WO2019196299A1 - 电子装置、鼻咽癌风险预警方法和计算机可读存储介质 - Google Patents

电子装置、鼻咽癌风险预警方法和计算机可读存储介质 Download PDF

Info

Publication number
WO2019196299A1
WO2019196299A1 PCT/CN2018/102107 CN2018102107W WO2019196299A1 WO 2019196299 A1 WO2019196299 A1 WO 2019196299A1 CN 2018102107 W CN2018102107 W CN 2018102107W WO 2019196299 A1 WO2019196299 A1 WO 2019196299A1
Authority
WO
WIPO (PCT)
Prior art keywords
feature
tag
nasopharyngeal cancer
customer
various
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/CN2018/102107
Other languages
English (en)
French (fr)
Inventor
卢少烽
洪博然
徐亮
阮晓雯
肖京
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.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co 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 Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2019196299A1 publication Critical patent/WO2019196299A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • 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
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • 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
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Definitions

  • the present application relates to the field of big data analysis technologies, and in particular, to an electronic device, a nasopharyngeal cancer risk warning method, and a computer readable storage medium.
  • Nasopharyngeal carcinoma is a high-grade malignant tumor with the highest incidence of otolaryngology and malignant tumors.
  • the etiology is complicated.
  • the cause of nasopharyngeal carcinoma in traditional medicine is still unclear.
  • Most of the existing researches come from clinical observations (related to heredity, environment, and viruses). However, clinical observations have limited access to personal information.
  • existing research usually relies on the professional medical knowledge and personal experience of the researchers. Therefore, the accuracy of the research cannot meet the requirements, and it is impossible to form an objective and accurate screening system for the cause of the disease. .
  • the main object of the present application is to provide an electronic device, a nasopharyngeal cancer risk warning method, and a computer readable storage medium, which are intended to promptly prevent or treat a customer and improve the condition of nasopharyngeal cancer.
  • a first aspect of the present application provides an electronic device including a memory and a processor, wherein the memory stores a nasopharyngeal cancer risk warning system operable on the processor, wherein the nasopharyngeal cancer risk warning system is
  • the processor implements the following steps when it executes:
  • nasopharyngeal cancer screening request After receiving a nasopharyngeal cancer screening request from a client to be screened, obtaining a characteristic label of the customer to be screened from the nasopharyngeal cancer screening request;
  • the feature tag fails to be obtained from the nasopharyngeal cancer screening request, obtaining the customer attribute data of the to-screen customer from the nasopharyngeal cancer screening request;
  • the warning information corresponding to the determined risk level of nasopharyngeal cancer is output.
  • a second aspect of the present application provides a method for alerting a risk of nasopharyngeal cancer, the method comprising the steps of:
  • nasopharyngeal cancer screening request After receiving a nasopharyngeal cancer screening request from a client to be screened, obtaining a characteristic label of the customer to be screened from the nasopharyngeal cancer screening request;
  • the feature tag fails to be obtained from the nasopharyngeal cancer screening request, obtaining the customer attribute data of the to-screen customer from the nasopharyngeal cancer screening request;
  • the warning information corresponding to the determined risk level of nasopharyngeal cancer is output.
  • a third aspect of the present application provides a computer readable storage medium storing a nasopharyngeal cancer risk warning system, the nasopharyngeal cancer risk warning system being executable by at least one processor to cause the At least one processor performs the following steps:
  • nasopharyngeal cancer screening request After receiving a nasopharyngeal cancer screening request from a client to be screened, obtaining a characteristic label of the customer to be screened from the nasopharyngeal cancer screening request;
  • the feature tag fails to be obtained from the nasopharyngeal cancer screening request, obtaining the customer attribute data of the to-screen customer from the nasopharyngeal cancer screening request;
  • the warning information corresponding to the determined risk level of nasopharyngeal cancer is output.
  • the technical solution of the present application after receiving the nasopharyngeal cancer screening request of the client to be screened, obtains the characteristic label of the customer to be screened according to the nasopharyngeal cancer screening request, specifically screening directly from the nasopharyngeal cancer Obtaining a feature tag of the to-be-screened client in the request, and when the acquisition fails, acquiring various types of the customer attribute information from each predetermined service server according to the customer attribute information in the nasopharyngeal cancer screening request Feature data, and then extracting the feature tag of the customer to be screened from the feature data according to a preset extraction rule; and then predetermining the distinctive feature tag included in the feature tag (having a significant influence on nasopharyngeal cancer)
  • the number of characteristic tags is analyzed to obtain a risk level of the nasopharyngeal cancer of the customer to be screened, and an early warning information corresponding to the obtained risk level of the nasopharynge
  • the application firstly uses the large amount of characteristic data of the customer to be screened to obtain the characteristic label, and then determines the risk level of the nasopharyngeal cancer of the customer according to the number of characteristic labels included in the characteristic label that have a great influence on the nasopharyngeal cancer, and gives The customer's corresponding warning information allows the customer to prevent or treat it as soon as possible, thus effectively improving the condition of nasopharyngeal cancer.
