WO2018120426A1 - 基于位置服务的个人健康状态评估方法、装置、设备和存储介质 - Google Patents

基于位置服务的个人健康状态评估方法、装置、设备和存储介质 Download PDF

Info

Publication number
WO2018120426A1
WO2018120426A1 PCT/CN2017/076470 CN2017076470W WO2018120426A1 WO 2018120426 A1 WO2018120426 A1 WO 2018120426A1 CN 2017076470 W CN2017076470 W CN 2017076470W WO 2018120426 A1 WO2018120426 A1 WO 2018120426A1
Authority
WO
WIPO (PCT)
Prior art keywords
health
user
score
feature
geographic location
Prior art date
Application number
PCT/CN2017/076470
Other languages
English (en)
French (fr)
Inventor
吴振宇
王建明
肖京
Original Assignee
平安科技（深圳）有限公司
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 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2018120426A1 publication Critical patent/WO2018120426A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment

Definitions

  • the present invention relates to the field of information processing technologies, and in particular, to a location service-based personal health state assessment method, apparatus, device, and storage medium.
  • Health insurance is an important insurance in the insurance business provided by the current insurance institution. It is the insurance subject's body as the insurance subject, and the insured person's expenses incurred in the case of injury caused by illness or accident or Loss insurance for compensation.
  • an insurance institution provides health insurance services to users, it is necessary to first assess the personal health status of the user, and then decide whether to apply health insurance to the user according to the personal health status of the user.
  • the assessment of the user's personal health status mainly adopts the following methods: First, the organization personnel can understand the user's health habits and medical records through questionnaires or face-to-face interviews, and then evaluate the user's personal health status. In this evaluation method, the user has strong subjectivity, arbitrariness and uncertainty in answering the questions raised by the questionnaire or the personnel of the organization, that is, the user may conceal the personal health status, so that the evaluation result cannot truly reflect the user's personal health. status. The second is that the organization personnel can understand the user's personal health status by checking the user's illness record.
  • the user may provide a false record of illness to conceal the personal health status, and the insurance institution cannot verify the accuracy; moreover, in the actual handling process of the insurance business, only a few users hold the record of the disease, and the data saturation of the disease record. Very low, can not be better applied in the process of health insurance business in insurance institutions.
  • the personal health status obtained by the existing personal health status assessment method has low objectivity and cannot truly and objectively reflect the user's personal health status.
  • the invention provides a location service-based personal health state evaluation method, device, device and storage medium, which are used to solve the problem that the personal health state obtained by the existing personal health state evaluation method has low objectivity.
  • the present invention provides a location service based personal health assessment method, including:
  • the geographic location information including POI information associated with the time
  • a personal health status assessment result is obtained based on the user health score and the trained supervised learning model.
  • the present invention provides a location service based personal health assessment device, comprising:
  • An information acquiring unit configured to acquire geographic location information of the user based on the location service, where the geographic location information includes POI information associated with the time;
  • the cluster analysis unit is configured to perform cluster analysis on all POI information of any user in a preset period to obtain a dynamic feature of the geographic location;
  • a health score obtaining unit configured to acquire a user health score corresponding to the geographic location dynamic feature based on the geographic location dynamic feature
  • the evaluation result obtaining unit is configured to obtain an individual health state evaluation result based on the user health score and the trained supervised learning model.
  • the present invention provides a location service based personal health assessment device, comprising a processor and a memory, the memory storing computer executable instructions, the processor for executing the computer executable instructions to perform the following step:
  • the geographic location information including POI information associated with the time
  • a personal health status assessment result is obtained based on the user health score and the trained supervised learning model.
  • the present invention provides a non-transitory computer readable storage medium for storing one or more computer-executable instructions that are executed by one or more processors such that the one The plurality of processors execute the location service based personal health status assessment method.
  • the present invention has the following advantages: the location service-based personal health state evaluation method, apparatus, device, and storage medium provided by the present invention, by acquiring the geographical location information of the user within a preset period Perform cluster analysis to obtain geographic location dynamic characteristics; and obtain corresponding user health scores based on geographic location dynamic characteristics; then input user health scores into trained supervised learning models for processing to obtain final personal health status assessment results, This process is not affected by subjective factors of the user and can significantly improve the assessment of personal health status. The objectivity and accuracy of the results.
  • the corresponding personal health state assessment result can be obtained based on the user health score of any user, and the data saturation is high, the coverage rate is wide, and the Accurately assess the user's personal health status.
  • FIG. 1 is a flow chart of a location service based personal health status assessment method in a first embodiment of the present invention.
  • FIG. 2 is a schematic block diagram of a location service based personal health assessment device in a second embodiment of the present invention.
  • FIG. 3 is a schematic diagram of a location service based personal health assessment device in a third embodiment of the present invention.
  • FIG. 1 shows a flow chart of a location service based personal health status assessment method in the present embodiment.
  • the location service based personal health assessment method can be performed by a location service based personal health assessment device in a financial institution such as a bank or insurance.
  • the working principle of the location service-based personal health assessment method is to estimate the activity trajectory of the user over a period of time, based on the relationship between the objective existing activity trajectory and the personal health state, to estimate the user's personal health state, so as to improve the evaluation.
  • the objectivity of the personal health status includes:
  • S1 Obtain geographical location information of the user based on the location service, where the geographic location information includes POI information associated with the time.
  • the geographical location information includes POI information of 0:00-24:00, and each POI information is used to indicate a point in the electronic map, including POI point name, longitude and latitude. And other information. Based on the user's geographic location information, you can find out the home address, office space, commute time, frequent entertainment, shopping, fitness and other information that the user passes every day. It can be understood that obtaining the geographic location information of the user based on the location service has strong objectivity and reliability.
  • LBS Location Based Service
  • the telecommunication mobile operator's radio communication network such as GSM network, CDMA network
  • external positioning method such as GPS.
  • Coordinates in the Geographic Information System (Geographic Information System, Supported by the GIS) platform, a value-added service that provides users with corresponding services.
  • GIS Geographic Information System
  • LBS is a combination of a mobile communication network and a computer network, and the two networks interact through a gateway.
  • the mobile terminal sends a request through the mobile communication network and transmits it to the LBS service platform through the gateway; the LBS service platform processes according to the user request and the current location of the user, and returns the result to the user through the gateway.
  • POI Point Of Interest
  • POI Point Of Interest
  • the mobile terminal based on the location service is a smart phone, and the location function of the smart phone is enabled, so that the LBS service platform obtains the geographical location information of the smart phone in real time, thereby knowing the geographical location information of the user carrying the smart phone.
  • the LBS service platform is connected to a location service-based personal health assessment device in a financial institution such as a bank or an insurance, so that the location service-based personal health assessment device can obtain the geographic location information of the user corresponding to the smartphone in real time.
  • the location information includes time and time in the POI information associated with the time, by which the POI information of the user at any moment can be known. It can be understood that the geographical location information is associated with the user ID, and the user ID is used to identify the uniquely identified user, which may be an identity card number or a mobile phone number.
  • the time threshold may be preset, so that when the location service obtains the geographic location information of the user, only the POI information that the user stays at any location reaches the time threshold is obtained. The amount of data of the collected POI information associated with time is avoided, resulting in a problem of low processing efficiency.
  • S2 Perform cluster analysis on all POI information of any user during the preset period to obtain geographic location dynamic characteristics.
  • the geographic location dynamic feature is a result of cluster analysis of all POI information of the user during the preset period, and can reflect the daily activity track of the user.
  • the preset period may be any period of time before the current system time, and may be one week, one month, three months, or half a year, and may be set independently according to requirements. It can be understood that the longer the preset period, the more the data amount of the geographical location information collected, the higher the accuracy of the processing result; the shorter the preset period, the higher the processing efficiency.
  • step S2 specifically includes the following steps:
  • S21 The DBSCAN clustering algorithm is used to cluster all POI information of any user in a preset period to obtain several sub-clusters.
  • DBSCAN Density-Based Spatial Clustering of Applications with Noise
  • the algorithm will have enough The regions of density are divided into clusters, and clusters of arbitrary shape are found in a spatial database with noise, which defines the cluster as the largest set of points to which density is connected.
  • the DBSCAN algorithm has the advantages of fast clustering and efficient processing of noise and the discovery of arbitrarily formed spatial clustering.
  • eps preset scan radius
  • minPts minimum included point
  • S22 Perform an iterative aggregation on each sub-cluster by using a K-MEANS clustering algorithm to obtain centroid POI information of each sub-cluster, and output the centroid POI information as a geo-location dynamic feature.
  • the K-MEANS algorithm is a typical distance-based algorithm.
  • the distance is used as the evaluation index of similarity. That is, the closer the distance between two objects is, the greater the similarity is.
  • Its calculation formula is Among them, the selection of the k initial cluster center points has a great influence on the clustering result, because in the first step of the algorithm, any k objects are randomly selected as the center of the initial cluster, initially representing a cluster. .
  • the algorithm reassigns each object to the nearest cluster for each object remaining in the dataset in each iteration based on its distance from each cluster center. If the value of J does not change before and after an iteration, the algorithm has converged.
  • K-MEANS algorithm can quickly and easily cluster data, has high efficiency and scalability for large data sets, time complexity is nearly linear, and is suitable for mining large-scale data sets.
  • the K-MEANS algorithm is used to iteratively aggregate the POI information in each sub-cluster until the last iteration, and the values before and after the iteration do not change, then the centroid POI information of the sub-cluster is obtained, and each centroid is obtained.
  • the POI information is output as a geographical location dynamic feature.
  • the geographic location information of the user one day includes the following POI information associated with the time: A, B, C, D, E, F, G, H, F, I, J, K... E, D, A, if A is the home address, B and C are the locations in the eps near the home address, D and E are the locations acquired on the work road, F is the office address, and G is the location in the eps near the office address, H, I, J, K For consumer places and so on.
  • step S21 When the DBSCAN clustering algorithm is used for clustering in step S21, by setting the scan radius (eps) and the minimum inclusion point (minPts), for example, all POI information in the eps near the home address and the home address can be clustered into one sub-cluster output. All POI information in the eps near the office and office is clustered into another sub-cluster output.
  • Step S22 performs iterative aggregation on each sub-cluster by using a K-MEANS clustering algorithm to obtain centroid POI information of each sub-cluster, and outputs each centroid POI information as a geo-location dynamic feature.
  • S3 Acquire a user health score corresponding to the geographic location dynamic feature based on the geographic location dynamic feature.
  • the process is not affected by human factors, so that the user health score obtained based on the geographical location dynamic feature is also not subject to human factors. Influence, objectivity.
  • step S3 specifically includes the following steps:
  • S31 Determine a health feature to which each geographical location dynamic feature belongs, and the health feature includes a lifestyle habit characteristic, an exercise habit feature, and a medical habit habit feature.
  • the habits of life include the working characteristics of the office hours during office hours, the overtime characteristics of the office hours after work hours, the travel characteristics of leaving the office during working hours, and the nighttime entertainment characteristics of the nighttime entertainment venues.
  • Exercise habits include features in exercise areas such as parks and gyms.
  • Characteristics of medical activities include characteristics of medical facilities such as hospitals and pharmacies. It can be understood that when the user analyzes all the POI information in the preset period, the basic information such as the commuting time, office space, and home address of the user can be basically determined.
  • S32 Determine a health feature score based on the frequency and time of all geographic location dynamic features corresponding to each health feature.
  • the health feature scores include the scores of the habits of the habits, the scores of the habits of the exercise habits, and the scores of the habits of the medical habits.
  • the score of the exercise habit characteristic is determined according to the frequency and time of the user in the exercise place such as a park or a gym. It is best to exercise for 10 hours a week for 30-year-old adults. The corresponding score is 100. If the user reaches 10 hours in a park, gym, etc. within one week, the corresponding exercise habit characteristic score is 100. For each less than 1 hour, the score of the corresponding exercise habit feature is reduced by 10. In the same way, the scores of the habits of living habits and the scores of the habits of medical treatment can be determined.
  • the health feature score is processed by using a preset health score model to obtain a user health score.
  • X is the user health score, i is the health feature, S i is the score corresponding to the health feature i, and W i is the weight corresponding to the health feature i;
  • the characteristics include not only the characteristics of living habits, exercise habits, medical habits and other characteristics that can be determined by geographical location information, but also objective characteristics such as age characteristics, medical insurance use characteristics and commercial insurance use characteristics. It can be understood that the weight corresponding to each health feature is determined according to the degree of influence of the health feature on the personal health state.
  • S4 Acquire personal health status assessment results based on user health scores and trained supervised learning models.
