[go: up one dir, main page]

WO2022201640A1 - Système d'intervention, procédé d'intervention et programme d'intervention - Google Patents

Système d'intervention, procédé d'intervention et programme d'intervention Download PDF

Info

Publication number
WO2022201640A1
WO2022201640A1 PCT/JP2021/043445 JP2021043445W WO2022201640A1 WO 2022201640 A1 WO2022201640 A1 WO 2022201640A1 JP 2021043445 W JP2021043445 W JP 2021043445W WO 2022201640 A1 WO2022201640 A1 WO 2022201640A1
Authority
WO
WIPO (PCT)
Prior art keywords
intervention
subject
improvement
productivity
prediction result
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2021/043445
Other languages
English (en)
Japanese (ja)
Inventor
佑子 佐野
昌宏 荻野
毅 田中
子盛 黎
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi Ltd
Original Assignee
Hitachi Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hitachi Ltd filed Critical Hitachi Ltd
Publication of WO2022201640A1 publication Critical patent/WO2022201640A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling

Definitions

  • the present invention relates to information processing service technology.
  • the present invention also relates to a technique for realizing a method of presenting intervention effects and then recommending an optimal intervention method for improving human activity productivity.
  • Patent Literature 1 discloses a method of recommending the next recommended target value of the health condition (for example, the target number of steps and the target calorie intake) based on the measured value and the target value of the health condition such as the number of steps and calories. ing.
  • the next recommended target value of the health condition for example, the target number of steps and the target calorie intake
  • the purpose of the present invention is to provide a system that presents the effects of intervention and proposes improvements to increase the activity productivity of the subject.
  • the present invention provides an intervention system that suggests to a subject and/or a user improvements in factors affecting the subject in order to improve the subject's activity productivity.
  • This intervention system For one or more of a plurality of predetermined influencing factors that affect the subject, a value representing the characteristic amount of the influencing factor is received as an input value, and a predicted value of activity productivity of the subject is output.
  • an activity productivity prediction unit including a model;
  • An improvement content list storing pre-stored improvement contents of the feature amount prepared in advance for each of the two or more influencing factors and/or two or more kinds of improvement contents of the feature amount prepared in advance for one influencing factor.
  • a no-intervention prediction result acquisition unit that acquires a value; Read out the improvement contents of the feature quantity for the influencing factor from the improvement content list storage unit, and for the remaining one or more influencing factors, receive the measured or input value representing the feature quantity of the present and/or a predetermined period up to the present. Then, the improvement content and the value representing the feature amount are input to the learning model as input values, and the process of obtaining the predicted value of the activity productivity output by the learning model is performed for each of the two or more improvement content.
  • An intervention effect calculation unit that calculates, as an intervention effect, the difference between the predicted value of activity productivity obtained by the no-intervention prediction result acquisition unit and the predicted value of activity productivity obtained by the prediction result acquisition unit with intervention for each improvement content.
  • It has a result output unit that associates two or more improvement contents with intervention effects for each improvement contents and notifies the subject and/or the user.
  • the present invention it is possible to present the optimal intervention method and its intervention effect for improving human activity productivity.
  • FIG. 1 is a block diagram showing the configuration of an intervention system according to Embodiment 1;
  • FIG. 4 is a table showing measurement data included in a measurement data DB according to Embodiment 1 and their feature amounts; 4 is a flow chart showing the processing flow of the learning phase of the activity-productivity prediction model of Embodiment 1.
  • FIG. FIG. 2 is a diagram representing baseline removal and addition of Embodiment 1;
  • 1 is a diagram showing a configuration of an activity productivity prediction model according to Embodiment 1;
  • FIG. 10 is a diagram showing processing for smoothing feature amount data of an influencing factor according to the first embodiment
  • 4 is a flowchart showing the processing flow after the prediction phase of the intervention system of Embodiment 1.
  • FIG. FIG. 4 is a flow chart showing a spread state between items of the activity-productivity prediction model of Embodiment 1;
  • FIG. 4 is a diagram showing a method of calculating an intervention effect according to Embodiment 1;
  • FIG. FIG. 2 is a diagram showing a method for determining an intervention method according to Embodiment 1;
  • FIG. FIG. 4 is a plan view showing a subject basic information management screen as an example of a display screen according to Embodiment 1;
  • FIG. 4 is a plan view showing a target person measurement data acquisition screen relating to influence factors as an example of a display screen according to Embodiment 1;
  • FIG. 4 is a plan view showing a target person measurement data acquisition screen relating to mental and physical conditions and activity productivity as an example of the display screen according to the first embodiment.
  • FIG. 4 is a plan view showing an activity productivity prediction screen as an example of a display screen according to Embodiment 1;
  • FIG. 4 is a plan view showing an intervention effect presentation screen as an example of a display screen according to Embodiment 1;
  • FIG. 4 is a plan view showing an intervention method candidate selection screen as an example of a display screen according to the first embodiment;
  • FIG. 4 is a plan view showing an intervention method determination screen as an example of a display screen according to Embodiment 1;
  • FIG. 3 is a plan view showing a screen for initial setting as an example of a display screen according to the first embodiment; 4 is a table showing subject basic information according to Embodiment 1.
  • FIG. FIG. 2 is a diagram showing a usage example of the first embodiment;
  • FIG. FIG. 11 is a block diagram showing the configuration of an activity productivity improvement system according to Embodiment 2;
  • the activity payability improvement system of this embodiment provides a service that intervenes in factors that affect the subject by means of an intervention system in order to improve the activity productivity of the subject.
  • the intervention system presents the improvement details (improvement method, post-improvement value, etc.) of the values (feature values) that represent the characteristics of the influencing factors, and the effects (intervention effects) that can be obtained when the improvement details are implemented. Make a proposal (recommendation) to
  • Notations such as “first”, “second”, “third” in this specification etc. are attached to identify the constituent elements, and do not necessarily limit the number, order, or content thereof is not. Also, numbers for identifying components are used for each context, and numbers used in one context do not necessarily indicate the same configuration in other contexts. Also, it does not preclude a component identified by a certain number from having the function of a component identified by another number.
  • FIG. 1 An activity productivity improvement system 100 according to Embodiment 1 of the present invention will be described with reference to FIGS. 1 to 20.
  • FIG. The activity productivity improvement system 100 acquires a value representing the feature amount of the factor that affects the subject by measurement or the like, and improves the feature amount of the factor that affects the subject to improve the activity productivity of the subject ( (improvement method, value after improvement, etc.) and the effect (intervention effect) when implementing the improvement content are associated and proposed (recommended) to the user.
  • the activity productivity improvement system 100 intervenes in the subject's activity and the like to improve the subject's activity productivity.
  • an activity productivity improvement system 100 that proposes (recommends) improvement contents for improving the working productivity of workers employed in companies etc.
  • the activity productivity improvement system 100 can also be applied to recommendations for practice methods.
  • FIG. 1 shows the overall configuration of an activity productivity improvement system according to a first embodiment.
  • FIG. 1 is a diagram showing the overall configuration of an activity productivity improvement system 100.
  • FIG. 2 is a diagram showing the configuration of the intervention system 1 of the activity productivity improvement system 100.
  • FIG. 3 shows an example of the feature amount of the influencing factor affecting the psychosomatic state of the subject, the feature amount of the subject's psychosomatic state, etc., collected by the measurement data collection system 2 of the activity productivity improvement system 100, and , and a diagram showing an example of data in a measurement data DB 153.
  • FIG. 1 shows the overall configuration of an activity productivity improvement system according to a first embodiment.
  • FIG. 1 is a diagram showing the overall configuration of an activity productivity improvement system 100.
  • FIG. 2 is a diagram showing the configuration of the intervention system 1 of the activity productivity improvement system 100.
  • FIG. 3 shows an example of the feature amount of the influencing factor affecting the psychosomatic state of the subject, the feature amount of the subject'
  • the activity productivity improvement system 100 comprises an intervention system 1 and a measurement data collection system 2. As described above, the activity productivity improvement system 100 has the intervention system 1 and the measurement data collection system 2 , which are connected through the wired or wireless communication line 5 .
