.

Figure 12 shows the acquired information and the explanatory variables and objective variables based on that information. As shown in Figure 12 (a), user information, infected area information, store information, purchase history information, and infected person information are acquired from the respective DBs.

The user information acquisition unit 701 performs the same process as the user information acquisition unit 101 for the user information (excluding the web column), calculates the difference value from each average value, and uses this as an explanatory variable. For other items, when a specific condition is met, flag information according to the degree of the condition is generated and acquired, and this is used as an explanatory variable. On the other hand, the user information acquisition unit 701 acquires infected person information from the infected person DB 800, and generates and acquires flag information according to the presence or absence of infection. These processes are performed for the same user ID.

The learning unit 702 is a part that performs known machine learning using user information, infected area information, store information, and purchase history information as explanatory variables and infected person information as the objective variable.

The prediction model 703 is a prediction model constructed through learning by the learning unit 702. The prediction model 102 provided in the above-mentioned infectious disease estimation device 100 is based on the prediction model 703.

Such a prediction model learning device 700 can learn a prediction model. In the above description, the presence or absence of an infection with a certain infectious disease is used as the objective variable, but this is not limited to this. For example, since there are several types of infectious diseases, information according to the type may be used as the objective variable. For example, the prediction model 703 may be learned by distinguishing between infections caused by COVID-19 and infections caused by influenza viruses. In addition, it is not limited to infectious diseases, and ordinary illnesses or injuries may also be distinguished.

Figure 13 is a schematic diagram of prediction model 703 (or prediction model 102). As shown in the figure, prediction model 703 may be trained to output the infection probability of infectious disease A, B, or no infection when inputs A to X (such as differential values of user information) are input.

Next, the effects of the infectious disease estimation device 100 of the present disclosure will be described. This infectious disease estimation device 100 includes a user information acquisition unit 101 that acquires user information indicating at least one of the user's behavior or the user's state that changes during infection (an example of an injury or illness), and a prediction model 102 that outputs the user's infection state based on the user information.

The user information acquisition unit 101 functions as a derivation unit that derives differential information between the user's behavior or state at the time of diagnosis and the user's behavior or state when healthy. The prediction model 102 outputs information (infection score) indicating the user's infection state based on the differential information.

The user information acquisition unit 101 derives a difference value between the average value of the user's behavior or state during a specified period when healthy. Note that this is not limited to a difference value between the average value, and it may be a difference value between the user's behavior or state at a predetermined point in the past.

In the present disclosure, a user's behavior is defined based on the user's range of movement or the user's physical movements. A user's condition is defined based on the user's vital data. A user's behavior is defined based on the communication information that the user is operating.

With this configuration, the infectious disease estimation device 100 disclosed herein can determine the infection state of a user based on at least one of the user's behavior and state, which change when the user is infected, and output the information. When a user is infected with a specific infectious disease, changes often occur in at least one of the user's behavior and state, and based on this, the infection state can be determined without undergoing a professional diagnosis.

For example, a user's behavior indicates their range of movement and subtle body movements, and when infected, changes occur from the range of movement and subtle body movements when healthy. By utilizing this, it is possible to accurately determine the infection state.

In the present disclosure, furthermore, the predictive model 102 outputs the infection status of the user based on the user's stay history in addition to the user's behavior or status.

If a user has stayed in an infected area or in a store with a high risk of infection (e.g., a closed store or a store where infection control measures are not in place), that stay history can have a significant impact on whether the user has been infected.

The prediction model 102 is composed of a prediction model trained using the behavior or user state of multiple users as explanatory variables and the infection state of multiple users as a target variable. When the behavior or state of a single user is input, the prediction model 102 outputs the infection state of the single user.

In this disclosure, the prediction model 102 is configured as described above, and the prediction model learning device 700 performs the learning process of the prediction model 102.

This prediction model learning device 700 includes a user information acquisition unit 701 that acquires user information from a user information DB 300 that stores user information including the user's behavior or user's condition, and a learning unit 702 that learns a prediction model using the user information as an explanatory variable and the user's infection condition as a target variable. The learning unit 702 then constructs a prediction model 703 by machine learning. This prediction model 703 functions as the prediction model 102 of the infectious disease estimation device 100 of the present disclosure.

When learning the prediction model 703, the user information acquisition unit 701 may acquire information indicating the user's stay history in addition to the user information, and the learning unit 702 may learn the prediction model 703 taking into account the stay history.