  • the trained supervised learning model input the user health score, you can output the individual The health status assessment results, so that the insurance institution can objectively understand the personal health status of the users who apply for health insurance based on the results of the personal health status assessment. Since the personal health status assessment result is not obtained through the user feedback questionnaire content or the self-provided disease record, it is not affected by the subjective factors of the user, and can significantly improve the accuracy and objectivity of the personal health status assessment result.
  • the location service-based personal health assessment method can obtain a corresponding personal health state assessment result based on any user health score and a trained supervised learning model, which has high data saturation, wide coverage, and can be more Accurately assessing the user's personal health status can solve the problem in the prior art that the user's personal health status cannot be assessed due to the lack of the user's disease record.
  • the location service-based personal health assessment method further includes: obtaining user health scores and medical health information of any user; and inputting user health scores and medical health information into a machine learning model for logistic regression processing to obtain training Good supervised learning model.
  • the medical health information may be obtained by the insurance institution from the major medical institutions, and the user's medical health information and the user health score are used as a training set of the supervised learning model for training the supervised learning model, thereby realizing the user-based Health scores and trained supervised learning models assess individual health status of unknown medical health information.
  • Logistic Regression is a commonly used machine learning method in the industry to estimate the possibility of something.
  • ⁇ is the model parameter, that is, the regression coefficient
  • ⁇ is the sigmoid function.
  • this function is transformed by the following logarithmic probability (that is, the logarithm of the ratio of the likelihood that x belongs to a positive class and the likelihood of a negative class):
  • the geographical location information of the acquired user during the preset period is clustered to obtain the dynamic feature of the geographic location; and the dynamic feature is acquired based on the geographic location dynamic feature.
  • Corresponding user health score then input the user health score into the trained supervised learning model for processing to obtain the final personal health status assessment result, which is not affected by subjective factors of the user.
  • the corresponding personal health state assessment result can be obtained based on the user health score of any user, the data saturation is high, the coverage rate is wide, and the user's personal health state can be more accurately evaluated. It can solve the problem in the prior art that the user's personal health status cannot be evaluated due to the lack of the user's disease record.
  • 10,000 users are provided with health insurance in an insurance institution, and 30% of the users' medical health information can be obtained from a database of major medical institutions, including but not limited to medical examination information. The remaining 70% of users did not have the corresponding medical examination information in major medical institutions, and could not obtain their corresponding medical health information.
  • the insurance organization obtains the geographic location information of 10000 users; and performs cluster analysis on the POI information of any user in the preset period to obtain the dynamic characteristics of the geographic location; and then uses the preset health scoring model to process the dynamic characteristics of the geographic location, To obtain the user health score corresponding to 10000 users; input the user health information and medical health information of 10000*30% users into the machine learning model, and perform logistic regression processing to output the trained supervised learning model; then, 10000 * 70% of users' user health information is entered into a trained supervised learning model to obtain personal health status assessment results for users with unknown medical health information.
  • the location service-based personal health assessment method provided by the embodiment is processed based on the geographic location information of the user during the preset period to obtain the final personal health state assessment result, which is not affected by the subjective factors of the user. Significantly improve the objectivity and accuracy of personal health status assessment results. Moreover, in the location service-based personal health assessment method, all data sets of the user health score and the corresponding medical health information are simultaneously used as a training set of the machine learning model, and logic is performed on all medical health information and user health assessments. Regression processing to obtain a trained supervised learning model; and then based on the trained supervised learning model, the user health score of any user who does not have medical health information is processed, and the corresponding personal health state evaluation result is output.
  • the location service-based personal health assessment method has high data saturation and wide coverage, and can more accurately evaluate the user's personal health status, so as to solve the problem that the user's personal health status cannot be assessed due to the lack of the user's disease record in the prior art. .
  • FIG. 2 shows a schematic block diagram of a location service based personal health assessment device in the present embodiment.
  • the location service-based personal health assessment device may be a location-based personal health assessment device in a financial institution such as a bank or insurance.
  • the working principle of the location-based personal health assessment device is to estimate the user's personal health status by collecting the activity trajectory of the user over a period of time based on the relationship between the objective existing activity trajectory and the personal health state, so as to improve the evaluation.
  • the objectivity of the personal health status as shown in picture 2
  • the location service-based personal health state evaluation device includes an information acquisition unit 10, a cluster analysis unit 20, a health score acquisition unit 30, an evaluation result acquisition unit 40, and a learning model training unit 50.
  • the information obtaining unit 10 is configured to acquire geographic location information of the user based on the location service, where the geographic location information includes POI information associated with the time.
  • the geographical location information includes POI information of 0:00-24:00, and each POI information is used to indicate a point in the electronic map, including POI point name, longitude and latitude. And other information. Based on the user's geographic location information, you can find out the home address, office space, commute time, frequent entertainment, shopping, fitness and other information that the user passes every day. It can be understood that obtaining the geographic location information of the user based on the location service has strong objectivity and reliability.
  • Location Based Service is to obtain the location information (geographic coordinates, or geodetic) of the mobile terminal user through the telecommunication mobile operator's radio communication network (such as GSM network, CDMA network) or external positioning method (such as GPS).
  • LBS Location Based Service
  • LBS is to obtain the location information (geographic coordinates, or geodetic) of the mobile terminal user through the telecommunication mobile operator's radio communication network (such as GSM network, CDMA network) or external positioning method (such as GPS).
  • LBS Geographic Information System
  • LBS is a combination of a mobile communication network and a computer network, and the two networks interact through a gateway.
  • the mobile terminal sends a request through the mobile communication network and transmits it to the LBS service platform through the gateway; the LBS service platform processes according to the user request and the current location of the user, and returns the result to the user through the gateway.
  • POI Point Of Interest
  • the POI can be presented on the electronic map to indicate a certain landmark, attraction and other location information on the electronic map.
  • the mobile terminal based on the location service is a smart phone, and the location function of the smart phone is enabled, so that the LBS service platform obtains the geographical location information of the smart phone in real time, thereby knowing the geographical location information of the user carrying the smart phone.
  • the LBS service platform is connected to a location service-based personal health assessment device in a financial institution such as a bank or an insurance, so that the location service-based personal health assessment device can obtain the geographic location information of the user corresponding to the smartphone in real time.
  • the location information includes time and time in the POI information associated with the time, by which the POI information of the user at any moment can be known. It can be understood that the geographical location information is associated with the user ID, and the user ID is used to identify the uniquely identified user, which may be an identity card number or a mobile phone number.
  • the time threshold may be preset, so that when the location service obtains the geographic location information of the user, only the POI information that the user stays at any location reaches the time threshold is obtained. The amount of data of the collected POI information associated with time is avoided, resulting in a problem of low processing efficiency.
  • the cluster analysis unit 20 is configured to perform cluster analysis on all POI information of any user during a preset period. Get geolocation dynamics.
  • the geographic location dynamic feature is a result of cluster analysis of all POI information of the user during the preset period, and can reflect the daily activity track of the user.
  • the preset period may be any period of time before the current system time, and may be one week, one month, three months, or half a year, and may be set independently according to requirements. It can be understood that the longer the preset period, the more the data amount of the geographical location information collected, the higher the accuracy of the processing result; the shorter the preset period, the higher the processing efficiency.
  • the cluster analysis unit 20 specifically includes a first cluster sub-unit 21 and a second cluster sub-unit 22.
  • the first clustering sub-unit 21 is configured to use the DBSCAN clustering algorithm to cluster all POI information of any user in a preset period to obtain several sub-clusters.
  • DBSCAN Density-Based Spatial Clustering of Applications with Noise
  • the algorithm divides regions of sufficient density into clusters and finds clusters of arbitrary shape in a spatial database with noise, which defines the cluster as the largest set of points connected by density.
  • eps preset scan radius
  • minPts minimum included point
  • the second clustering sub-unit 22 is configured to perform iterative aggregation on each sub-cluster by using a K-MEANS clustering algorithm to obtain centroid POI information of each sub-cluster, and output the centroid POI information as a geo-location dynamic feature.
  • the K-MEANS algorithm is a typical distance-based algorithm.
  • the distance is used as the evaluation index of similarity. That is, the closer the distance between two objects is, the greater the similarity is.
  • Its calculation formula is Among them, the selection of the k initial cluster center points has a great influence on the clustering result, because in the first step of the algorithm, any k objects are randomly selected as the center of the initial cluster, initially representing a cluster. .
  • the algorithm reassigns each object to the nearest cluster for each object remaining in the dataset in each iteration based on its distance from each cluster center. If the value of J does not change before and after an iteration, the algorithm has converged.
  • K-MEANS algorithm can quickly and easily cluster data, has high efficiency and scalability for large data sets, time complexity is nearly linear, and is suitable for mining large-scale data sets.
  • the K-MEANS algorithm is used to iteratively aggregate the POI information in each sub-cluster until the last iteration, and the values before and after the iteration do not change, then the centroid POI information of the sub-cluster is obtained, and each A centroid POI message is output as a geo-location dynamic feature.
  • the geographic location information of the user one day includes the following POI information associated with the time: A, B, C, D, E, F, G, H, F, I, J, K... E, D, A, if A is the home address, B and C are the locations in the eps near the home address, D and E are the locations acquired on the work road, F is the office address, and G is the location in the eps near the office address, H, I, J, K For consumer places and so on.
  • the first cluster sub-unit 21 performs clustering by using the DBSCAN clustering algorithm, by setting the scan radius (eps) and the minimum inclusion point (minPts), for example, all the POI information in the eps near the home address and the home address can be clustered into A sub-cluster output clusters all POI information in the eps near the office and office to another sub-cluster output.
  • the second cluster sub-unit 22 performs iterative aggregation on each sub-cluster by using a K-MEANS clustering algorithm to obtain centroid POI information of each sub-cluster, and outputs each centroid POI information as a geo-location dynamic feature.
  • the health score obtaining unit 30 is configured to acquire a user health score corresponding to the geographic location dynamic feature based on the geographic location dynamic feature.
  • the process is not affected by human factors, so that the user health score obtained based on the geographical location dynamic feature is also not subject to human factors. Influence, objectivity.
  • the health score acquisition unit 30 specifically includes a health feature acquisition sub-unit 31, a health score acquisition sub-unit 32, and a health score acquisition sub-unit 33.
  • the health feature acquisition sub-unit 31 is configured to determine a health feature to which each geographic location dynamic feature belongs, and the health feature includes a lifestyle habit feature, an exercise habit feature, and a medical habit feature.
  • the habits of life include the working characteristics of the office hours during office hours, the overtime characteristics of the office hours after work hours, the travel characteristics of leaving the office during working hours, and the nighttime entertainment characteristics of the nighttime entertainment venues.
  • Exercise habits include features in exercise areas such as parks and gyms.
  • Characteristics of medical activities include characteristics of medical facilities such as hospitals and pharmacies. It can be understood that when the user analyzes all the POI information in the preset period, the basic information such as the commuting time, office space, and home address of the user can be basically determined.
  • the health score acquisition sub-unit 32 is configured to determine a health feature score based on the frequency and time of all geographic location dynamic characteristics corresponding to each health feature.
  • the health feature scores include the scores of the habits of the habits, the scores of the habits of the exercise habits, and the scores of the habits of the medical habits.
  • the score of the exercise habit characteristic is determined according to the frequency and time of the user in the exercise place such as a park or a gym. It is best to exercise for 10 hours a week for adults of 30 years old, with a corresponding score of 100; When the time of exercise in a park, gym, etc. reaches 10 hours in a week, the score of the corresponding exercise habit characteristic is 100 points; for less than 1 hour, the score of the corresponding exercise habit characteristic is reduced by 10. In the same way, the scores of the habits of living habits and the scores of the habits of medical treatment can be determined.
  • the health score acquisition sub-unit 33 is configured to process the health feature scores by using a preset health score model to obtain a user health score.
  • X is the user health score, i is the health feature, S i is the score corresponding to the health feature i, and W i is the weight corresponding to the health feature i;
  • the characteristics include not only the characteristics of living habits, exercise habits, medical habits and other characteristics that can be determined by geographical location information, but also objective characteristics such as age characteristics, medical insurance use characteristics and commercial insurance use characteristics. It can be understood that the weight corresponding to each health feature is determined according to the degree of influence of the health feature on the personal health state.
  • the evaluation result obtaining unit 40 is configured to obtain an individual health state evaluation result based on the user health score and the trained supervised learning model.
  • the user health score can be input, and the personal health status assessment result can be output, so that the insurance institution can objectively understand the personal health status of the user who handles the health insurance based on the personal health status assessment result.