  • the intervention system 1 is installed in a facility managed by the company's personnel department.
  • the measurement data collection system 2 is installed in a place where data collection is easy.
  • intervention system 1 and the measurement data collection system 2 may be configured as an integrated system.
  • the measurement data collection system 2 has a measurement device 3 and a data collection terminal 4, which are connected through a wired or wireless communication line 5.
  • FIG. The data collection device 3 and the data collection terminal 4 may be installed at separate locations.
  • the measuring device 3 of the measurement data collection system 2 collects values (data) that represent the characteristic quantities of the influence factors that affect the mental and physical condition of the subject, such as living conditions and work environment.
  • Devices such as wristband sensors, tablet terminals, smartphones, and PCs can be used as the measuring device 3. Each of these devices may be configured to collect a value representing one feature amount, or may also collect a plurality of predetermined types of data.
  • the data measured by the measuring device 3 is collected by the data collection terminal 4.
  • the values (data) representing the feature amounts of some or all of the influencing factors may be input by the subject or the user (operator) on the input screen displayed on the display unit of the data collection terminal 4. In that case, the data collection terminal 4 collects the data of the value representing the feature quantity by accepting the input value.
  • influencing factors are set in advance: "interpersonal interaction", “lifestyle habits”, “indefinite complaints”, “meal”, and “sleep”.
  • a plurality of types of feature amounts are set for each influencing factor.
  • four types of “drinking amount”, “smoking amount”, “exercise amount”, and “exercise time” are set as the characteristic amount of "lifestyle habit” of the influencing factor.
  • the exercise amount and exercise time are measured by an exercise sensor (wristband type sensor) worn by the user.
  • the amount of drinking and the amount of smoking are input by the subject or the user (operator) on the input screen displayed by the data collection terminal 4 on the display unit, and the data collection terminal 4 receives the input values to collect them.
  • FIG. 3 also describes the mental and physical conditions and activity productivity, which are used when learning the learning model (activity productivity prediction model), but are not used when making predictions by the activity productivity prediction model. Therefore, the measurement data collection system 2 does not collect them.
  • the intervention system 1 has a function of providing an improvement content recommendation service as a service for intervening influencing factors of a subject by information processing.
  • This function receives the value (data) of the feature amount of the influencing factor from the measurement data collection system 2, and based on them, determines the factors influencing the subject in order to improve the activity productivity of the subject. It proposes (intervenes in) the content of improvement to the user. At this time, the effect (intervention effect) when implementing the improvement content is also output to the user together with the improvement content.
  • the user to whom the intervention effect is to be output is not limited to the operator, and includes the target person.
  • the intervention system 1 has an input unit 11, an output unit 12, a communication unit 13, a control unit 14, a storage unit 15, etc., which are connected via a bus 16.
  • the input unit 11 is a part for inputting operations by the administrator of the intervention system 1 or the like.
  • the output unit 12 is a part that displays a screen or the like for the administrator of the intervention system 1 or the like.
  • the communication unit 13 has a communication interface and performs communication processing with the measurement data collection system 2 .
  • Control unit 14 includes a data processing unit 140 .
  • the data processing unit 140 has a subject basic information management unit 141 , a subject measurement data acquisition unit 142 , an activity productivity prediction unit 143 , an intervention effect calculation unit 144 , an improvement content determination unit 145 and a result output unit 146 .
  • the data processing unit 140 has a function of inputting data from the measurement data collection system 2, a function of processing and analyzing the measurement data, a function of outputting control instructions to the measurement data collection system 2, and a data collection terminal 4. It implements functions such as outputting data for display.
  • the control unit 14 also controls the intervention system 1 as a whole.
  • the storage unit 15 includes a subject basic information storage unit 151, a subject measurement data storage unit 152, a measurement data DB 153, an activity productivity prediction model storage unit 154, an activity productivity prediction result storage unit 155, and a spillover state calculation result storage unit 156. , an intervention effect calculation result storage unit 157 , an optimum improvement content storage unit 158 , and a management table storage unit 159 .
  • Measurement data DB storage unit 153 In the measurement data DB 153 of the storage unit 15, the data of the influence factors and the feature amounts of the psychosomatic state in FIG. Data indicating time-series changes in values indicating feature quantities of activity productivity at the time of measurement and after that are stored in association with each other.
  • Activity productivity as shown in FIG. 3, is work performance here. Use the results of measuring the error rate of
  • the management table storage unit 159 of the storage unit 15 stores a list (improvement content list 159C) of previously prepared feature quantity improvement details (improvement methods and/or feature quantity values after improvement) for the influencing factors.
  • a list improved content list 159C
  • feature quantity improvement details improved methods and/or feature quantity values after improvement
  • the improvement content list 159C includes three types of exercise habit improvement menus for 10 minutes of training.
  • the improvement content list 159C contains two or more improvement content. As for these improvement contents, one or more improvement contents may be prepared for two or more influencing factors, or two or more improvement contents may be prepared for one influencing factor.
  • the target person basic information management unit 141 of the control unit 14 registers and manages the target person basic information input by the target person or the administrator in the target person basic information storage unit 151, and manages the target person's service use. At this time, processing for confirming the subject basic information storage unit 151, etc. is performed.
  • the target person basic information registered in the target person basic information storage unit 151 includes attribute value usage history information for each individual target person, target person setting information, and the like. Attribute values include gender, age, department, position, company history, personnel evaluation data, and the like.
  • the usage history information includes information for managing the history of the subject's usage of the services provided by this system.
  • Subject Setting Information includes setting information set by the Subject or the administrator regarding the functions of the Service.
  • the subject measurement data acquisition unit 142 requests, via the communication unit 13, the measurement data collection system 2 to collect feature data of predetermined influencing factors affecting the psychosomatic state of the subject,
  • the data collected by the measurement data collection system 2 is received and stored in the subject measurement data storage unit 152 .
  • the subject measurement data acquisition unit 142 refers to the influence factor evaluation list 159A and the mental and physical condition evaluation list 159B stored in advance in the management table storage unit 159, and selects items of data to be collected from the measurement data collection system 2. It is good also as a structure which determines.
  • the activity productivity prediction unit 143 has a prediction model generation unit 143A that generates a learning model (prediction model) that outputs a prediction value of the activity productivity of the subject using a value representing the feature amount of the influence factor as an input value; It is composed of a result calculation instructing section 143B and an influence state calculating section 143C.
  • a prediction model generation unit 143A that generates a learning model (prediction model) that outputs a prediction value of the activity productivity of the subject using a value representing the feature amount of the influence factor as an input value; It is composed of a result calculation instructing section 143B and an influence state calculating section 143C.
  • the predictive model generation unit 143A reads out the feature amount data of influence factors and mental and physical states of many people stored in the measurement data DB 153 of the storage unit 15, and the data of the time change of the feature amount of activity productivity. , the data of the feature amount of the influence factor and the mental and physical state are used as input data, and the data of the time change of the feature amount of the activity productivity is used as the correct data, and the machine learning (AI) method is applied to learn the learning model. As a result, an activity productivity prediction model is generated and stored in the activity productivity prediction model storage unit 154 of the storage unit 15 .
  • the prediction result calculation instructing unit 143B of the activity productivity prediction unit 143 reads out the feature amount data of the environmental factor measured by the measurement data collection system 2 for the target person from the measurement data storage unit 152, and prepares the activity productivity prediction model. It is input as an input value of the activity productivity prediction model stored in the storage unit 154, and the time change from the present to the future of the feature amount of the activity productivity is output as a prediction result.