  • FIG. 1 is a schematic flow chart of an embodiment of a method for early warning of nasopharyngeal cancer risk according to the present application
  • FIG. 2 is a schematic flow chart of a second embodiment of a method for early warning of nasopharyngeal cancer risk according to the present application
  • FIG. 3 is a schematic flow chart of a confirmation scheme of a predetermined distinctive feature label in the nasopharyngeal cancer risk warning method of the present application;
  • FIG. 4 is a schematic diagram of an operating environment of an embodiment of a nasopharyngeal cancer risk warning system according to the present application.
  • FIG. 5 is a program block diagram of an embodiment of a nasopharyngeal cancer risk warning system according to the present application.
  • FIG. 6 is a block diagram showing the program of the second embodiment of the nasopharyngeal cancer risk warning system of the present application.
  • FIG. 1 is a schematic flow chart of an embodiment of a method for early warning of nasopharyngeal cancer risk according to the present application.
  • the nasopharyngeal cancer risk warning method comprises:
  • Step S10 after receiving a nasopharyngeal cancer screening request of the client to be screened, obtaining a feature label of the customer to be screened from the nasopharyngeal cancer screening request;
  • the nasopharyngeal cancer screening request includes customer attribute data (eg, a certificate number, or a name and a document number) of the customer to be screened and/or a feature tag of the customer to be screened; wherein the feature tag includes basic feature information (eg, The city belongs to the northwestern part of China, the eating habits of the cities in which it belongs are spicy, the PM2.5 (fine particles) of the city is often exceeded, the bad weather in the city is too high, and the harmful gas positions are engaged, etc., and the preference information is preferred (for example, prefer to sleep late) , preference for tobacco and alcohol, preference for grilled food, preference for outdoor sports, etc.), behavioral information (for example, more games, more overtime, more take-outs, more medical visits, etc.) and/or social relationship information (for example, unmarried, Living alone, not always in contact with friends, etc.).
  • the screening server After receiving the nasopharyngeal cancer screening request from the client to be screened, the screening server first checks whether the
  • Step S20 if the feature tag fails to be obtained from the nasopharyngeal cancer screening request, obtaining the customer attribute data of the to-screen customer from the nasopharyngeal cancer screening request;
  • the nasopharyngeal cancer screening request does not include the customer's feature tag
  • the feature tag is not obtained from the nasopharyngeal cancer screening request (ie, the feature tag is failed to be acquired)
  • the nasopharyngeal cancer screening is performed.
  • the customer attribute data of the to-screen customer is obtained from the request, to obtain the feature label of the customer to be screened according to the customer attribute data of the screening customer.
  • Step S30 extracting, from a plurality of predetermined service servers, various feature data corresponding to the customer attribute data of the to-screen customer;
  • the screening server communicates with a plurality of predetermined business servers (eg, a bank server, a medical server, an insurance server, an instant messaging server, a game server, a weather server, a takeaway server, and/or a resume server, etc.); After the customer attribute data of the customer is to be screened, the screening server extracts various characteristic data corresponding to the customer attribute data of the to-screen customer from a plurality of predetermined business servers (for example, bank loan amount and repayment information) , outpatient medical record information "for example, the number of visits in a preset time, the type of disease, the duration of each illness, etc.”, insurance information "for example, the industry, gender, age, marital status, occupation, etc.”
  • Information about the use of the instant messaging tool account for example, information such as the communication tool daily login time information, daily online duration, etc.”, game information "for example, daily game login time information, daily game online duration, etc.”, weather information "for example , in the last three years, the number of days in which PM2.5 (fine
  • Step S40 Perform feature tag analysis on the extracted feature data according to a preset feature tag extraction rule to analyze the feature tag of the to-screen customer;
  • the extraction rule of the feature tag is preset in the screening server, and after extracting various feature data corresponding to the to-screen customer, the extraction rule is used to perform feature tag analysis on the extracted feature data, thereby analyzing The feature tag of the customer to be screened.