  • the personal health status assessment result is not obtained through the user feedback questionnaire content or the self-provided disease record, it is not affected by the subjective factors of the user, and can significantly improve the accuracy and objectivity of the personal health status assessment result.
  • the location service-based personal health assessment device can obtain a corresponding personal health status assessment result based on any user health score and a trained supervised learning model, which has high data saturation, wide coverage, and more accurate. Evaluating the user's personal health status can solve the problem in the prior art that the user's personal health status cannot be assessed due to the lack of the user's disease record.
  • the location service-based personal health assessment device further includes a learning model training unit 50 for acquiring user health scores and medical health information of any user; and inputting user health scores and medical health information into the machine learning model. Logistic regression processing to obtain a trained supervised learning model.
  • the medical health information may be obtained by the insurance institution from the major medical institutions, and the user's medical health information and the user health score are used as a training set of the supervised learning model for training the supervised learning model, thereby realizing the user-based Health scores and trained supervised learning models assess individual health status of unknown medical health information.
  • Logistic Regression is a commonly used machine learning method in the industry to estimate the possibility of something.
  • ⁇ is the model parameter, that is, the regression coefficient
  • ⁇ is the sigmoid function.
  • this function is transformed by the following logarithmic probability (that is, the logarithm of the ratio of the likelihood that x belongs to a positive class and the likelihood of a negative class):
  • the location service-based personal health assessment device performs cluster analysis on the acquired geographic location information of the user during the preset period to obtain the geographic location dynamic feature; and acquires the dynamic feature based on the geographic location Corresponding user health score; then input the user health score into the trained supervised learning model to obtain the final personal health status assessment result, which is not affected by the subjective factors of the user, and can significantly improve the personal health status assessment result.
  • the location service-based personal health assessment device can obtain a corresponding personal health status assessment result based on the user health score of any user, with high data saturation and wide coverage, and can more accurately evaluate the user's personal health status. It can solve the problem in the prior art that the user's personal health status cannot be evaluated due to the lack of the user's disease record.
  • 10,000 users are provided with health insurance in an insurance institution, and 30% of the users' medical health information can be obtained from a database of major medical institutions, including but not limited to medical examination information. The remaining 70% of users did not have the corresponding medical examination information in major medical institutions, and could not obtain their corresponding medical health information.
  • the insurance organization obtains the geographic location information of 10000 users; and performs cluster analysis on the POI information of any user in the preset period to obtain the dynamic characteristics of the geographic location; and then uses the preset health scoring model to process the dynamic characteristics of the geographic location, To obtain the user health score corresponding to 10000 users; input the user health information and medical health information of 10000*30% users into the machine learning model, and perform logistic regression processing to output the trained supervised learning model; then, 10000 * 70% of users' user health information is entered into a trained supervised learning model to obtain personal health status assessment results for users with unknown medical health information.
  • the location service-based personal health assessment device provided by the embodiment is processed based on the geographic location information of the user during the preset period to obtain the final personal health state assessment result, and the process is not subject to the user owner.
  • the influence of factors can significantly improve the objectivity and accuracy of the results of personal health assessment.
  • all data sets of the user health score and the corresponding medical health information are simultaneously used as a training set of the machine learning model, and logic is applied to all medical health information and user health assessments. Regression processing to obtain a trained supervised learning model; and then based on the trained supervised learning model, the user health score of any user who does not have medical health information is processed, and the corresponding personal health state evaluation result is output.
  • the location service-based personal health assessment device has high data saturation and wide coverage, and can more accurately evaluate the user's personal health status, so as to solve the problem that the user's personal health status cannot be evaluated due to the lack of the user's disease record in the prior art. .
  • FIG. 3 is a schematic structural diagram of a location service based personal health assessment device 300 according to a third embodiment of the present invention.
  • the device 300 may be a mobile terminal having a certain data processing capability such as a mobile phone, a tablet computer, a personal digital assistant (PDA), or an on-board computer, or a terminal such as a desktop computer or a server.
  • the device 300 includes a radio frequency (RF) circuit 301, a memory 302, an input module 303, a display module 304, a processor 305, an audio circuit 306, a WiFi (Wireless Fidelity) module 307, and a power source 308.
  • RF radio frequency
  • the input module 303 and the display module 304 serve as user interaction means of the device 300 for implementing interaction between the user and the device 300, for example, receiving a health assessment instruction input by the user and displaying a corresponding personal health status assessment result.
  • the input module 303 is configured to receive a health assessment instruction input by the user, and send the health assessment instruction to the processor 305, where the health assessment instruction includes the user health score.
  • the processor 305 is configured to obtain an individual health state assessment result based on the trained supervised learning model according to the health assessment instruction, and send the personal health state assessment result to the display module 304.
  • the display module 304 receives and displays the personal health status assessment result.
  • the input module 303 can be configured to receive numeric or character information input by a user, and to generate signal inputs related to user settings and function control of the device 300.
  • the input module 303 can include a touch panel 3031.
  • the touch panel 3031 also referred to as a touch screen, can collect touch operations on or near the user (such as the operation of the user using any suitable object or accessory such as a finger or a stylus on the touch panel 3031), and according to the preset The programmed program drives the corresponding connection device.
  • the touch panel 3031 may include two parts of a touch detection device and a touch controller.
  • the touch detection device detects the touch orientation of the user, and detects a signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts the touch information into contact coordinates, and sends the touch information.
  • the touch panel 3031 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves.
  • the input module 303 may further include other input devices 3032.
  • the other input devices 3032 may include but are not limited to physical keyboards, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, joysticks, and the like. One or more of them.
  • display module 304 can be used to display information entered by a user or information provided to a user and various menu interfaces of device 300.
  • the display module 304 can include a display panel 3041.
  • the display panel 3041 can be configured in the form of an LCD or an Organic Light-Emitting Diode (OLED).
  • the touch panel 3031 can cover the display panel 3041 to form a touch display screen.
  • the touch display screen detects a touch operation on or near it, it is transmitted to the processor 305 to determine the type of the touch event, and then processed.
  • the 305 provides a corresponding visual output on the touch display based on the type of touch event.
  • the touch display includes an application interface display area and a common control display area.
  • the arrangement manner of the application interface display area and the display area of the common control is not limited, and the arrangement manner of the two display areas can be distinguished by up-and-down arrangement, left-right arrangement, and the like.
  • the application interface display area can be used to display the interface of the application. Each interface can contain interface elements such as at least one application's icon and/or widget desktop control.
  • the application interface display area can also be an empty interface that does not contain any content.
  • the common control display area is used to display controls with high usage, such as setting buttons, interface numbers, scroll bars, phone book icons, and the like.
  • the WiFi module 307 can be used as the network interface of the device 300 to implement data interaction between the device 300 and other devices.
  • the network interface can be connected to the remote storage device and the external display device through network communication.
  • the network interface is configured to receive the geographic location information of the user based on the location service sent by the remote storage device, and send the geographic location information to the processor 305;
  • the personal health status assessment result is sent to the external display device.
  • the external display device can receive and display the personal health status assessment result.
  • the remote storage device connected to the network interface through the WiFi network may be a cloud server or other database, where the remote storage device stores location information of the user based on the location service, where the geographic location information can be obtained.
  • the WiFi network is sent to the WiFi module 307, and the WiFi module 307 sends the acquired geographic location information to the processor 305, and sends the personal health status assessment result to the external display device.
  • the memory 302 includes a first memory 3021 and a second memory 3022.
  • the first memory 3021 can be a non-transitory computer readable storage medium having an operating system, a database, and computer executable instructions stored thereon.
  • Computer executable instructions are executable by processor 305 for implementing the embodiment shown in FIG. Location-based personal health assessment method.
  • the database stored on the memory 302 is used to store various types of data, such as various data involved in the above-described location service-based personal health assessment method, such as geographic location information and the supervised learning model.
  • the second memory 3021 can be an internal memory of the device 300 that provides a cached operating environment for operating systems, databases, and computer executable instructions in a non-transitory computer readable storage medium.
  • processor 305 is the control center of device 300, which connects various portions of the entire handset using various interfaces and lines, by running or executing computer-executable collections and/or databases stored in first memory 3021. The data, performing various functions and processing data of the device 300, thereby performing overall monitoring of the device 300.
  • processor 305 can include one or more processing modules.
  • the processor 305 by executing the stored computer executable instructions and/or data in the database in the first memory 3021, the processor 305 is configured to perform the following steps: acquiring geographic location information of the user based on the location service, the geographic The location information includes POI information associated with time; performing cluster analysis on all POI information of any user in a preset period to acquire a geographic location dynamic feature; and acquiring and dynamically dynamic based on the geographical location dynamic feature User health score corresponding to the feature; obtaining the personal health status assessment result based on the user health score and the trained supervised learning model.
  • the processor 305 further performs the steps of: acquiring a user health score and medical health information of the user; and inputting the user health score and the medical health information into a machine learning model for performing a logistic regression process to obtain the trained There is a supervised learning model.
  • the clustering analysis is performed on all POI information of any user in a preset period to obtain geographic location dynamic characteristics, including:
  • the DBSCAN clustering algorithm is used to cluster all POI information of any user in a preset period to obtain several sub-clusters;
  • Each of the sub-clusters is iteratively aggregated by using a K-MEANS clustering algorithm to obtain centroid POI information of each of the sub-clusters, and the centroid POI information is output as the geo-location dynamic feature.
  • the obtaining, according to the geographic location dynamic feature, a user health score corresponding to the geographic location dynamic feature including:
  • Determining a health feature to which each of the geographic location dynamic features belongs the health features including lifestyle habit characteristics, exercise habit characteristics, and medical habit characteristics;
  • the health feature score is processed by using a preset health score model to obtain the user health score.
  • X is a user health score, i is a health feature, S i is a score corresponding to the health feature i, and W i is a health feature i corresponding to Weights;
  • the health features include lifestyle habits, exercise habits, and medical habits, as well as age characteristics, health care use characteristics, and commercial use characteristics.
  • the location service-based personal health assessment device 300 provided by the embodiment, the processor 305 performs cluster analysis on the acquired geographic location information of the user during the preset period to obtain the geographic location dynamic feature; and based on the geographic location The dynamic feature obtains the corresponding user health score; then the user health score is input into the trained supervised learning model for processing to obtain the final personal health state evaluation result, which is not affected by the subjective factors of the user, and can significantly improve the personal health state.
  • the objectivity and accuracy of the assessment results may be obtained based on the user health score of any user, and the data saturation is high and the coverage is wide. The user's personal health status can be more accurately evaluated to solve the problem in the prior art that the user's personal health status cannot be assessed due to the user's lack of medical records.
  • the embodiment provides a non-transitory computer readable storage medium.
  • the non-transitory computer readable storage medium is for storing one or more computer executable instructions.
  • the computer executable instructions are executed by one or more processors such that the one or more processors perform the location service based personal health assessment method described in the first embodiment, to avoid repetition, Narration.
  • modules and algorithm steps of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods for implementing the described functions for each particular application, but such implementation should not be considered to be beyond the scope of the present invention.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative, for example, of the modules Dividing, only for one logical function division, may be further divided in actual implementation, for example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or module, and may be electrical, mechanical or otherwise.
  • the modules described as separate components may or may not be physically separated.
  • the components displayed as modules may or may not be physical modules, that is, may be located in one place, or may be distributed to multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.
  • the functions, if implemented in the form of software functional modules and sold or used as separate products, may be stored in a computer readable storage medium.
  • the technical solution of the present invention which is essential or contributes to the prior art, or a part of the technical solution, may be embodied in the form of a software product, which is stored in a storage medium, including
  • the instructions are used to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Public Health (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Databases & Information Systems (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