  • the prediction result calculation instructing unit 143 ⁇ /b>B stores the obtained time change (time-series data) of the feature amount of activity productivity in the activity productivity prediction result storage unit 155 .
  • the activity productivity prediction unit 143 uses the data of the characteristic amount of the environmental factor for the current and/or up to the current predetermined period measured by the measurement data collection system 2 as the activity productivity. It is input to the prediction model, and the temporal change in the feature amount of the activity productivity output by the activity productivity prediction model from the present to the future for a predetermined period is acquired. The obtained temporal change of the feature amount of activity productivity is stored in the activity productivity prediction result storage unit 155 as a prediction result without intervention.
  • the activity productivity prediction unit 143 reads the improvement contents of the feature amount for the influence factor from the improvement content list storage unit in order to obtain the prediction result with intervention, and the feature amount for the remaining influence factors is obtained by the measurement data collection system. 2 receives the value representing the feature amount of the present and/or the predetermined period up to the present measured, etc., inputs the improvement content and the value representing the feature amount into the activity productivity prediction model as input values, and predicts the activity productivity A time change of the current and/or future activity productivity feature output by the model is obtained. This processing is performed for each of two or more improvement contents, and the temporal change in the feature amount of activity productivity obtained for each is stored in the activity productivity prediction result storage unit 155 as a prediction result with intervention.
  • the spillover state calculation unit 143C identifies how changes in data items in the activity productivity prediction model spread to other items. Specifically, the influence state calculation unit 143C calculates the influence state in which the activity productivity is affected by the influence factor via the psychosomatic state. This will be explained in detail later with reference to FIG.
  • the intervention effect calculation unit 144 includes a no-intervention prediction result acquisition unit 144A, an intervention prediction result acquisition unit 144B, and an intervention presence/absence difference calculation unit 144C.
  • the non-intervention prediction result acquisition unit 144A acquires the non-intervention prediction result (temporal change in feature amount of activity productivity) stored in the activity productivity prediction result storage unit 155 .
  • the interventional prediction result acquisition unit 144B acquires interventional prediction results (temporal changes in activity productivity feature amounts) stored in the activity productivity prediction result storage unit 155 for each improvement content.
  • the intervention presence/absence difference calculation unit 144C calculates the difference (time change) between the prediction results obtained by the no-intervention prediction result acquisition unit 144A and the intervention prediction result acquisition unit 144B, and stores it in the intervention effect calculation result 157 as an intervention effect.
  • the improvement content determination unit 145 includes a multiple intervention effect acquisition unit 145A and an optimal improvement content determination unit 145B.
  • the multiple intervention effect acquisition unit 145A acquires intervention effects (time-series data) for each of two or more improvement contents stored in the intervention effect calculation result 157.
  • the optimum improvement content determination unit 145B compares the effects of intervention and determines the improvement content recommended to the user based on the comparison results.
  • the improvement content determination unit 14B based on at least one or more of the magnitude of the intervention effect at one or more predetermined points in time, the speed of change over time of the intervention effect, and the stability of change over time of the intervention effect, Decide what improvements to recommend to users.
  • the result output unit 146 outputs the calculated intervention effect for each improvement content, the recommended improvement content, and the like to the user (subject or operator). Specifically, for example, it is displayed on a screen of a PC monitor, a tablet terminal, or the like from the output unit 12 . Also, it may be displayed on the screen of the data collection terminal 4 via the communication unit 13 .
  • the control unit 14 in FIG. 2 is composed of a Central Processing Unit (CPU), Read Only Memory (ROM), Random Access Memory (RAM), etc., and the CPU executes a software program stored in advance in the ROM. , realizes the function of each unit in the data processing unit 140 .
  • CPU Central Processing Unit
  • ROM Read Only Memory
  • RAM Random Access Memory
  • FIG. 3 shows the items of feature amounts for one of a large number of subjects who are data acquisition targets for the measurement data DB. It should be noted that the feature amounts of the environmental factors collected by the measurement data collection system 2 for the intervention target are the same items as the feature amounts of the environmental factors in FIG. 3 .
  • Influence factor feature amount data, psychosomatic state feature amount data, and activity productivity feature amount data in FIG. 3 are all acquired at the frequency shown in FIG. 3 over the period shown in FIG. It is time-series data that
  • Influence factors include interpersonal interaction, lifestyle, indefinite complaints, meals, and sleep data.
  • Interpersonal interaction is extracted (measured) from the conversation frequency, conversation volume, number of conversations, and emails accumulated in mailers, which are extracted (measured) from the voices of the other party and the person themselves recorded with a microphone during web conferences and telephone conferences.
  • e-mail frequency/e-mail transmission time, and the number of meetings/free time extracted from the scheduler are used as feature quantities.
  • the lifestyle habits are characterized by the amount of drinking and smoking obtained from questionnaires, and the amount of exercise and exercise time obtained from exercise sensors worn on the body, such as wristband-type acceleration sensors. From the exercise time data, it is also possible to extract the time spent doing desk work and walking time.
  • Indefinite complaints are characterized by the strength of headache, back pain, and stiff shoulders, which are evaluated by a questionnaire.
  • Meals are characterized by meal times and nutritional balance obtained from questionnaires. In addition to the questionnaire, it is also possible to ask the subject or the subject to take a picture of the content of the meal, and to perform image analysis on the content.
  • Sleep is characterized by sleep time and sleep quality (depth) measured by the motion sensor described above.
  • the feature values of these influencing factors can change daily depending on the environment, so the frequency of measurement is daily.
  • the physical and mental state feature data includes cognitive function, motor function, and mental function data.
  • Cognitive function is characterized by processing speed, strength of inhibitory function, memory, etc., evaluated by conducting cognitive function tests using applications such as PCs, tablet terminals, and smartphones.
  • the feature amount may be evaluated using a questionnaire for evaluating and scoring cognitive functions, such as MMSE or the Hasegawa simple intelligence scale.
  • Motor function is measured by image analysis while performing a given exercise, and features such as endurance, balance, reaction speed, and muscle strength are extracted from the measurement data.
  • a wearable sensor such as the wristband acceleration sensor described above may be used to measure the feature amount.
  • Mental functions are characterized by stress, depressive tendencies, self-affirmation, etc. obtained from questionnaires.
  • the heart rate may be measured to evaluate the autonomic nerves and used as the feature quantity of the stress value.
  • the amount of dialogue, the amount of e-mails, the tone of voice, and the frequency of typing on the keyboard may be used as feature amounts of the depression tendency.
  • activity productivity is defined as work performance
  • input frequency and error rate measured by PC keyboard input are used as feature quantities.
  • the number of contracts for sales positions, the number of paperwork for clerical jobs, and the like may be used as feature amounts of performance according to job type.
  • activity productivity can be defined as subjective evaluation results such as work engagement, which expresses enthusiasm and devotion to work. Not only self-evaluation but also evaluation by others may be used. Also, personnel evaluation data may be used.
  • the above feature values are time-series data measured regularly, such as every day or once a week, for a certain period of time, such as three months. Each piece of data is provided with the measurement date and time.
  • FIG. 3 shows the measurement data of the feature amount for one person, the measurement data DB 153 stores the feature amount for many subjects.
  • the measurement data collection system 2 converts the feature values of the environmental factors shown in FIG. 3 for the intervening subject into time-series data that is regularly measured every day or once a week for a certain period of time, such as three months. Although it is desirable to collect and store in the measurer measurement data storage unit 152, it is also possible to collect only the current feature amount.
  • FIG. 4 is a processing flow of the activity productivity prediction model learning phase performed by the prediction model generation unit 143A of the first embodiment.
  • FIG. 5 is a diagram for explaining preprocessing (removal/addition of baseline) of data of features of psychosomatic state and activity productivity used for learning.
  • FIG. 6 is a diagram showing the structure of a learning model.
  • FIG. 7 is a diagram for explaining preprocessing (smoothing processing) of feature amount data of environmental factors.
  • the prediction model generation unit 143A generates an activity productivity prediction model through steps LS1 to LS3. The steps will be described below.