In this way, by learning a predictive model based on user information as well as visit history, predictive processing based on the user's behavior or state in the user information and also on the user's visit history is possible.

In the above explanation, the infectious disease estimation device 100 has been described as an example of a device that estimates an infectious state, but this is not limited to this, and the device can also be applied to an injury/illness state estimation device that estimates any injury or illness state of the body. For example, the device can also be applied to estimating illnesses other than infectious diseases, such as injuries, and other injury/illness states.

In addition, in this disclosure, the prediction model 102 has been given as an example of a function of the prediction unit, but the present invention is not limited to using a prediction model 102 based on machine learning. For example, a score table may be provided in which a score is associated with the difference value of each item, and the infectious disease score may be calculated according to the score table.

The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or may be realized using two or more devices that are physically or logically separated and directly or indirectly connected (e.g., using wires, wirelessly, etc.). The functional blocks may be realized by combining the one device or the multiple devices with software.

Functions include, but are not limited to, judgement, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, regard, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs the transmission function is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on the method of realization for either of these.

For example, the infectious disease estimation device 100 and the predictive model learning device 700 in one embodiment of the present disclosure may function as a computer that performs processing of the infectious disease estimation method of the present disclosure. FIG. 14 is a diagram showing an example of the hardware configuration of the infectious disease estimation device 100 and the predictive model learning device 700 in one embodiment of the present disclosure. The infectious disease estimation device 100 and the predictive model learning device 700 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

In the following description, the term "apparatus" can be interpreted as a circuit, device, unit, etc. The hardware configuration of the infectious disease estimation apparatus 100 and the predictive model learning apparatus 700 may be configured to include one or more of the devices shown in the figure, or may be configured to exclude some of the devices.

The functions of the infectious disease estimation device 100 and the predictive model learning device 700 are realized by loading specific software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communications via the communication device 1004, and control at least one of the reading and writing of data in the memory 1002 and storage 1003.

The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 may be configured with a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, the above-mentioned user information acquisition unit 101 and prediction model 102 may be realized by the processor 1001.

The processor 1001 also reads out programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to these. The programs used are those that cause a computer to execute at least a part of the operations described in the above-mentioned embodiments. For example, the user information acquisition unit 101 may be realized by a control program stored in the memory 1002 and running on the processor 1001, and other functional blocks may be similarly realized. Although the above-mentioned various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may be transmitted from a network via a telecommunications line.

The memory 1002 is a computer-readable recording medium, and may be composed of, for example, at least one of a ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Erasable Programmable ROM), a RAM (Random Access Memory), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing an infectious disease estimation method according to one embodiment of the present disclosure.

Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, and the like. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other suitable medium including at least one of memory 1002 and storage 1003.

The communication device 1004 is hardware (transmission and reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc., to realize at least one of, for example, Frequency Division Duplex (FDD) and Time Division Duplex (TDD). For example, one function of the above-mentioned user information acquisition unit 101, the output unit 103, etc. may be realized by the communication device 1004. These transmission and reception functions may be implemented as a transmission unit and a reception unit that are physically or logically separated.

The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that performs output to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one configuration (e.g., a touch panel).

In addition, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

In addition, the infectious disease estimation device 100 and the prediction model learning device 700 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

The notification of information is not limited to the aspects/embodiments described in the present disclosure, and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI), Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB), System Information Block (SIB))), other signals, or a combination of these. In addition, the RRC signaling may be called an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, etc.

Each aspect/embodiment described in this disclosure may be applied to at least one of systems utilizing LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (new Radio), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth (registered trademark), or other suitable systems, and next generation systems enhanced based on these. Additionally, multiple systems may be combined (for example, a combination of at least one of LTE and LTE-A with 5G, etc.).

The processing steps, sequences, flow charts, etc. of each aspect/embodiment described in this disclosure may be reordered unless inconsistent. For example, the methods described in this disclosure present elements of various steps using an example order and are not limited to the particular order presented.

The input and output information may be stored in a specific location (e.g., memory) or may be managed using a management table. The input and output information may be overwritten, updated, or added to. The output information may be deleted. The input information may be transmitted to another device.

The determination may be based on a value represented by one bit (0 or 1), a Boolean (true or false) value, or a comparison of numerical values (e.g., a comparison with a predetermined value).