一种基于位置服务的个人健康状态评估方法、装置、设备和存储介质，该基于位置服务的个人健康状态评估方法包括：基于位置服务获取用户的地理位置信息，地理位置信息包括与时间相关联的POI信息（S1）；对任一用户在预设期间内所有的POI信息进行聚类分析，获取地理位置动态特征（S2）；基于地理位置动态特征，获取与地理位置动态特征相对应的用户健康评分（S3）；基于用户健康评分和训练好的有监督学习模型，获取个人健康状态评估结果（S4）。该基于位置服务的个人健康状态评估方法获取的个人健康状态评估结果，此过程不受用户主观因素影响，可显著提高个人健康状态评估结果的客观性和准确性。

Description

基于位置服务的个人健康状态评估方法、装置、设备和存储介质 技术领域
本发明涉及信息处理技术领域，尤其涉及一种基于位置服务的个人健康状态评估方法、装置、设备和存储介质。
背景技术
健康保险(Health insurance)是当前保险机构所提供的保险业务中的一项重要险种，是以被保险人的身体为保险标的，使被保险人在疾病或意外事故所致伤害时发生的费用或损失获得补偿的保险。保险机构在给用户提供健康保险业务时，需先评估用户的个人健康状态，再根据用户的个人健康状态决定是否给该用户办理健康保险。
当前健康保险办理过程中，用户个人健康状况的评估主要采用如下方式：其一是，机构人员通过调查问卷或者当面询问方式了解用户的健康习惯和病历等信息，进而评估用户个人健康状态。该评估方式中，用户在回答调查问卷或者机构人员所提出的问题时具有较强的主观性、随意性和不确定性，即用户可能隐瞒个人健康状态，使得评估结果无法真实反映用户的个人健康状态。其二是，机构人员通过查看用户的得病记录来了解用户的个人健康状态。该评估方式中，用户可能提供虚假的得病记录以隐瞒个人健康状态，保险机构无法进行准确性核实；而且，在保险业务实际办理过程中，只有少数用户持有得病记录，得病记录的数据饱和度很低，无法更好地应用在保险机构办理健康保险业务过程中。现有个人健康状态评估方式获取的个人健康状态存在客观性低，无法真实客观地反映用户的个人健康状态的问题。
发明内容
本发明提供一种基于位置服务的个人健康状态评估方法、装置、设备和存储介质，用于解决现有个人健康状态评估方式获得的个人健康状态存在客观性低的问题。
本发明解决其技术问题所采用的技术方案是：
第一方面，本发明提供一种基于位置服务的个人健康状态评估方法，包括：
基于位置服务获取用户的地理位置信息，所述地理位置信息包括与时间相关联的POI信息；
对任一用户在预设期间内所有的POI信息进行聚类分析，获取地理位置动态特征；
基于所述地理位置动态特征，获取与所述地理位置动态特征相对应的用户健康评分；
基于所述用户健康评分和训练好的有监督学习模型，获取个人健康状态评估结果。
第二方面，本发明提供一种基于位置服务的个人健康状态评估装置，包括：
信息获取单元，用于基于位置服务获取用户的地理位置信息，所述地理位置信息包括与时间相关联的POI信息；
聚类分析单元，用于对任一用户在预设期间内所有的POI信息进行聚类分析，获取地理位置动态特征；
健康评分获取单元，用于基于所述地理位置动态特征，获取与所述地理位置动态特征相对应的用户健康评分；
评估结果获取单元，用于基于所述用户健康评分和训练好的有监督学习模型，获取个人健康状态评估结果。
第三方面，本发明提供一种基于位置服务的个人健康状态评估设备，包括处理器及存储器，所述存储器存储有计算机可执行指令，所述处理器用于执行所述计算机可执行指令以执行如下步骤：
基于位置服务获取用户的地理位置信息，所述地理位置信息包括与时间相关联的POI信息；
对任一用户在预设期间内所有的POI信息进行聚类分析，获取地理位置动态特征；
基于所述地理位置动态特征，获取与所述地理位置动态特征相对应的用户健康评分；
基于所述用户健康评分和训练好的有监督学习模型，获取个人健康状态评估结果。
第四方面，本发明提供一种非易失性计算机可读存储介质，用于存储一个或多个计算机可执行指令，所述计算机可执行指令被一个或多个处理器执行，使得所述一个或多个处理器执行所述的基于位置服务的个人健康状态评估方法。
本发明与现有技术相比具有如下优点：本发明所提供的基于位置服务的个人健康状态评估方法、装置、设备和存储介质中，通过对获取到的用户在预设期间内的地理位置信息进行聚类分析以获取地理位置动态特征；并基于地理位置动态特征获取对应的用户健康评分；再将用户健康评分输入训练好的有监督学习模型进行处理，以获取最终的个人健康状态评估结果，此过程不受用户主观因素影响，可显著提高个人健康状态评估 结果的客观性和准确性。而且，该基于位置服务的个人健康状态评估方法、装置、设备和存储介质中，可基于任一用户的用户健康评分获取对应的个人健康状态评估结果，数据饱和度高、覆盖率广，能够更精准地评估用户个人健康状态。
附图说明
下面将结合附图及实施例对本发明作进一步说明，附图中：
图1是本发明第一实施例中基于位置服务的个人健康状态评估方法的一流程图。
图2是本发明第二实施例中基于位置服务的个人健康状态评估装置的一原理框图。
图3是本发明第三实施例中基于位置服务的个人健康状态评估设备的一示意图。
具体实施方式
为了对本发明的技术特征、目的和效果有更加清楚的理解，现对照附图详细说明本发明的具体实施方式。
第一实施例
图1示出本实施例中的基于位置服务的个人健康状态评估方法的一流程图。该基于位置服务的个人健康状态评估方法可由银行、保险等金融机构中的基于位置服务的个人健康状态评估设备执行。该基于位置服务的个人健康状态评估方法的工作原理是通过采集用户在一段时间内的活动轨迹，基于客观存在的活动轨迹与个人健康状态的关联关系，推定用户的个人健康状态，以提高评估出的个人健康状态的客观性。如图1所示，基于位置服务的个人健康状态评估方法包括：
S1：基于位置服务获取用户的地理位置信息，地理位置信息包括与时间相关联的POI信息。
以任一用户一天的地理位置信息为例，该地理位置信息中包括0：00—24：00的POI信息，每一POI信息用于指示电子地图中的一点，包括POI点名称、经度和纬度等信息。基于用户的地理位置信息，可了解用户每天经过的家庭住址、办公场所、上下班时间、常去的娱乐、购物、健身等信息。可以理解地，基于位置服务获取用户的地理位置信息，具有较强的客观性和可靠性。
基于位置服务(Location Based Service，简称LBS)是通过电信移动运营商的无线电通讯网络(如GSM网、CDMA网)或外部定位方式(如GPS)获取移动终端用户的位置信息(地理坐标，或大地坐标)，在地理信息***(Geographic Information System， 简称GIS)平台的支持下，为用户提供相应服务的一种增值业务。总体来看，LBS由移动通信网络和计算机网络结合而成，两个网络之间通过网关实现交互。移动终端通过移动通信网络发出请求，经过网关传递给LBS服务平台；LBS服务平台根据用户请求和用户当前位置进行处理，并将结果通过网关返回给用户。POI(Point Of Interest,即兴趣点或信息点)，包括名称、类型、经度、纬度等资料，以使POI可在电子地图上呈现，以标示电子地图上的某个地标、景点等地点信息。
本实施例中，基于位置服务的移动终端为智能手机，通过开启智能手机上的定位功能，以使LBS服务平台实时获取智能手机的地理位置信息，从而了解携带该智能手机的用户的地理位置信息。该LBS服务平台与银行、保险等金融机构中的基于位置服务的个人健康状态评估设备相连，以使该基于位置服务的个人健康状态评估设备能够实时获取该智能手机对应的用户的地理位置信息。地理位置信息包括与时间相关联的POI信息中的时间包括日期和时刻，通过该地理位置信息可了解用户在任一时刻所处的POI信息。可以理解地，地理位置信息与用户ID相关联，用户ID用于识别唯一识别用户，可以是身份证号或手机号。
可以理解地，为了减少数据处理量，提高处理效率，可预先设置时间阈值，以使基于位置服务获取用户的地理位置信息时，只获取用户在任一地点停留时间达到该时间阈值的POI信息，以避免采集到的与时间相关联的POI信息的数据量较多，导致处理效率低的问题。
S2：对任一用户在预设期间内所有的POI信息进行聚类分析，获取地理位置动态特征。
其中，地理位置动态特征是对用户在预设期间内所有POI信息进行聚类分析的结果，可体现用户的日常活动轨迹。其中，预设期间可以是当前***时间之前的任意一段时间，可以为一周、一个月、三个月或半年，可根据需求自主设置。可以理解地，预设期间越长，其采集到的地理位置信息的数据量越多，处理结果的准确性越高；预设期间越短，其处理效率越高。
进一步地，步骤S2具体包括如下步骤：
S21：采用DBSCAN聚类算法对任一用户在预设期间内所有的POI信息进行聚类，以获取若干子集群。
DBSCAN(Density-Based Spatial Clustering of Applications with Noise，具有噪声的基于密度的聚类方法)是一种基于密度的空间聚类算法。该算法将具有足够 密度的区域划分为簇，并在具有噪声的空间数据库中发现任意形状的簇，它将簇定义为密度相连的点的最大集合。DBSCAN算法具有聚类速度快且能够有效处理噪声和发现任意形成的空间聚类的优点。
具体地，预设扫描半径(以下简称为eps)和最小包含点数(minPts)，任选一个未被访问(unvisited)的POI信息开始，找出与其距离在eps之内(包括eps)的所有POI信息，将POI信息与距离在eps之内的所有POI信息作为一个子集群输出，以将用户所有POI信息在电子地图上划分出若干常去场所，即每一子集群对应一常去场所。
S22：采用K-MEANS聚类算法对每一子集群进行迭代聚合，以获取每一子集群的质心POI信息，将质心POI信息作为地理位置动态特征输出。
K-MEANS算法是很典型的基于距离的算法，采用距离作为相似性的评价指标，即认为两个对象的距离越近，其相似度就越大。其计算公式为
Figure PCTCN2017076470-appb-000001
其中，k个初始类聚类中心点的选取对聚类结果具有较大的影响，因为在该算法第一步中是随机的选取任意k个对象作为初始聚类的中心，初始地代表一个簇。该算法在每次迭代中对数据集中剩余的每个对象，根据其与各个簇中心的距离将每个对象重新赋给最近的簇。若一次迭代前后，J的值没有发生变化，说明算法已经收敛。K-MEANS算法可快速简单地对数据进行聚类，对大数据集具有较高的效率且可伸缩性，时间复杂度近于线性，而且适合挖掘大规模数据集。
本实施例中，采用K-MEANS算法对每一子集群中的POI信息进行迭代聚合，直到最后一次迭代时，迭代前后数值没有发生变化，则获取该子集群的质心POI信息，将每一质心POI信息作为一地理位置动态特征输出。
若用户某天的地理位置信息包括与时间相关联的如下POI信息：A、B、C、D、E、F、G、H、F、I、J、K……E、D、A，若A为家庭住址，B和C分别为家庭住址附近eps内的地点，D和E为工作路上获取的地点，F为办公地址，G为办公地址附近eps内的地点，H、I、J、K为消费场所等。步骤S21中采用DBSCAN聚类算法进行聚类时，通过设置扫描半径(eps)和最小包含点数(minPts)，例如可将家庭住址和家庭住址附近eps内所有的POI信息聚类为一子集群输出，将办公场所和办公场所附近eps内所有的POI信息聚类为另一子集群输出。步骤S22对每一子集群采用K-MEANS聚类算法进行迭代聚合，以获取每一子集群的质心POI信息，将每一质心POI信息作为一地理位置动态特征输出。
S3：基于地理位置动态特征，获取与地理位置动态特征相对应的用户健康评分。
由于地理位置动态特征是通过对基于位置服务获取到的地理位置信息进行聚类分析获取到的，其过程不受人为因素影响，使得基于地理位置动态特征获取到的用户健康评分同样不受人为因素影响，客观性强。
进一步地，步骤S3具体包括如下步骤：
S31：确定每一地理位置动态特征所属的健康特征，健康特征包括生活习惯特征、锻炼习惯特征和就医习惯特征。
其中，生活习惯特征包括上班时间在办公场所的上班特征、下班时间在办公场所的加班特征、上班时间离开办公场所的出差特征和夜间在娱乐场所的夜间娱乐特征等。锻炼习惯特征包括在公园、健身房等锻炼场所特征。就医活动特征包括在医院、药店等医疗场所特征。可以理解地，在对用户在预设期间内所有的POI信息进行聚类分析时，可基本确定该用户的上下班时间、办公场所、家庭住址等基本信息。
S32：基于每一健康特征对应的所有地理位置动态特征的频率和时间确定健康特征分值。
由于健康特征包括生活习惯特征、锻炼习惯特征和就医习惯特征，相应地，健康特征分值包括生活习惯特征的分值、锻炼习惯特征的分值和就医习惯特征的分值。以锻炼习惯特征的分值为例，锻炼习惯特征的分值根据用户在公园、健身房等锻炼场所的频率和时间确定。以30岁的成年人每周锻炼10小时最佳，对应的分值为100；若用户在一周内在公园、健身房等锻炼场所的时间达到10小时，则其对应的锻炼习惯特征的分值为100分；每小于1小时，则其对应的锻炼习惯特征的分值减小10。同理，可确定生活习惯特征的分值和就医习惯特征的分值。
S33：采用预设健康评分模型对健康特征分值进行处理，获取用户健康评分。
其中，预设健康评分模型包括X＝∑Si*Wi；X为用户健康评分，i是健康特征，Si是健康特征i对应的分值，Wi是健康特征i对应的权重；健康特征不仅包括生活习惯特征、锻炼习惯特征、就医习惯特征等可通过地理位置信息确定的特征，还包括年龄特征、医保使用特征和商保使用特征等客观特征。可以理解地，每一健康特征对应的权重依据该健康特征对个人健康状态的影响程度确定。