  • Step S50 performing quantitative analysis on the predetermined significant feature label in the feature tag of the customer to be screened, and determining the risk level of the nasopharyngeal cancer of the customer to be screened;
  • the pre-determined significant characteristic label contained therein is quantitatively analyzed, and the nasopharyngeal cancer risk level of the customer to be screened is determined according to the quantitative analysis (for example, the nasopharyngeal cancer risk level includes low The higher the risk level of nasopharyngeal cancer, the higher the risk level of nasopharyngeal cancer, the greater the chance that the client to be screened may have nasopharyngeal cancer.
  • Step S60 outputting early warning information corresponding to the determined risk level of nasopharyngeal cancer.
  • the screening server outputs corresponding preset warning information (ie, some precautions and health advice, etc.) according to the determined risk level of nasopharyngeal cancer.
  • the warning information corresponding to the low-risk level can be “****** customers, without significant features of nasopharyngeal cancer. It is recommended to conduct a nasopharyngeal cancer risk screening every year, do more indoor aerobic exercise, and participate less.
  • the warning information corresponding to the medium risk level can be “****** customers, with significant features of nasopharyngeal cancer, suggest further medical examinations, do more indoor aerobic exercise Less participation in outdoor strenuous exercise, early sleep and get up early;
  • the warning information corresponding to the high-risk level can be “****** customers, you are a high-risk target for nasopharyngeal cancer, and must do further medical examination within 7 days” ;and many more.
  • the technical solution of the embodiment after receiving the nasopharyngeal cancer screening request of the client to be screened, according to the nasopharyngeal cancer screening request, obtaining the characteristic label of the customer to be screened, specifically directly screening from the nasopharyngeal cancer Obtaining a feature tag of the to-screen customer in the request, and, when the acquisition fails, acquiring, according to the customer attribute information in the nasopharyngeal cancer screening request, each of the customer attribute information corresponding to each of the predetermined service servers Characteristic data, and extracting the feature tag of the customer to be screened from the feature data according to a preset extraction rule; and then predetermining the distinctive feature tag included in the feature tag (having a significant influence on nasopharyngeal cancer)
  • the number of characteristic tags is analyzed to obtain a risk level of the nasopharyngeal cancer of the customer to be screened, and an early warning information corresponding to the obtained risk level of the nasoph
  • the feature tag is obtained according to a large amount of characteristic data of the customer to be screened, and the risk level of the nasopharyngeal cancer of the client is determined according to the number of feature tags included in the feature tag that have a great influence on the nasopharyngeal cancer.
  • the risk level of the nasopharyngeal cancer of the client is determined according to the number of feature tags included in the feature tag that have a great influence on the nasopharyngeal cancer.
  • FIG. 2 is a schematic flow chart of a second embodiment of the method for early warning of nasopharyngeal cancer risk.
  • the nasopharyngeal cancer risk level includes a low risk level, a medium risk level, and a high risk level
  • the step S50 includes:
  • Step S51 analyzing whether there is a predetermined significant feature tag in the feature tag of the to-be-screened client;
  • the screening server first determines whether the feature tag of the to-be-screened customer contains a predetermined significant feature tag based on all the distinctive feature tags determined in advance.
  • Step S52 if there is no predetermined significant feature label, determining that the nasopharyngeal cancer risk level of the customer to be screened is a low risk level;
  • nasopharyngeal cancer risk level of the customer to be screened is a low risk level.
  • Step S53 if there is a predetermined significant feature tag, whether the number of the predetermined significant feature tags included in the analysis is greater than a preset number, or the number of predetermined significant feature tags included in the analysis accounts for all predetermined significant features. Whether the percentage of the total number of labels is greater than a preset percentage;
  • the risk level of the nasopharyngeal cancer is further determined according to the quantity of the predetermined significant feature tag included in the feature tag of the to-be-screened client; Specifically, comparing the number of the predetermined significant feature tags included in the feature tag of the to-screen customer to a preset number, or, by using the predetermined distinctive feature tag included in the feature tag of the to-screen customer The percentage of the number of all predetermined significant feature tags is compared to a preset percentage (eg, 80%).
  • Step S54 if the number of the predetermined significant feature tags is greater than the preset number, or the percentage of the predetermined significant feature tags is greater than the preset percentage by the total number of all the predetermined significant feature tags. Determining the risk level of nasopharyngeal cancer of the customer to be screened as a high risk level;
  • Step S55 if the number of the predetermined significant feature tags included is less than or equal to the preset number, or the percentage of the predetermined significant feature tags included in the total number of all the predetermined significant feature tags is less than or equal to the pre- If the percentage is set, it is determined that the risk level of the nasopharyngeal cancer of the customer to be screened is the medium risk level.