  • Step LS1 The prediction model generation unit 143A uses the feature amount data of the influence factors, the feature amount data of the physical and mental conditions, and the feature amount data of the activity productivity stored in the measurement data DB 153 to be used for learning the activity productivity prediction model. read out.
  • Step LS2 The prediction model generation unit 143A performs preprocessing for inputting the data of the influence factor, the psychosomatic state, and the feature amount of each of the activity productivity acquired in step LS1 into the activity productivity prediction model.
  • the prediction model generation unit 143A subtracts the date and time of the first measurement from the date and time of measurement given to the data for one person, thereby making the date and time elapsed from the start of measurement a time stamp.
  • the prediction model generation unit 143A interpolates the data by arranging the data with the shortest measurement frequency. For example, in the example of FIG. 3, the feature amount is measured every day or once a week. interpolate to As the interpolation process, the prediction model generator 143A performs spline interpolation if the data is a continuous value, and rounds off to the nearest value after the spline interpolation if the data is a discrete value.
  • the interpolation process does not have to be spline interpolation, and for example, linear interpolation, Lagrangian interpolation, or an interpolation method that fills in the same value as the immediately preceding measurement data may be used.
  • the prediction model generating unit 143A may perform baseline removal shown in FIG. 5 on the data of feature amounts of psychosomatic state and activity productivity as preprocessing. This is to improve the prediction accuracy by removing prediction errors due to individual differences in the phase (prediction phase) in which prediction is performed using the activity productivity prediction model.
  • the prediction result calculation instructing unit 143B only gives the feature amount data of the influence factor as an input variable (input value) to the activity productivity prediction model, and the feature amount data of the psychosomatic state and the activity productivity is don't give For this reason, in the prediction phase using the activity productivity prediction model, if the feature amount data of the influencing factors that represent the living situation and work environment are the same, the same activity is performed without considering the individual's internal state (physical and mental state). A productivity prediction result is output.
  • the activity productivity prediction result by the activity productivity prediction model fluctuates by the amount corresponding to the individual difference, and the accuracy decreases.
  • the prediction model generation unit 143A sets the value (baseline) at the start of measurement to zero for the feature amount data of the psychosomatic state and the feature amount data of the activity productivity. You may perform the process (baseline removal) which subtracts so that it may become. This eliminates individual differences in the original activity productivity, and allows attention to be paid only to changes in activity productivity.
  • the prediction model generation unit 143A generates a prediction model using the data after the processing of removing the baseline from the feature amount data of the psychosomatic state and the feature amount data of the activity productivity. , the change in activity productivity is output as a prediction result.
  • baseline addition processing is performed to add or multiply the subject's baseline to the feature amount data of the predicted physical and mental state and the feature amount data of activity productivity.
  • the subject measurement data acquisition unit 142 provides the measurement data collection system 2 with the feature amount data of the physical and mental conditions in addition to the feature amount data of the environmental factors. and activity productivity feature amount data, and the prediction result calculation instructing unit 143B inputs these data to the prediction model as input data.
  • Step LS3 the prediction model generation unit 143A learns an activity productivity prediction model (learning model) using the preprocessed data.
  • the prediction model generation unit 143A uses a recurrent neural network (RNN) as an example of a learning model, as shown in FIG. Series data is input, and the output layer (output variable) inputs time-series data of feature values of activity productivity as correct data.
  • RNN recurrent neural network
  • a recurrent neural network can represent time-series data with the hidden layer becoming a latent variable by recursively inputting itself into the hidden layer.
  • the prediction model generation unit 143A can accurately predict (output) the activity productivity when inputting the data of the feature amount of the influence factor into this model.
  • the prediction model generation unit 143A inputs the feature amount data of the psychosomatic state to the hidden layer of the RNN, and performs learning so that the output of the hidden layer has a smaller error from the feature amount data of the psychosomatic state.
  • LSTM Long short-term memory
  • LSTM Long short-term memory
  • Any method other than RNN may be used as long as it is a machine learning method that can handle time-series data.
  • a hidden Markov model HMM
  • HMM hidden Markov model
  • the prediction model generation unit 143A may smooth the feature amount data of the influence factor before inputting it to the input layer of the learning model, as shown in FIG. Therefore, the prediction model generator 143A may perform smoothing filter processing in the learning model.
  • the feature amount data of the influencing factors that are put into the input layer have different effects on the mental and physical state depending on their properties. For example, influencing factors affecting depression are thought to be social interaction and nutrition. In interpersonal interaction, daily fluctuations sharply affect depressive states, but in nutrition, daily fluctuations are not important, and only large fluctuations over a period of about one month are presumed to affect depressive states.
  • time-series data of interpersonal interaction into the RNN as it is, but the time-series data of nutrition is smoothed with a smoothing filter to remove fluctuation components (high-frequency components) in cycles of one day to one week. It is considered desirable to input to the RNN at . As a result, learning progresses at an early stage, and convergence is likely to be facilitated even with a small amount of data.
  • the prediction model generation unit 143A performs filtering for smoothing in the direction of the time axis immediately after the input layer of the RNN.
  • the strength of smoothing is determined for each property of .
  • the weight that determines the strength of smoothing is 0 to 1 (0 is no smoothing, 1 is the maximum smoothing)
  • the weight given to the combination of [interpersonal interaction x depressive state] is 0, [nutrition x depressive state ] is determined to be 1.
  • the time-series data of the feature amount of interpersonal interaction is divided into five regions along the time axis, and the data in each region is smoothed into a single value [0, 0, 1, 0, 0].
  • the time-series data of the nutritional feature amount is divided into five regions in the time axis direction, and the data in each region is smoothed [0.2, 0.2, 0.2, 0.2, 0. 2] is applied.
  • the interpersonal interaction data is the same as the raw data, but the nutrition data is smooth data without high-frequency components.
  • the numerical values in the filter are proportionally distributed according to the weight.
  • a smoothing filter is used here, other methods such as a low-pass filter, a median filter, etc. may be used as long as they are capable of smoothing.
  • Step LS4 The predictive model generation unit 143A stores the learned model obtained in step LS3 in the activity productivity predictive model storage unit 154.
  • Step PS1 The subject's environmental factor feature amount data collected by the measurement data collection system 2 is stored in the subject's measurement data storage unit 152 .
  • the prediction result calculation instructing unit 143B acquires feature amount data of the subject's environmental factors from the measurement data storage unit 152 .
  • Step PS2 The prediction result calculation instructing unit 143B performs the same preprocessing as the preprocessing performed in step LS2 on the data of the feature amount of the influence factor acquired in the previous step.
  • Step PS3 The prediction result calculation instruction unit 143B inputs the feature amount data of the influence factor processed in the previous step to the learned activity productivity prediction model stored in the activity productivity prediction model storage unit 154, and performs prediction. Calculating and outputting the result (time-series data of feature quantity of activity productivity).
  • the prediction result calculation instructing unit 143B outputs time-series changes in the feature amount of the psychosomatic state from the hidden layer of the activity productivity prediction model as necessary.
  • Step PS4 The non-intervention prediction result acquisition unit 144A stores the prediction result output by the activity productivity prediction model in the activity productivity prediction result storage unit 155 as a non-intervention prediction result.
  • Step PS5 The prediction result calculation instructing unit 143B stores the learned activity productivity prediction model stored in the activity productivity prediction model storage unit 154 with the improvement contents of the environmental factors and the feature amount of the influence factor processed in the previous step. data to calculate and output prediction results (time-series data of feature values of activity productivity).
  • the prediction result calculation instructing unit 143B outputs time-series changes in the feature amount of the psychosomatic state from the hidden layer of the activity productivity prediction model as necessary.
  • Step PS6 The prediction result acquisition unit 144B with intervention stores the prediction result output by the activity productivity prediction model in the activity productivity prediction result storage unit 155 as a prediction result with intervention.