S4：基于用户健康评分和训练好的有监督学习模型，获取个人健康状态评估结果。
可以理解地，在训练好的有监督学习模型中，输入用户健康评分，即可输出个人 健康状态评估结果，以使保险机构可基于个人健康状态评估结果，客观了解办理健康保险的用户的个人健康状态。由于个人健康状态评估结果不是通过用户反馈的问卷内容或者自主提供的得病记录获取，不受用户主观因素影响，可显著提高个人健康状态评估结果的准确性和客观性。而且，该基于位置服务的个人健康状态评估方法，可基于任一用户健康评分和训练好的有监督学习模型，获取相应的个人健康状态评估结果，其数据饱和度高、覆盖率广，能够更精准地评估用户个人健康状态，可解决现有技术中因用户得病记录缺失无法评估用户的个人健康状态的问题。
进一步地，该基于位置服务的个人健康状态评估方法还包括：获取任一用户的用户健康评分和医疗健康信息；将用户健康评分和医疗健康信息输入机器学习模型中进行逻辑回归处理，以获取训练好的有监督学习模型。
其中，医疗健康信息可以是保险机构从各大医疗机构中获取得到的，将用户的医疗健康信息和用户健康评分作为有监督学习模型的训练集，用于训练有监督学习模型，从而实现基于用户健康评分和训练好的有监督学习模型对未知医疗健康信息的个人健康状态评估。
其中，逻辑回归(Logistic Regression)是当前业界比较常用的机器学习方法，用于估计某种事物的可能性。逻辑回归(Logistic Regression)是一个被logistic方程归一化后的线性回归。在逻辑回归(Logistic Regression)中，若设样本是{x,y}，y是0或者1，表示正类或者负类，x是我们的m维的样本特征向量。那么这个样本x属于正类，也就是y＝1的“概率”可以通过下面的逻辑函数来表示：
Figure PCTCN2017076470-appb-000002
其中，θ是模型参数，也就是回归系数，σ是sigmoid函数。实际上这个函数是由下面的对数几率(也就是x属于正类的可能性和负类的可能性的比值的对数)变换得到的：
Figure PCTCN2017076470-appb-000003
本实施例所提供的基于位置服务的个人健康状态评估方法中，通过对获取到的用户在预设期间内的地理位置信息进行聚类分析以获取地理位置动态特征；并基于地理位置动态特征获取对应的用户健康评分；再将用户健康评分输入训练好的有监督学习模型进行处理，以获取最终的个人健康状态评估结果，此过程不受用户主观因素影响，可显 著提高个人健康状态评估结果的客观性和准确性，以解决现有个人健康状态评估客观性低的问题。而且，该基于位置服务的个人健康状态评估方法中，可基于任一用户的用户健康评分获取对应的个人健康状态评估结果，数据饱和度高、覆盖率广，能够更精准地评估用户个人健康状态，可解决现有技术中因用户得病记录缺失无法评估用户的个人健康状态的问题。
在一具体实施例中，设有10000个用户在保险机构中办理健康保险，其中30％的用户的医疗健康信息可从各大医疗机构的数据库中获取，该医疗健康信息包括但不限于体检信息；其余70％的用户未在各大医疗机构办理过相应的体检信息，无法获取其对应的医疗健康信息。保险机构通过获取10000个用户的地理位置信息；并对预设期间内任一用户的POI信息进行聚类分析后获取地理位置动态特征；再采用预设健康评分模型对地理位置动态特征进行处理，以获取10000个用户对应的用户健康评分；再将10000*30％个用户的用户健康信息和医疗健康信息输入机器学习模型，进行逻辑回归处理，以输出训练好的有监督学习模型；然后将10000*70％个用户的用户健康信息输入训练好的有监督学习模型，以获取未知医疗健康信息的用户的个人健康状态评估结果。
本实施例所提供的基于位置服务的个人健康状态评估方法，基于用户在预设期间内的地理位置信息进行处理，以获取最终的个人健康状态评估结果，此过程不受用户主观因素影响，可显著提高个人健康状态评估结果的客观性和准确性。而且，该基于位置服务的个人健康状态评估方法中，将同时存在用户健康评分和对应的医疗健康信息的所有数据集作为机器学习模型的训练集，通过对所有医疗健康信息和用户健康评进行逻辑回归处理，以获取训练好的有监督学习模型；再基于训练好的有监督学习模型对不存在医疗健康信息的任一用户的用户健康评分进行处理，输出对应的个人健康状态评估结果。该基于位置服务的个人健康状态评估方法的数据饱和度高、覆盖率广，能够更精准地评估用户个人健康状态，以解决现有技术中因用户得病记录缺失无法评估用户的个人健康状态的问题。
第二实施例
图2示出本实施例中的基于位置服务的个人健康状态评估装置的一原理框图。该基于位置服务的个人健康状态评估装置可以是银行、保险等金融机构中的基于位置服务的个人健康状态评估设备。该基于位置服务的个人健康状态评估装置的工作原理是通过采集用户在一段时间内的活动轨迹，基于客观存在的活动轨迹与个人健康状态的关联关系，推定用户的个人健康状态，以提高评估出的个人健康状态的客观性。如图2所示， 基于位置服务的个人健康状态评估装置包括信息获取单元10、聚类分析单元20、健康评分获取单元30、评估结果获取单元40和学习模型训练单元50。
信息获取单元10，用于基于位置服务获取用户的地理位置信息，地理位置信息包括与时间相关联的POI信息。
以任一用户一天的地理位置信息为例，该地理位置信息中包括0：00—24：00的POI信息，每一POI信息用于指示电子地图中的一点，包括POI点名称、经度和纬度等信息。基于用户的地理位置信息，可了解用户每天经过的家庭住址、办公场所、上下班时间、常去的娱乐、购物、健身等信息。可以理解地，基于位置服务获取用户的地理位置信息，具有较强的客观性和可靠性。基于位置服务(Location Based Service，简称LBS)是通过电信移动运营商的无线电通讯网络(如GSM网、CDMA网)或外部定位方式(如GPS)获取移动终端用户的位置信息(地理坐标，或大地坐标)，在地理信息***(Geographic Information System，简称GIS)平台的支持下，为用户提供相应服务的一种增值业务。总体来看，LBS由移动通信网络和计算机网络结合而成，两个网络之间通过网关实现交互。移动终端通过移动通信网络发出请求，经过网关传递给LBS服务平台；LBS服务平台根据用户请求和用户当前位置进行处理，并将结果通过网关返回给用户。POI(Point Of Interest,即兴趣点或信息点)，包括名称、类型、经度、纬度等资料，以使POI可在电子地图上呈现，以标示电子地图上的某个地标、景点等地点信息。
本实施例中，基于位置服务的移动终端为智能手机，通过开启智能手机上的定位功能，以使LBS服务平台实时获取智能手机的地理位置信息，从而了解携带该智能手机的用户的地理位置信息。该LBS服务平台与银行、保险等金融机构中的基于位置服务的个人健康状态评估设备相连，以使该基于位置服务的个人健康状态评估设备能够实时获取该智能手机对应的用户的地理位置信息。地理位置信息包括与时间相关联的POI信息中的时间包括日期和时刻，通过该地理位置信息可了解用户在任一时刻所处的POI信息。可以理解地，地理位置信息与用户ID相关联，用户ID用于识别唯一识别用户，可以是身份证号或手机号。
可以理解地，为了减少数据处理量，提高处理效率，可预先设置时间阈值，以使基于位置服务获取用户的地理位置信息时，只获取用户在任一地点停留时间达到该时间阈值的POI信息，以避免采集到的与时间相关联的POI信息的数据量较多，导致处理效率低的问题。
聚类分析单元20，用于对任一用户在预设期间内所有的POI信息进行聚类分析， 获取地理位置动态特征。
其中，地理位置动态特征是对用户在预设期间内所有POI信息进行聚类分析的结果，可体现用户的日常活动轨迹。其中，预设期间可以是当前***时间之前的任意一段时间，可以为一周、一个月、三个月或半年，可根据需求自主设置。可以理解地，预设期间越长，其采集到的地理位置信息的数据量越多，处理结果的准确性越高；预设期间越短，其处理效率越高。
聚类分析单元20具体包括第一聚类子单元21和第二聚类子单元22。
第一聚类子单元21，用于采用DBSCAN聚类算法对任一用户在预设期间内所有的POI信息进行聚类，以获取若干子集群。
DBSCAN(Density-Based Spatial Clustering of Applications with Noise，具有噪声的基于密度的聚类装置)是一种基于密度的空间聚类算法。该算法将具有足够密度的区域划分为簇，并在具有噪声的空间数据库中发现任意形状的簇，它将簇定义为密度相连的点的最大集合。
具体地，预设扫描半径(以下简称为eps)和最小包含点数(minPts)，任选一个未被访问(unvisited)的POI信息开始，找出与其距离在eps之内(包括eps)的所有POI信息，将POI信息与距离在eps之内的所有POI信息作为一个子集群输出，以将用户所有POI信息在电子地图上划分出若干常去场所，即每一子集群对应一常去场所。
第二聚类子单元22，用于采用K-MEANS聚类算法对每一子集群进行迭代聚合，以获取每一子集群的质心POI信息，将质心POI信息作为地理位置动态特征输出。
K-MEANS算法是很典型的基于距离的算法，采用距离作为相似性的评价指标，即认为两个对象的距离越近，其相似度就越大。其计算公式为
Figure PCTCN2017076470-appb-000004
其中，k个初始类聚类中心点的选取对聚类结果具有较大的影响，因为在该算法第一步中是随机的选取任意k个对象作为初始聚类的中心，初始地代表一个簇。该算法在每次迭代中对数据集中剩余的每个对象，根据其与各个簇中心的距离将每个对象重新赋给最近的簇。若一次迭代前后，J的值没有发生变化，说明算法已经收敛。K-MEANS算法可快速简单地对数据进行聚类，对大数据集具有较高的效率且可伸缩性，时间复杂度近于线性，而且适合挖掘大规模数据集。
本实施例中，采用K-MEANS算法对每一子集群中的POI信息进行迭代聚合，直到最后一次迭代时，迭代前后数值没有发生变化，则获取该子集群的质心POI信息，将每 一质心POI信息作为一地理位置动态特征输出。
若用户某天的地理位置信息包括与时间相关联的如下POI信息：A、B、C、D、E、F、G、H、F、I、J、K……E、D、A，若A为家庭住址，B和C分别为家庭住址附近eps内的地点，D和E为工作路上获取的地点，F为办公地址，G为办公地址附近eps内的地点，H、I、J、K为消费场所等。第一聚类子单元21采用DBSCAN聚类算法进行聚类时，通过设置扫描半径(eps)和最小包含点数(minPts)，例如可将家庭住址和家庭住址附近eps内所有的POI信息聚类为一子集群输出，将办公场所和办公场所附近eps内所有的POI信息聚类为另一子集群输出等。第二聚类子单元22对每一子集群采用K-MEANS聚类算法进行迭代聚合，以获取每一子集群的质心POI信息，将每一质心POI信息作为一地理位置动态特征输出。
健康评分获取单元30，用于基于地理位置动态特征，获取与地理位置动态特征相对应的用户健康评分。
由于地理位置动态特征是通过对基于位置服务获取到的地理位置信息进行聚类分析获取到的，其过程不受人为因素影响，使得基于地理位置动态特征获取到的用户健康评分同样不受人为因素影响，客观性强。
进一步地，健康评分获取单元30具体包括健康特征获取子单元31、健康分值获取子单元32和健康评分获取子单元33。
健康特征获取子单元31，用于确定每一地理位置动态特征所属的健康特征，健康特征包括生活习惯特征、锻炼习惯特征和就医习惯特征。
其中，生活习惯特征包括上班时间在办公场所的上班特征、下班时间在办公场所的加班特征、上班时间离开办公场所的出差特征和夜间在娱乐场所的夜间娱乐特征等。锻炼习惯特征包括在公园、健身房等锻炼场所特征。就医活动特征包括在医院、药店等医疗场所特征。可以理解地，在对用户在预设期间内所有的POI信息进行聚类分析时，可基本确定该用户的上下班时间、办公场所、家庭住址等基本信息。
健康分值获取子单元32，用于基于每一健康特征对应的所有地理位置动态特征的频率和时间确定健康特征分值。
由于健康特征包括生活习惯特征、锻炼习惯特征和就医习惯特征，相应地，健康特征分值包括生活习惯特征的分值、锻炼习惯特征的分值和就医习惯特征的分值。以锻炼习惯特征的分值为例，锻炼习惯特征的分值根据用户在公园、健身房等锻炼场所的频率和时间确定。以30岁的成年人每周锻炼10小时最佳，对应的分值为100；若用户在 一周内在公园、健身房等锻炼场所的时间达到10小时，则其对应的锻炼习惯特征的分值为100分；每小于1小时，则其对应的锻炼习惯特征的分值减小10。同理，可确定生活习惯特征的分值和就医习惯特征的分值。
健康评分获取子单元33，用于采用预设健康评分模型对健康特征分值进行处理，获取用户健康评分。
其中，预设健康评分模型包括X＝∑Si*Wi；X为用户健康评分，i是健康特征，Si是健康特征i对应的分值，Wi是健康特征i对应的权重；健康特征不仅包括生活习惯特征、锻炼习惯特征、就医习惯特征等可通过地理位置信息确定的特征，还包括年龄特征、医保使用特征和商保使用特征等客观特征。可以理解地，每一健康特征对应的权重依据该健康特征对个人健康状态的影响程度确定。
评估结果获取单元40，用于基于用户健康评分和训练好的有监督学习模型，获取个人健康状态评估结果。