  • FIG. 3 is a schematic flowchart of a confirmation scheme of a predetermined distinctive feature label in the present application, where the determining step of the predetermined significant feature label includes:
  • Step S1 selecting a first preset number of customers, and obtaining customer attribute data of each selected customer;
  • the screening server selects a first predetermined number (for example, 10,000) of customers from the customer database (selected customers are customers who have determined whether they have nasopharyngeal cancer), and obtains customer attribute information of the customers (for example, the ID number) , or, name and ID number).
  • a first predetermined number for example, 10,000
  • customers are customers who have determined whether they have nasopharyngeal cancer
  • customer attribute information of the customers for example, the ID number
  • name and ID number for example, name and ID number
  • Step S2 extracting various feature data corresponding to customer attribute data of each customer from a plurality of predetermined service servers;
  • the screening server extracts feature data corresponding to the customer from each of the plurality of predetermined service servers to extract each customer in each predetermined Characteristic data in the business server.
  • the characteristic data is historical behavior data of the customer in the business server (for example, bank loan amount and repayment status information, outpatient medical record information, for example, the number of medical treatments in a preset time period, the type of disease, the disease each time) Duration, etc.”, insurance information "for example, industry, gender, age, marital status, occupation, etc.”, information on the use of instant messaging tool accounts "for example, information such as daily login time of communication tools, daily online duration, etc.” , game information “for example, daily game landing time information, daily game online time and other information", weather information "for example, in the last three years, PM2.5 (fine particles) seriously exceeded the number of days", take-out order information "for example, every day The time information of the takeaway, the type of takeaway that is taken out every day, etc.”, the information filled in the resume of the job search "
  • Step S3 performing feature tag analysis on the extracted feature data according to a preset feature tag extraction rule, to analyze feature tags of each client;
  • the screening server After extracting various feature data of each customer, the screening server performs feature tag analysis on each feature data of each customer according to a preset extraction rule, thereby obtaining a feature tag of each customer.
  • the feature tag includes basic feature information (for example, the city belongs to the northwestern region of China, the eating habits of the city to which it belongs is spicy, the PM2.5 (fine particles) of the city is often exceeded, the bad weather in the city is too high, and the hazardous gas positions are engaged, etc.)
  • Habit information for example, preference for late sleep, preference for tobacco and alcohol, preference for grilled food, preference for outdoor sports, etc.
  • behavioral information eg, more games, more overtime, more take-outs, more medical visits, etc.
  • Social relationship information for example, unmarried, living alone, not always in contact with friends, etc.
  • Step S4 determining, according to a predetermined mapping relationship between the nasopharyngeal cancer and the customer attribute data, an abnormal customer having a nasopharyngeal cancer and a normal client not having a nasopharyngeal cancer among the first predetermined number of customers;
  • the customer database records the disease label of each customer.
  • the screening server can determine which of the first preset number of customers is an abnormal customer with nasopharyngeal cancer, and which is the customer based on the customer's customer attribute data. A normal client who does not have nasopharyngeal cancer.
  • Step S5 using the feature tag corresponding to each normal client and the feature tag corresponding to each abnormal client as a training sample of the preset salient feature analysis model, and training the salient feature analysis model by using each of the training samples to determine various types. Ranking of the importance of feature tags in the salient feature analysis model;
  • the salient feature analysis model used in the embodiment is a gradient promotion decision tree model
  • the training step of the salient feature analysis model includes: training the salient feature analysis model by using each of the training samples to construct multiple trees.
  • Iterative decision tree select the top N decision trees with the highest accuracy as the final training result of the model; output the importance order of all feature tags in the salient feature analysis model according to the selected decision tree (if a feature tag and whether or not If the disease is irrelevant, it is not included in the decision tree model).
  • step S6 various feature tags are subjected to preset type analysis according to the order of importance in the salient feature analysis model, and a significant feature tag having a significant influence on nasopharyngeal carcinoma is analyzed.
  • the preset type analysis for example, BI (Business Intelligence) analysis, can verify whether the different values of each feature tag have a significant difference in the prevalence of nasopharyngeal cancer by BI analysis, if a The difference in the value of the characteristic label has a significant difference in the prevalence of nasopharyngeal carcinoma, and it is determined that the characteristic label is a significant characteristic label.
  • BI Business Intelligence
  • the feature tag extraction rule preset in the nasopharyngeal cancer risk warning method of the present application is: setting a corresponding tag threshold for various feature data types of consecutive values;
  • the labeling threshold of the number of days in which the city PM2.5 (fine particles) exceeds the standard in the last three years may be 60 days.