  • Step PS7 The prediction result calculation instruction unit 143B and the intervention prediction result acquisition unit 144B repeat steps PS5 and PS6 for all of the plurality of improvement details selected from the improvement content list 159C.
  • Step PS8 The intervention presence/absence difference calculation unit 144C calculates an intervention effect for each improvement content, and the result output unit 146 displays the improvement content and the intervention effect in correspondence with each other on a display device or the like, and presents them to the subject or the user.
  • Step PS9 The optimum improvement content determination unit 145B selects the optimum improvement content based on the intervention effect, and the result output unit 146 displays the optimum improvement content and presents it to the subject and the user.
  • intervention system 1 of the present embodiment it is possible to present the effects of intervention and then propose improvement details for increasing the subject's activity productivity.
  • the ripple state calculation unit 143C identifies how a change in a data item in the activity productivity prediction model affects other items.
  • the prediction result calculation instructing unit 143B not only acquires the feature amount of activity productivity from the activity productivity prediction model in step PS5, Output changes over time in predicted values of cognitive function feature values.
  • the influence state calculation unit 143C determines the time points (change points) 902 to 904 at which the predicted values of the feature amounts of motor function, cognitive function amount, and activity productivity start to improve, for example, the feature amount of each function is set from the initial value to a predetermined value. It is obtained by calculating the point in time when the percentage (for example, 10%) increases.
  • the point of change may be defined by the point of time when improvement ends, the point of time when the rate of change is greatest, or the like, in addition to the point of time when improvement begins.
  • the influence state calculation unit 143C starts improving motor function at time 902 three days after improving the exercise habit, starts improving cognitive function at time 903 one week later, and further improves one week. At a later point in time 904, it can be seen that the improvement in activity productivity has begun.
  • the influence state calculation unit 143C draws the graph of the predicted value so that the graph is arranged in the order in which the change points 902 to 904 occur so that the relationship between the calculated change points 902 to 904 can be understood.
  • a graph is generated as shown in FIG. 9A to be presented to the user in order of function and activity productivity. By viewing FIG. 9(a), the user can understand that the activity productivity is affected by the influencing factor via the psychosomatic state.
  • the spillover state calculation unit 143C may add a numerical value or the like indicating the number of delay days to the user on the generated graph, as shown in FIG. 9(a).
  • the spillover state calculation unit may generate a chart that simply illustrates the causal relationship between items and the number of days of delay, as in FIG. 9(b).
  • the non-intervention prediction result acquisition unit 144A obtains the activity productivity prediction result when no intervention is performed with respect to the influence factors such as the living situation and the work environment that affect the mental and physical condition of the subject, and performs the intervention. No prediction result. That is, the activity productivity prediction unit 143 inputs the feature amount data of the environmental factors of the present and/or the predetermined period up to the present measured by the measurement data collection system 2 into the activity productivity prediction model, and calculates the activity productivity. A time change in the feature amount of activity productivity output by the prediction model from the present to the future for a predetermined period is acquired, and stored in the activity productivity prediction result storage unit 155 as a prediction result without intervention. The non-intervention prediction result acquisition unit 144A acquires the non-intervention prediction result (time change of feature amount of activity productivity) stored in the activity productivity prediction result storage unit 155 as shown in FIG.
  • the interventional prediction result acquisition unit 144B selects the improvement content from the improvement content list 159C of the management table storage unit 159,
  • the activity productivity prediction result when this improvement is implemented is obtained and used as a prediction result with intervention. That is, the activity productivity prediction unit 143 reads out the improvement content of the feature amount for the influence factor from the improvement content list storage unit, and for the feature amount of the remaining influence factor, the current and / or A value representing a feature amount for a predetermined period up to the present is received, the improvement content and the value representing the feature amount are input to the activity productivity prediction model as input values, and the current and/or predetermined period output by the activity productivity prediction model Obtain the temporal change of the feature quantity of the future activity productivity of the period.
  • This processing is performed for each of two or more improvement contents, and the temporal change in the characteristic quantity of activity productivity obtained for each is stored in the activity productivity prediction result storage unit 155 as a prediction result with intervention.
  • the intervention-implemented prediction result acquisition unit 144B acquires the intervention-implemented prediction result (temporal change in feature amount of activity productivity) stored in the activity productivity prediction result storage unit 155 for each improvement content as shown in FIG. . However, in FIG. 10, one prediction result with intervention is displayed.
  • the intervention presence/absence difference calculation unit 144C calculates the time-series data obtained by subtracting the prediction result without intervention from the prediction result with intervention, and defines this as the intervention effect.
  • a value obtained by dividing the prediction result with intervention by the prediction result without intervention may be calculated, and this time-series data may be used as the intervention effect.
  • the intervention effect is stored in the intervention effect calculation result 157 .
  • the intervention effect calculation unit 144 performs chronological interventions for three types of improvement per day: (a) walking for 30 minutes, (b) running for 30 minutes, and (c) muscle training for 10 minutes. effects have been calculated.
  • the improvement content determination unit 145 selects the optimal intervention effect based on a predetermined standard from the character sequence data of the three intervention effects obtained, and obtains the improvement content corresponding to the optimal intervention effect.
  • the predetermined criteria are (1) magnitude of intervention effect at a point in time; (2) speed of time change of intervention effect; (3) Use at least one of the stability of intervention effects over time.
  • the criterion of (1) is selected and the criterion is set to judge that the improvement content with the largest intervention effect after 8 weeks from the start of intervention (implementation of improvement content) is optimal, ( The 10-minute muscle training in c) is the optimum content of improvement.
  • the user predefines criteria based on one of (1), (2), and (3), or a combination of multiple criteria, depending on the purpose.
  • criteria (1) and (2) among multiple time-series data on intervention effects
  • the value of the intervention effect with the highest evaluation is set to 1, and the other normalize the intervention effect data.
  • the size of the intervention effect after normalization can be compared.
  • the value of the intervention effect may be weighted according to the degree of importance, and the optimum content of improvement may be determined using the value of the intervention effect after weighting.
  • FIG. 12 shows an example of a screen displayed on a PC monitor, a tablet terminal, or the like from the output unit 12 by the target person basic information management unit 141 to receive input of the target person's basic information from the target person or administrator. .
  • the subject basic information management unit 141 may display this screen on the data collection terminal 4 via the communication unit 13 .
  • the screen in FIG. 12 includes a subject information column 12001 and a scanning menu column 12002.
  • the target person information column 12001 has fields for entering the target person ID, name, date of birth, gender, department, position, company history, personnel evaluation, and the like. Such information may be automatically obtained in association with the ID of the personnel system, in addition to being input by the administrator or the subject.
  • a measurement data acquisition (influence factor) button 12002-1 a measurement data acquisition (mental and physical state/activity productivity) button 12002-2, an activity productivity prediction button 12002-3, and an intervention effect presentation button 12002- 4.
  • an improvement content recommendation button 12002-5 When the subject or user (operator) presses buttons 12002-1 to 12002-2, the screens shown in FIGS. 13 to 17 are displayed.
  • the screen of FIG. 13 is displayed when the measurement data acquisition (influence factor) button 12002-1 is pressed on the screen of FIG.
  • the screen of FIG. 13 is an example of a screen on which the subject measurement data acquisition unit 142 shows the user the conditions for collecting the values of the feature amounts of the influence factors of the subject and the collected data.
  • the subject measurement data acquisition unit 142 acquires data from the system and sensors of the measurement data collection system 2, and displays the acquired data to the subject on this screen. do.
  • the feature quantity conversation frequency is "10 times / day” and the conversation volume is "1 time/day” and the number of conversations is “3 people/day”, and the results are displayed.
  • the screen in Fig. 13 is configured so that the subject or user can manually input by pressing the input button.