可以理解地，在训练好的有监督学习模型中，输入用户健康评分，即可输出个人健康状态评估结果，以使保险机构可基于个人健康状态评估结果客观了解办理健康保险的用户的个人健康状态。由于个人健康状态评估结果不是通过用户反馈的问卷内容或者自主提供的得病记录获取，不受用户主观因素影响，可显著提高个人健康状态评估结果的准确性和客观性。而且，该基于位置服务的个人健康状态评估装置可基于任一用户健康评分和训练好的有监督学习模型，获取相应的个人健康状态评估结果，其数据饱和度高、覆盖率广，能够更精准地评估用户个人健康状态，可解决现有技术中因用户得病记录缺失无法评估用户的个人健康状态的问题。
进一步地，该基于位置服务的个人健康状态评估装置还包括学习模型训练单元50，用于获取任一用户的用户健康评分和医疗健康信息；将用户健康评分和医疗健康信息输入机器学习模型中进行逻辑回归处理，以获取训练好的有监督学习模型。
其中，医疗健康信息可以是保险机构从各大医疗机构中获取得到的，将用户的医疗健康信息和用户健康评分作为有监督学习模型的训练集，用于训练有监督学习模型，从而实现基于用户健康评分和训练好的有监督学习模型对未知医疗健康信息的个人健康状态评估。
其中，逻辑回归(Logistic Regression)是当前业界比较常用的机器学习方法，用于估计某种事物的可能性。逻辑回归(Logistic Regression)是一个被logistic 方程归一化后的线性回归。在逻辑回归(Logistic Regression)中，若设样本是{x,y}，y是0或者1，表示正类或者负类，x是我们的m维的样本特征向量。那么这个样本x属于正类，也就是y＝1的“概率”可以通过下面的逻辑函数来表示：
Figure PCTCN2017076470-appb-000005
其中，θ是模型参数，也就是回归系数，σ是sigmoid函数。实际上这个函数是由下面的对数几率(也就是x属于正类的可能性和负类的可能性的比值的对数)变换得到的：
Figure PCTCN2017076470-appb-000006
本实施例所提供的基于位置服务的个人健康状态评估装置中，通过对获取到的用户在预设期间内的地理位置信息进行聚类分析以获取地理位置动态特征；并基于地理位置动态特征获取对应的用户健康评分；再将用户健康评分输入训练好的有监督学习模型进行处理，以获取最终的个人健康状态评估结果，此过程不受用户主观因素影响，可显著提高个人健康状态评估结果的客观性和准确性，以解决现有个人健康状态评估客观性低的问题。而且，该基于位置服务的个人健康状态评估装置中，可基于任一用户的用户健康评分获取对应的个人健康状态评估结果，数据饱和度高、覆盖率广，能够更精准地评估用户个人健康状态，可解决现有技术中因用户得病记录缺失无法评估用户的个人健康状态的问题。
在一具体实施例中，设有10000个用户在保险机构中办理健康保险，其中30％的用户的医疗健康信息可从各大医疗机构的数据库中获取，该医疗健康信息包括但不限于体检信息；其余70％的用户未在各大医疗机构办理过相应的体检信息，无法获取其对应的医疗健康信息。保险机构通过获取10000个用户的地理位置信息；并对预设期间内任一用户的POI信息进行聚类分析后获取地理位置动态特征；再采用预设健康评分模型对地理位置动态特征进行处理，以获取10000个用户对应的用户健康评分；再将10000*30％个用户的用户健康信息和医疗健康信息输入机器学习模型，进行逻辑回归处理，以输出训练好的有监督学习模型；然后将10000*70％个用户的用户健康信息输入训练好的有监督学习模型，以获取未知医疗健康信息的用户的个人健康状态评估结果。
本实施例所提供的基于位置服务的个人健康状态评估装置，基于用户在预设期间内的地理位置信息进行处理，以获取最终的个人健康状态评估结果，此过程不受用户主 观因素影响，可显著提高个人健康状态评估结果的客观性和准确性。而且，该基于位置服务的个人健康状态评估装置中，将同时存在用户健康评分和对应的医疗健康信息的所有数据集作为机器学习模型的训练集，通过对所有医疗健康信息和用户健康评进行逻辑回归处理，以获取训练好的有监督学习模型；再基于训练好的有监督学习模型对不存在医疗健康信息的任一用户的用户健康评分进行处理，输出对应的个人健康状态评估结果。该基于位置服务的个人健康状态评估装置的数据饱和度高、覆盖率广，能够更精准地评估用户个人健康状态，以解决现有技术中因用户得病记录缺失无法评估用户的个人健康状态的问题。
第三实施例
图3是本发明第三实施例的基于位置服务的个人健康状态评估设备300的结构示意图。其中，设备300可以为手机、平板电脑、个人数字助理(PersonalDigital Assistant，PDA)和或车载电脑等具有一定的数据处理能力的移动终端、或者台式电脑、服务器等终端。如图3所示，设备300包括射频(RadioFrequency，RF)电路301、存储器302、输入模块303、显示模块304、处理器305、音频电路306、WiFi(WirelessFidelity)模块307和电源308。
输入模块303和显示模块304作为设备300的用户交互装置，用于实现用户与设备300之间的交互，例如，接收用户输入的健康评估指令并显示对应的个人健康状态评估结果。输入模块303用于接收用户输入的健康评估指令，并将所述健康评估指令发送给所述处理器305，所述健康评估指令包括所述用户健康评分。所述处理器305用于根据所述健康评估指令，基于所述训练好的有监督学习模型，获取个人健康状态评估结果，并将所述个人健康状态评估结果发送给所述显示模块304。显示模块304接收并显示所述个人健康状态评估结果。
在一些实施例中，输入模块303可用于接收用户输入的数字或字符信息，以及产生与设备300的用户设置以及功能控制有关的信号输入。在一些实施例中，该输入模块303可以包括触控面板3031。触控面板3031，也称为触摸屏，可收集用户在其上或附近的触摸操作(比如用户使用手指、触笔等任何适合的物体或附件在触控面板3031上的操作)，并根据预先设定的程式驱动相应的连接装置。可选地，触控面板3031可包括触摸检测装置和触摸控制器两个部分。其中，触摸检测装置检测用户的触摸方位，并检测触摸操作带来的信号，将信号传送给触摸控制器；触摸控制器从触摸检测装置上接收触摸信息，并将它转换成触点坐标，再送给该处理器305，并能接收处理器305发来 的命令并加以执行。此外，可以采用电阻式、电容式、红外线以及表面声波等多种类型实现触控面板3031。除了触控面板3031，输入模块303还可以包括其他输入设备3032，其他输入设备3032可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆等中的一种或多种。
在一些实施例中，显示模块304可用于显示由用户输入的信息或提供给用户的信息以及设备300的各种菜单界面。显示模块304可包括显示面板3041，可选地，可以采用LCD或有机发光二极管(Organic Light-Emitting Diode，OLED)等形式来配置显示面板3041。
可以理解地，触控面板3031可以覆盖显示面板3041，形成触摸显示屏，当该触摸显示屏检测到在其上或附近的触摸操作后，传送给处理器305以确定触摸事件的类型，随后处理器305根据触摸事件的类型在触摸显示屏上提供相应的视觉输出。
触摸显示屏包括应用程序界面显示区及常用控件显示区。该应用程序界面显示区及该常用控件显示区的排列方式并不限定，可以为上下排列、左右排列等可以区分两个显示区的排列方式。该应用程序界面显示区可以用于显示应用程序的界面。每一个界面可以包含至少一个应用程序的图标和/或widget桌面控件等界面元素。该应用程序界面显示区也可以为不包含任何内容的空界面。该常用控件显示区用于显示使用率较高的控件，例如，设置按钮、界面编号、滚动条、电话本图标等应用程序图标等。
WiFi模块307作为设备300的网络接口，可以实现设备300与其他设备的数据交互，本实施例中，网络接口可与远端存储设备和外部显示设备通过网络通信相连。所述网络接口用于接收所述远端存储设备发送的基于位置服务获取用户的地理位置信息，并将所述地理位置信息发送给所述处理器305；还用于接收所述处理器305发送的个人健康状态评估结果，并将所述个人健康状态评估结果发送给所述外部显示设备。外部显示设备可接收并显示所述个人健康状态评估结果。本实施例中，与该网络接口通过WiFi网络相连的远端存储设备可以是云服务器或其他数据库，该远端存储设备上存储有基于位置服务获取用户的地理位置信息，该地理位置信息可通过WiFi网络发送给WiFi模块307，WiFi模块307将获取到的所述地理位置信息发送给所述处理器305，并将所述所述个人健康状态评估结果发送给所述外部显示设备。
存储器302包括第一存储器3021及第二存储器3022。在一些实施例中，第一存储器3021可为非易失性计算机可读存储介质，其上存储有操作***、数据库及计算机可执行指令。计算机可执行指令可被处理器305所执行，用于实现如图1所示的实施例 的基于位置服务的个人健康状态评估方法。存储器302上存储的数据库用于存储各类数据，例如，上述基于位置服务的个人健康状态评估方法中所涉及的各种数据，如地理位置信息和所述有监督学习模型。第二存储器3021可为设备300的内存储器，为非易失性计算机可读存储介质中的操作***、数据库和计算机可执行指令提供高速缓存的运行环境。
在本实施例中，处理器305是设备300的控制中心，利用各种接口和线路连接整个手机的各个部分，通过运行或执行存储在第一存储器3021内的计算机可执行搜集和/或数据库内的数据，执行设备300的各种功能和处理数据，从而对设备300进行整体监控。可选地，处理器305可包括一个或多个处理模块。
在本实施例中，通过执行存储该第一存储器3021内的计算机可执行指令和/或数据库内的数据，处理器305用于执行如下步骤：基于位置服务获取用户的地理位置信息，所述地理位置信息包括与时间相关联的POI信息；对任一用户在预设期间内所有的POI信息进行聚类分析，获取地理位置动态特征；基于所述地理位置动态特征，获取与所述地理位置动态特征相对应的用户健康评分；基于所述用户健康评分和训练好的有监督学习模型，获取个人健康状态评估结果。
所述处理器305还执行如下步骤：获取用户的用户健康评分和医疗健康信息；将所述用户健康评分和所述医疗健康信息输入机器学习模型中进行逻辑回归处理，以获取所述训练好的有监督学习模型。
优选地，所述对任一用户在预设期间内所有的POI信息进行聚类分析，获取地理位置动态特征，包括：
采用DBSCAN聚类算法对任一用户在预设期间内所有的POI信息进行聚类，以获取若干子集群；
采用K-MEANS聚类算法对每一所述子集群进行迭代聚合，以获取每一所述子集群的质心POI信息，将所述质心POI信息作为所述地理位置动态特征输出。
优选地，所述基于所述地理位置动态特征，获取与所述地理位置动态特征相对应的用户健康评分，包括：
确定每一所述地理位置动态特征所属的健康特征，所述健康特征包括生活习惯特征、锻炼习惯特征和就医习惯特征；
基于每一所述健康特征对应的所有地理位置动态特征的频率和时间确定所述健康特征分值；
采用预设健康评分模型对所述健康特征分值进行处理，获取所述用户健康评分。
优选地，所述预设健康评分模型包括X＝∑Si*Wi；X为用户健康评分，i是健康特征，Si是健康特征i对应的分值，Wi是健康特征i对应的权重；所述健康特征包括生活习惯特征、锻炼习惯特征和就医习惯特征，还包括年龄特征、医保使用特征和商保使用特征。
本实施例所提供的基于位置服务的个人健康状态评估设备300，处理器305通过对获取到的用户在预设期间内的地理位置信息进行聚类分析以获取地理位置动态特征；并基于地理位置动态特征获取对应的用户健康评分；再将用户健康评分输入训练好的有监督学习模型进行处理，以获取最终的个人健康状态评估结果，此过程不受用户主观因素影响，可显著提高个人健康状态评估结果的客观性和准确性。设备300的处理器执行第一实施例中的基于位置服务的个人健康状态评估方法时，可基于任一用户的用户健康评分获取对应的个人健康状态评估结果，数据饱和度高、覆盖率广，能够更精准地评估用户个人健康状态，以解决现有技术中因用户得病记录缺失无法评估用户的个人健康状态的问题。
第四实施例
本实施例提供一种非易失性计算机可读存储介质。该非易失性计算机可读存储介质用于存储一个或多个计算机可执行指令。具体地，计算机可执行指令被一个或多个处理器执行，使得所述一个或多个处理器执行第一实施例所述的基于位置服务的个人健康状态评估方法，为避免重复，这里不再赘述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的模块及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的***、装置和模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述模块的 划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个模块或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或模块的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个地方，或者也可以分布到多个网络模块上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能模块可以集成在一个处理模块中，也可以是各个模块单独物理存在，也可以两个或两个以上模块集成在一个模块中。
所述功能如果以软件功能模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以权利要求的保护范围为准。