Each aspect/embodiment described in this disclosure may be used alone, in combination, or switched depending on the execution. In addition, notification of specific information (e.g., notification that "X is the case") is not limited to being done explicitly, but may be done implicitly (e.g., not notifying the specific information).

Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended as an illustrative example and does not have any limiting meaning on the present disclosure.

Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

Software, instructions, information, etc. may also be transmitted and received via a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and/or wireless technologies (such as infrared, microwave), then these wired and/or wireless technologies are included within the definition of a transmission medium.

The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

Note that the terms described in this disclosure and the terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of the channel and the symbol may be a signal (signaling). Also, the signal may be a message. Also, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

As used in this disclosure, the terms "system" and "network" are used interchangeably.

In addition, the information, parameters, etc. described in this disclosure may be represented using absolute values, may be represented using relative values from a predetermined value, or may be represented using other corresponding information. For example, radio resources may be indicated by an index.

In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" may be used interchangeably.

A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Additionally, "judgment" and "decision" can include considering resolving, selecting, choosing, establishing, comparing, etc., to have been "judged" or "decided." In other words, "judgment" and "decision" can include considering some action to have been "judged" or "decided." Additionally, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using at least one of one or more wires, cables, and printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

The "means" in the configuration of each of the above devices may be replaced with "part," "circuit," "device," etc.

When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Additionally, the term "or," as used in this disclosure, is not intended to be an exclusive or.

In this disclosure, where articles have been added through translation, such as a, an, and the in English, this disclosure may include that the nouns following these articles are in the plural form.

In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combined" may also be interpreted in the same way as "different."

100...infectious disease estimation device, 101...user information acquisition unit, 102...prediction model, 103...output unit, 200...mobile terminal, 201...communication control unit, 202...location measurement unit, 203...vital measurement unit, 204...communication information analysis unit, 205...voice analysis unit, 206...sensor, 300...user information DB, 400...purchase history DB, 500...food and beverage store DB, 600...infected area DB, 700...prediction model learning device, 701...user information acquisition unit, 702...learning unit, 703...prediction model, 800...infected person DB.

Claims (6)

A user information acquisition unit that acquires user information indicating a user's behavior that changes when the user is injured or sick , and flag information indicating an infection risk ;
A derivation unit that derives difference information between the user's behavior when diagnosed and the user 's behavior when healthy;
a prediction unit that outputs information indicating an injury or illness state of the user based on the difference information and the flag information ;
Equipped with
The user's behavior includes a purchasing behavior of the user and a movement of the user;
The flag information is acquired when a predetermined purchase item has been purchased based on the purchase history of the user stored in a purchase history DB, and is acquired when the user is in a predetermined infected area stored in an infected area DB,
The prediction unit is
the prediction model is trained using learning difference information between the behaviors of the multiple learning users at the time of diagnosis and the behaviors of the multiple learning users when healthy and learning flag information based on the behaviors of the multiple learning users as explanatory variables, and using the injury/illness states of the multiple learning users as objective variables;
the prediction model outputs the injury or illness state of the user when the difference information based on the behavior of the user and the flag information are input.
Injury/illness condition estimation device. The injury or illness state estimation device according to claim 1 , wherein the derivation unit derives, as difference information, a difference value between an average value of the user's behavior or state during a predetermined period when the user is healthy or the average value of the user's behavior or state during a predetermined period when the user is healthy. The injury or illness state estimation device according to claim 1 or 2 , wherein the user's behavior is based on communication information operated by the user. Store information is information indicating the degree of infection or the level of infection prevention measures.
The prediction model is further trained using explanatory variables in which store information at which the user has stayed is set as flag information,
The prediction unit further outputs information indicating the injury or illness state of the user based on flag information including store information where the user has stayed.
The injury/illness state estimating device according to any one of claims 1 to 3. A prediction model learning device that learns the prediction model in the injury/disease state estimation device according to any one of claims 1 to 4 ,
a user information acquiring unit that acquires user information from a user information storage unit that stores user information including user behavior for learning ;
A prediction model learning device comprising: a learning unit that learns a prediction model using the user information as an explanatory variable and the illness/injury condition of the learning user as a target variable. The user information acquisition unit acquires, in addition to the user information, information indicating a stay history of the user for learning ,
The prediction model learning device according to claim 5 , wherein the learning unit learns the prediction model by taking into account the stay history.

Images