  • the amount of alcohol consumed which is a characteristic quantity of lifestyle habits, can be input by selecting "1 drink/week" from a plurality of options.
  • the subject presses the save button to return to the subject basic information management screen (FIG. 12).
  • the screen in FIG. 14 is displayed when the measurement data acquisition (psychological state/activity productivity) button 12002-2 is pressed on the screen in FIG.
  • the screen of FIG. 14 is an example of a screen on which the subject measurement data acquisition unit 142 shows the user the conditions for collecting the values of the feature amounts of the psychosomatic state and activity productivity of the subject and the collected data.
  • step LS2 when the prediction model generation unit 143A removes the baseline shown in FIG. Collect data on features of mind-body state and activity productivity.
  • the item displayed as automatic measurement is that the subject measurement data acquisition unit 142 acquires data from the system and sensors of the measurement data collection system 2, and sends the acquired data to the subject on this screen.
  • evaluation values such as processing speed, inhibitory function, and memory, which are feature quantities, are acquired using a cognitive function application that operates on a tablet terminal.
  • input frequency and error rate are obtained as indices related to work performance from PC keyboard input.
  • the acquired feature amount is displayed on the screen in FIG.
  • the subject manually enters them by pressing the input button. For example, in the item of stress, which is a characteristic quantity of mental function, the subject selects "2" from options of 0 to 10 on a scale of 10. After completing the input, the subject presses the save button to return to the subject basic information management screen.
  • step LS2 if the prediction model generating unit 143A predicts the value of activity productivity as it is without removing the baseline, or even if the baseline is removed, the change in activity productivity If it is sufficient to predict only the data, there is no need to perform input on this screen.
  • the user can decide whether or not to remove the baseline by the prediction model generation unit 143A on the administrator setting screen. This should be consistent with whether or not to remove the baseline in the predictive model generator 143A.
  • FIG. 15 The screen of FIG. 15 is displayed when the activity productivity prediction button 12002-3 is pressed on the screen of FIG.
  • the screen of FIG. 15 is a screen for displaying the activity productivity prediction result output from the prediction result calculation instructing section 143B of the activity productivity prediction section 143.
  • the screen of FIG. 15 includes an activity productivity prediction result column 15001 and an intervention influence state column 15002.
  • the activity productivity prediction result column 15001 displays the value of the predicted feature amount of activity productivity.
  • the content of improvement (improvement of exercise habits), the time change of the feature amount of activity productivity when it is implemented, and the time change of the prediction result of the feature amount of motor function and cognitive function are also included. are displayed together.
  • a time-series graph of each feature amount is displayed in the order of change time points calculated by the influence state calculation unit 143C.
  • intervention spillover state column 15002 may be simply displayed in a graph structure as shown in FIG. 9(b).
  • the screen of FIG. 16 is displayed when the intervention effect presentation button 12002-4 is pressed on the screen of FIG.
  • the screen of FIG. 16 is a screen that displays the intervention effect calculation result 157 obtained by the intervention effect calculation unit 144 .
  • the screen of FIG. 17 is displayed when the improvement content recommendation button 12002-5 is pressed on the screen of FIG.
  • the screen of FIG. 17 is a screen for selecting a plurality of candidate improvement contents in order to determine the optimum improvement contents in the optimum improvement contents determination unit 145B. It is configured to accept selection of a plurality of improvement contents.
  • the improvement content related to improvement of exercise habits is selected, but it is also possible to select different types of improvement content other than improvement of exercise habits.
  • the screen of FIG. 18 is an example of a screen displaying the optimum improvement content determined by the optimum improvement content determination unit 145B.
  • the activity productivity when each improvement content is implemented is predicted by the prediction result calculation instructing unit 143B using the prediction model 154.
  • 145 A of intervention effect acquisition parts calculate an intervention effect about each improvement content.
  • the optimum improvement content determination unit 145B compares intervention effects for each improvement content and determines the optimum improvement content.
  • the screen in FIG. 18 includes an optimal improvement content column 18001 and an intervention effect comparison column 18002.
  • the optimum improvement content column 18001 displays the optimum improvement content determined by the optimum improvement content determination unit 145B from among the improvement content candidates selected on the improvement content candidate selection screen in FIG.
  • the time-series data of the intervention effect for each improvement content is superimposed and the intervention effect can be easily compared.
  • sentences explaining the criteria for determining the content of improvement are also displayed.
  • the magnitude of the intervention effect after 4 weeks has passed since the start of the intervention is used as a determination criterion, and the magnitude of the intervention effect after 4 weeks has passed is displayed in the graph for each improvement content.
  • FIG. 19 shows a screen for initial setting of the activity payability improvement system 100 of this embodiment. This is a screen for setting by a system administrator such as a person in charge of human resources before starting to use this system.
  • baseline removal column 19001 the presence or absence of baseline removal shown in FIG. 5 is specified.
  • the strength of smoothing is specified for each property of the effect factor shown in FIG. 7 (0 is no smoothing, 1 is maximum smoothing).
  • the display method of the spillover status is specified.
  • the influence factor ⁇ psychosomatic state ⁇ the ripple state of activity productivity is displayed, or the influence factor ⁇ the ripple state of activity productivity is displayed by omitting the ripple state of the psychosomatic state in the middle. You can choose to display or not to display the spillover status.
  • FIG. 20 shows the data structure in the subject basic information storage unit 151 managed by the subject basic information management unit 141. As shown in FIG. In addition to the information input on the subject basic information management screen of FIG. Quantitative data are also associated.
  • the activity productivity prediction unit 143 calculates the activity productivity prediction result storage unit 155, and the intervention effect calculation unit 144 calculates the intervention prediction result By calculating the difference between the prediction result without intervention and the intervention effect calculation result 157, the improvement content determination unit 145 compares the time-series data of a plurality of intervention effects, thereby determining the optimum improvement content. This allows the subject and the manager to know the content of improvement suitable for improving the activity productivity of the subject and the effect of intervention when it is implemented.
  • FIG. 21 shows a usage example of the activity payability improving system 100 of the first embodiment.
  • the customer is the personnel department of a company, and the customer's problem is low employee productivity and insufficient corporate profits.
  • the personnel department selects employees with low productivity from among the employees and applies the activity payability improvement system 100 of the first embodiment. Specifically, it acquires feature data on influencing factors, physical and mental conditions, and activity productivity, and presents to employees the optimal improvement details and the effects of intervention when they are implemented.
  • Embodiment 2 An activity productivity improvement system according to Embodiment 2 of the present invention will be described with reference to FIG.
  • the basic configuration of the second embodiment is the same as that of the first embodiment, but differs from the first embodiment in that the intervention system 1 is arranged in the server of the service provider.
  • the intervention system 1 is arranged in the server 6 of the service provider.
  • the measurement data collection system 2 is arranged in the target person's home or company, as in the first embodiment.
  • the intervention system 1 and the measurement data collection system are connected via a communication network 7 .
  • a plurality of measurement data collection systems 2 may be provided for each subject, or may be shared equipment within a company.
  • the communication network 7 and the server 6 may be configured in a cloud computing system.
  • the server 6 is a device under the jurisdiction of the service provider.
  • the server 6 realizes a function of providing an improvement content recommendation service similar to the intervention system 1 of the first embodiment to the target person and company administrator as a service based on information processing.
  • the server 6 provides service processing to the measurement system in a client-server manner.
  • the server 6 has a subject management function and the like.
  • the target person management function is a function of registering, accumulating, and managing target person information, measurement data, recommendation results, etc. of a group of subjects obtained through a plurality of systems 2 in a DB.
  • the present invention is not limited to the above-described embodiments, and includes various modifications. For example, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Moreover, it is possible to add, delete, or replace a part of the configuration of each embodiment with the configuration of another embodiment.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