Claims (19)

  1. 一种基于位置服务的个人健康状态评估方法，其特征在于，包括：
    基于位置服务获取用户的地理位置信息，所述地理位置信息包括与时间相关联的POI信息；
    对任一用户在预设期间内所有的POI信息进行聚类分析，获取地理位置动态特征；
    基于所述地理位置动态特征，获取与所述地理位置动态特征相对应的用户健康评分；
    基于所述用户健康评分和训练好的有监督学习模型，获取个人健康状态评估结果。
  2. 根据权利要求1所述的基于位置服务的个人健康状态评估方法，其特征在于，还包括：获取用户的用户健康评分和医疗健康信息；将所述用户健康评分和所述医疗健康信息输入机器学习模型中进行逻辑回归处理，以获取所述训练好的有监督学习模型。
  3. 根据权利要求1或2所述的基于位置服务的个人健康状态评估方法，其特征在于，所述对任一用户在预设期间内所有的POI信息进行聚类分析，获取地理位置动态特征，包括：
    采用DBSCAN聚类算法对任一用户在预设期间内所有的POI信息进行聚类，以获取若干子集群；
    采用K-MEANS聚类算法对每一所述子集群进行迭代聚合，以获取每一所述子集群的质心POI信息，将所述质心POI信息作为所述地理位置动态特征输出。
  4. 根据权利要求3所述的基于位置服务的个人健康状态评估方法，其特征在于，所述基于所述地理位置动态特征，获取与所述地理位置动态特征相对应的用户健康评分，包括：
    确定每一所述地理位置动态特征所属的健康特征，所述健康特征包括生活习惯特征、锻炼习惯特征和就医习惯特征；
    基于每一所述健康特征对应的所有地理位置动态特征的频率和时间确定所述健康特征分值；
    采用预设健康评分模型对所述健康特征分值进行处理，获取所述用户健康评分。
  5. 根据权利要求4所述的基于位置服务的个人健康状态评估方法，其特征在于，所述预设健康评分模型包括X＝∑Si*Wi；X为用户健康评分，i是健康特征，Si是健康特征i对应的分值，Wi是健康特征i对应的权重；所述健康特征包括生活习惯特征、锻炼习惯特征和就医习惯特征，还包括年龄特征、医保使用特征和商保使用特征。
  6. 一种基于位置服务的个人健康状态评估装置，其特征在于，包括：
    信息获取单元，用于基于位置服务获取用户的地理位置信息，所述地理位置信息包括与时间相关联的POI信息；
    聚类分析单元，用于对任一用户在预设期间内所有的POI信息进行聚类分析，获取地理位置动态特征；
    健康评分获取单元，用于基于所述地理位置动态特征，获取与所述地理位置动态特征相对应的用户健康评分；
    评估结果获取单元，用于基于所述用户健康评分和训练好的有监督学习模型，获取个人健康状态评估结果。
  7. 根据权利要求6所述的基于位置服务的个人健康状态评估装置，其特征在于，还包括学习模型训练单元，用于获取用户的用户健康评分和医疗健康信息；将所述用户健康评分和所述医疗健康信息输入机器学习模型中进行逻辑回归处理，以获取所述训练好的有监督学习模型。
  8. 根据权利要求6或7所述的基于位置服务的个人健康状态评估装置，其特征在于，所述聚类分析单元包括：
    第一聚类子单元，用于采用DBSCAN聚类算法对任一用户在预设期间内所有的POI信息进行聚类，以获取若干子集群；
    第二聚类子单元，用于采用K-MEANS聚类算法对每一所述子集群进行迭代聚合，以获取每一所述子集群的质心POI信息，将所述质心POI信息作为所述地理位置动态特征输出。
  9. 根据权利要求8所述的基于位置服务的个人健康状态评估装置，其特征在于，所述健康评分获取单元包括：
    健康特征获取子单元，用于确定每一所述地理位置动态特征所属的健康特征，所述健康特征包括生活习惯特征、锻炼习惯特征和就医习惯特征；
    健康分值获取子单元，用于基于每一所述健康特征对应的所有地理位置动态特征的频率和时间确定所述健康特征分值；
    健康评分获取子单元，用于采用预设健康评分模型对所述健康特征分值进行处理，获取所述用户健康评分。
  10. 根据权利要求9所述的基于位置服务的个人健康状态评估装置，其特征在于，所述预设健康评分模型包括X＝∑Si*Wi；X为用户健康评分，i是健康特征，Si是健康特征i对应的分值，Wi是健康特征i对应的权重；所述健康特征包括生活习惯特征、锻炼习惯 特征和就医习惯特征，还包括年龄特征、医保使用特征和商保使用特征。
  11. 一种基于位置服务的个人健康状态评估设备，其特征在于，包括处理器及存储器，所述存储器存储有计算机可执行指令，所述处理器用于执行所述计算机可执行指令以执行如下步骤：
    基于位置服务获取用户的地理位置信息，所述地理位置信息包括与时间相关联的POI信息；
    对任一用户在预设期间内所有的POI信息进行聚类分析，获取地理位置动态特征；
    基于所述地理位置动态特征，获取与所述地理位置动态特征相对应的用户健康评分；
    基于所述用户健康评分和训练好的有监督学习模型，获取个人健康状态评估结果。
  12. 根据权利要求11所述的设备，其特征在于，所述处理器还执行如下步骤：获取用户的用户健康评分和医疗健康信息；将所述用户健康评分和所述医疗健康信息输入机器学习模型中进行逻辑回归处理，以获取所述训练好的有监督学习模型。
  13. 根据权利要求11或12所述的设备，其特征在于，所述对任一用户在预设期间内所有的POI信息进行聚类分析，获取地理位置动态特征，包括：
    采用DBSCAN聚类算法对任一用户在预设期间内所有的POI信息进行聚类，以获取若干子集群；
    采用K-MEANS聚类算法对每一所述子集群进行迭代聚合，以获取每一所述子集群的质心POI信息，将所述质心POI信息作为所述地理位置动态特征输出。
  14. 根据权利要求13所述的设备，其特征在于，所述基于所述地理位置动态特征，获取与所述地理位置动态特征相对应的用户健康评分，包括：
    确定每一所述地理位置动态特征所属的健康特征，所述健康特征包括生活习惯特征、锻炼习惯特征和就医习惯特征；
    基于每一所述健康特征对应的所有地理位置动态特征的频率和时间确定所述健康特征分值；
    采用预设健康评分模型对所述健康特征分值进行处理，获取所述用户健康评分。
  15. 根据权利要求14所述的设备，其特征在于，所述预设健康评分模型包括X＝∑Si*Wi；X为用户健康评分，i是健康特征，Si是健康特征i对应的分值，Wi是健康特征i对应的权重；所述健康特征包括生活习惯特征、锻炼习惯特征和就医习惯特征，还包括年龄特征、医保使用特征和商保使用特征。
  16. 根据权利要求11所述的设备，其特征在于，所述设备还包括与所述处理器相连的用户交互装置；所述用户交互装置，用于接收用户输入的健康评估指令，并将所述健康评估指令发送给所述处理器，所述健康评估指令包括所述用户健康评分；
    所述处理器，用于根据所述健康评估指令，基于所述训练好的有监督学习模型，获取个人健康状态评估结果，并将所述个人健康状态评估结果发送给所述用户交互装置；
    所述用户交互装置，还用于接收并显示所述个人健康状态评估结果。
  17. 根据权利要求11所述的设备，其特征在于，所述设备还包括与所述处理器相连的网络接口；所述网络接口与远端存储设备和外部显示设备相连；所述网络接口用于接收所述远端存储设备发送的基于位置服务获取用户的地理位置信息，并将所述地理位置信息发送给所述处理器；还用于接收所述处理器发送的个人健康状态评估结果，并将所述个人健康状态评估结果发送给所述外部显示设备。
  18. 根据权利要求11所述的设备，其特征在于，所述存储器中存储有数据库，用于存储所述地理位置信息和所述有监督学习模型。
  19. 一种非易失性计算机可读存储介质，其特征在于，用于存储一个或多个计算机可执行指令，所述计算机可执行指令被一个或多个处理器执行，使得所述一个或多个处理器执行权利要求1-5任一项所述的基于位置服务的个人健康状态评估方法。
PCT/CN2017/076470 2016-12-29 2017-03-13 基于位置服务的个人健康状态评估方法、装置、设备和存储介质 WO2018120426A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201611246234.X 2016-12-29
CN201611246234.XA CN106682427A (zh) 2016-12-29 2016-12-29 基于位置服务的个人健康状态评估方法及装置