L'invention concerne un système qui propose, après présentation d'effets d'intervention, le contenu d'amélioration pour augmenter la productivité d'action d'un sujet.　Afin d'améliorer la productivité d'action d'un sujet, une intervention est faite afin de proposer, au sujet et/ou à un utilisateur, le contenu d'amélioration d'un facteur qui influe sur le sujet. Tout d'abord, la valeur qui représente une quantité de caractéristiques concernant un ou plusieurs facteurs d'influence est mesurée et entrée dans un modèle d'apprentissage, et la valeur prédite de productivité d'action fournie en sortie par le modèle d'apprentissage est acquise en tant que résultat de prédiction non intervenu. Ensuite, le contenu créé au préalable d'amélioration d'une quantité de caractéristiques et la valeur qui représente la quantité de caractéristiques sont entrés dans le modèle d'apprentissage et un résultat de prédiction intervenu fourni en sortie par le modèle d'apprentissage est acquis. La différence entre les résultats de prédiction non intervenu et intervenu est calculée en tant qu'effet d'intervention, qui est ensuite notifié au sujet en association avec le contenu d'amélioration.
PCT/JP2021/043445 2021-03-26 2021-11-26 Système d'intervention, procédé d'intervention et programme d'intervention Ceased WO2022201640A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021-053936 2021-03-26
JP2021053936A JP7407146B2 (ja) 2021-03-26 2021-03-26 介入システム、介入方法、および、介入プログラム