Publications (1)

Publication Number Publication Date
WO2018120426A1 true WO2018120426A1 (zh) 2018-07-05

Family

ID=58873340

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/076470 WO2018120426A1 (zh) 2016-12-29 2017-03-13 基于位置服务的个人健康状态评估方法、装置、设备和存储介质

Country Status (2)

Country Link
CN (1) CN106682427A (zh)
WO (1) WO2018120426A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111243732A (zh) * 2018-11-28 2020-06-05 苏州市铼健康医疗护理服务有限公司 基于多点采集的人体健康状态评估***及评估方法
WO2020120301A1 (en) * 2018-12-10 2020-06-18 Koninklijke Philips N.V. Hierarchical local model for social determinants of health index prediction
CN112233816A (zh) * 2020-10-27 2021-01-15 贵州精准医疗电子有限公司 健康监测方法、装置及计算机可读介质
US20210158105A1 (en) * 2018-08-14 2021-05-27 Canon Kabushiki Kaisha Medical information processing apparatus, medical information processing method, and non-transitory computer-readable storage medium

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109086323A (zh) * 2018-06-28 2018-12-25 上海中通吉网络技术有限公司 用户家庭和工作地址的确定方法和***
TWI680428B (zh) * 2018-11-27 2019-12-21 旺旺友聯產物保險股份有限公司 理賠系統
CN110957044A (zh) * 2019-09-20 2020-04-03 上海派拉软件股份有限公司 基于改进的逻辑回归模型的健康管理方法
CN110895970A (zh) * 2019-10-22 2020-03-20 泰康保险集团股份有限公司 数据处理方法、装置、电子设备和计算机可读介质
TWI751453B (zh) * 2019-11-19 2022-01-01 臺灣銀行股份有限公司 穿戴裝置或行動裝置之風險評估方法
CN112967806A (zh) * 2021-02-26 2021-06-15 平安科技（深圳）有限公司 健康检测方法、装置、设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080005076A1 (en) * 2006-06-28 2008-01-03 Microsoft Corporation Entity-specific search model
US20090006194A1 (en) * 2007-06-27 2009-01-01 Microsoft Corporation Location, destination and other contextual information-based mobile advertisements
CN103731916A (zh) * 2014-01-14 2014-04-16 上海河广信息科技有限公司 一种基于无线网络的用户位置预测***和方法
CN103747523A (zh) * 2014-01-14 2014-04-23 上海河广信息科技有限公司 一种基于无线网络的用户位置预测***和方法
CN104933157A (zh) * 2015-06-26 2015-09-23 百度在线网络技术（北京）有限公司 用于获取用户属性信息的方法、装置及服务器
CN106097095A (zh) * 2016-06-08 2016-11-09 腾讯科技（深圳）有限公司 确定信用的方法及装置

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20140107714A (ko) * 2013-02-25 2014-09-05 한국전자통신연구원 건강 관리 시스템 및 그것의 건강 정보 제공 방법
CN104239556B (zh) * 2014-09-25 2017-07-28 西安理工大学 基于密度聚类的自适应轨迹预测方法
CN106028444A (zh) * 2016-07-01 2016-10-12 国家计算机网络与信息安全管理中心 预测移动终端位置的方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080005076A1 (en) * 2006-06-28 2008-01-03 Microsoft Corporation Entity-specific search model
US20090006194A1 (en) * 2007-06-27 2009-01-01 Microsoft Corporation Location, destination and other contextual information-based mobile advertisements
CN103731916A (zh) * 2014-01-14 2014-04-16 上海河广信息科技有限公司 一种基于无线网络的用户位置预测***和方法
CN103747523A (zh) * 2014-01-14 2014-04-23 上海河广信息科技有限公司 一种基于无线网络的用户位置预测***和方法
CN104933157A (zh) * 2015-06-26 2015-09-23 百度在线网络技术（北京）有限公司 用于获取用户属性信息的方法、装置及服务器
CN106097095A (zh) * 2016-06-08 2016-11-09 腾讯科技（深圳）有限公司 确定信用的方法及装置

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210158105A1 (en) * 2018-08-14 2021-05-27 Canon Kabushiki Kaisha Medical information processing apparatus, medical information processing method, and non-transitory computer-readable storage medium
US11914918B2 (en) * 2018-08-14 2024-02-27 Canon Kabushiki Kaisha Medical information processing apparatus, medical information processing method, and non-transitory computer-readable storage medium
CN111243732A (zh) * 2018-11-28 2020-06-05 苏州市铼健康医疗护理服务有限公司 基于多点采集的人体健康状态评估***及评估方法
WO2020120301A1 (en) * 2018-12-10 2020-06-18 Koninklijke Philips N.V. Hierarchical local model for social determinants of health index prediction
CN112233816A (zh) * 2020-10-27 2021-01-15 贵州精准医疗电子有限公司 健康监测方法、装置及计算机可读介质

Also Published As

Publication number Publication date
CN106682427A (zh) 2017-05-17

Similar Documents

Publication Publication Date Title
WO2018120426A1 (zh) 基于位置服务的个人健康状态评估方法、装置、设备和存储介质
US11844626B2 (en) Fitness systems and methods
CN110033851B (zh) 信息推荐方法、装置、存储介质及服务器
WO2018120425A1 (zh) 个人财产状态评估方法、装置、设备和存储介质
US20180068075A1 (en) Medical system and program
JP2015502624A (ja) 生理データを利用した社会的感情の判定
KR102128043B1 (ko) 개인맞춤형 생활체육 추천 플랫폼 시스템
JP6533243B2 (ja) 提供装置、提供方法、及び提供プログラム
CN103942463A (zh) 一种基于患者身体病症的导医***
US10769737B2 (en) Information processing device, information processing method, and program
CN106605418A (zh) 使用基于位置的服务的移动客户端的电力管理
CN105917349A (zh) 对请求的用户数据的隐私过滤以及上下文激活的隐私模式
CN108369586A (zh) 用于检测网络中的交互和影响的***和方法
Yue et al. Fusing location data for depression prediction
CN105103184A (zh) 行程估计
JP2018077821A (ja) ユーザによって訪問される施設のカテゴリの予測モデルを生成する方法、プログラム、サーバ装置、及び処理装置
Park et al. Bayesian network-based high-level context recognition for mobile context sharing in cyber-physical system
WO2016015471A1 (zh) 一种预测用户离网的方法及装置
JP2021507366A (ja) ユーザの健康状態を監視するためのシステムおよび方法
US20150112706A1 (en) System and Methods for Personal health Analytics Technical Field
US20180165708A1 (en) Notification Control based on Location, Activity, and Temporal Prediction
JP2012221447A (ja) 遠隔診断システム、データ送信方法、データ受信方法、及びそれらに用いられる通信端末装置、データ解析装置、並びにプログラム、記憶媒体
KR101706474B1 (ko) 스마트폰 이용행태 수집 가공 시스템
Rocha et al. New Knowledge in Information Systems and Technologies: Volume 3
Andrew et al. Using location lifelogs to make meaning of food and physical activity behaviors

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: 17888341

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC, EPO FORM 1205A DATED 27.09.19

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC, EPO FORM 1205A DATED 27.09.19

122 Ep: pct application non-entry in european phase

Ref document number: 17888341

Country of ref document: EP

Kind code of ref document: A1