Publications (1)

Publication Number Publication Date
WO2022201640A1 true WO2022201640A1 (fr) 2022-09-29

Family

ID=83395257

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/043445 Ceased WO2022201640A1 (fr) 2021-03-26 2021-11-26 Système d'intervention, procédé d'intervention et programme d'intervention

Country Status (2)

Country Link
JP (1) JP7407146B2 (fr)
WO (1) WO2022201640A1 (fr)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018142258A (ja) * 2017-02-28 2018-09-13 オムロン株式会社 生産管理装置、方法およびプログラム
JP2020531982A (ja) * 2017-09-01 2020-11-05 オムロン株式会社 介入効果指数を判定するための装置、方法、プログラム及び信号

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017022013A1 (fr) * 2015-07-31 2017-02-09 株式会社ＦｉＮＣ Serveur de gestion de santé, procédé de commande de serveur de gestion de santé et programme de gestion de santé

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018142258A (ja) * 2017-02-28 2018-09-13 オムロン株式会社 生産管理装置、方法およびプログラム
JP2020531982A (ja) * 2017-09-01 2020-11-05 オムロン株式会社 介入効果指数を判定するための装置、方法、プログラム及び信号

Also Published As

Publication number Publication date
JP2022151045A (ja) 2022-10-07
JP7407146B2 (ja) 2023-12-28

Similar Documents

Publication Publication Date Title
JP5234364B2 (ja) 保健指導支援システム
US20210256545A1 (en) Summarizing and presenting recommendations of impact factors from unstructured survey response data
JP2004110548A (ja) ユーザビリティ評価支援装置および方法
JP6244476B2 (ja) 健康管理サーバおよび健康管理サーバ制御方法並びに健康管理プログラム
EP3208768A1 (fr) Dispositif d'évaluation de caractéristique, système d'évaluation de caractéristique, procédé d'évaluation de caractéristique, et programme d'évaluation de caractéristique
Vaid et al. Smartphones in personal informatics: a framework for self-tracking research with mobile sensing
JP6626170B1 (ja) 健康評価システム、健康評価サーバ及び健康評価プログラム
JP2009169461A (ja) トレーニング支援システム、トレーニング支援方法及びトレーニング支援プログラム
Brewster et al. Feasibility and psychometric integrity of mobile phone-based intensive measurement of cognition in older adults
JP2010257031A (ja) 組織力診断システム、組織力診断方法およびサーバプログラム
JP2023065808A (ja) 情報提供装置、情報提供方法及びコンピュータプログラム
JP7452898B2 (ja) 情報処理装置及びプログラム
JP2022164130A (ja) プログラム、情報処理装置、及び方法
JP6192510B2 (ja) 健康プログラム分析システム及びプラットフォームサービス提供方法
US20190180851A1 (en) System and method for predicting non-adherence risk based on socio-economic determinates of health
JP7407146B2 (ja) 介入システム、介入方法、および、介入プログラム
Miguel Cruz et al. Determinants in the number of staff in hospitals’ maintenance departments: a multivariate regression analysis approach
JP2020009469A (ja) 評価結果を分析するためのコンピュータシステムおよびそのコンピュータシステムにおいて実行される方法およびプログラム
JP7390847B2 (ja) 情報処理装置およびコンピュータプログラム
JP2004102868A (ja) ユーザビリティ評価支援装置
Dlodlo et al. SELECTED SOCIAL MEDIA ANTECEDENTS: ATTITUDES TOWARDS AND BEHAVIOURAL IMPACTS ON ITS USAGE AMONG CONSUMERS IN A DEVELOPING COUNTRY.
JP2023019492A (ja) 生産性予測システム、生産性予測方法、及びプログラム
US11631476B2 (en) Computer program product, device, system and method for gathering respondent input
JP2020047291A (ja) 健康評価システム、健康評価サーバ及び健康評価プログラム
JP7778410B1 (ja) 情報生成システムおよび情報生成方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21933238

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21933238

Country of ref document: EP

Kind code of ref document: A1