  • the tag threshold corresponding to the number of days above the blue warning level of the city in the last three years may be 55 days.
  • the threshold is "55 days", it means that the bad weather in the city is too much; the number of days in the last year after sleeping at 23:00 in the last year may be 100 days.
  • the number of days in the last year is more than 23:00, the number of days is greater than the corresponding one.
  • the label threshold is "100 days", it means that it is preferred to sleep late; the labeling threshold of the number of take-outs of the barbecue in the most recent year may be 80 times.
  • the label threshold corresponding to the number of medical treatments in the last year may be 30 times, when the number of medical treatments in the most recent year is greater than the corresponding label threshold "30 times” , representing the number of medical treatments.
  • the label range corresponding to the city includes: a collection of cities in the northwest region, a collection of cities in the North China region, a collection of cities in the Central China region, a collection of cities in the South China region, etc., when the city to which the customer belongs belongs to the city in the northwest region city collection,
  • the label information corresponding to the city to which the customer belongs is “belonging to Northwest China”;
  • the label range corresponding to the eating habits of the city includes: spicy city collection, partial greasy city collection, partial light city collection, partial sweet/salty city combination, etc.
  • the label information corresponding to the city to which the customer belongs is “the eating habit is spicy”; the label range corresponding to the position includes: the collection of harmful gas positions, non-volatile and harmful The collection of gas positions, the collection of positions that are prone to generate volatile harmful gases, and the collection of harmless gas positions, etc.
  • the label information corresponding to the industry in which the customer is engaged is “working with harmful gases”. post”.
  • the tag information corresponding to the feature data of various continuous values of each client is determined, and the mapping relationship between various feature data types and tag ranges according to non-continuous values is determined.
  • the tag information corresponding to the feature data of various non-continuous values of each client is determined.
  • the present application also proposes a nasopharyngeal cancer risk warning system.
  • FIG. 4 is a schematic diagram of an operating environment of an embodiment of the nasopharyngeal cancer risk warning system 10 of the present application.
  • the nasopharyngeal cancer risk warning system 10 is installed and operated in the electronic device 1.
  • the electronic device 1 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a server.
  • the electronic device 1 may include, but is not limited to, a memory 11, a processor 12, and a display 13.
  • Figure 4 shows only the electronic device 1 with components 11-13, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.
  • the memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a hard disk or memory of the electronic device 1.
  • the memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in hard disk equipped on the electronic device 1, a smart memory card (SMC), and a secure digital (SD). Card, flash card, etc.
  • the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device.
  • the memory 11 is used to store application software and various types of data installed in the electronic device 1, such as program codes of the nasopharyngeal cancer risk warning system 10.
  • the memory 11 can also be used to temporarily store data that has been output or is about to be output.
  • the processor 12 may be a Central Processing Unit (CPU), microprocessor or other data processing chip for running program code or processing data stored in the memory 11, such as performing nasopharyngeal carcinoma Risk warning system 10, etc.
  • CPU Central Processing Unit
  • microprocessor or other data processing chip for running program code or processing data stored in the memory 11, such as performing nasopharyngeal carcinoma Risk warning system 10, etc.
  • the display 13 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch sensor, or the like in some embodiments.
  • the display 13 is for displaying information processed in the electronic device 1 and a user interface for displaying visualization.
  • the components 11-13 of the electronic device 1 communicate with one another via a system bus.
  • FIG. 5 is a program block diagram of a preferred embodiment of the nasopharyngeal cancer risk warning system 10 of the present application.
  • the nasopharyngeal cancer risk warning system 10 can be divided into one or more modules, one or more modules being stored in the memory 11 and being processed by one or more processors (this embodiment is a processor) 12) Executed to complete the application.
  • the nasopharyngeal cancer risk warning system 10 can be divided into a first acquisition module 101, a second acquisition module 102, an extraction module 103, a first analysis module 104, a second analysis module 105, and an early warning output module 106. .
  • the module referred to in the present application refers to a series of computer program instruction segments capable of performing a specific function, and is more suitable than the program for describing the execution process of the nasopharyngeal cancer risk warning system 10 in the electronic device 1, wherein:
  • the first obtaining module 101 is configured to obtain, after receiving a nasopharyngeal cancer screening request of the client to be screened, the feature label of the to-screen customer from the nasopharyngeal cancer screening request;
  • the nasopharyngeal cancer screening request includes customer attribute data (eg, a certificate number, or a name and a document number) of the customer to be screened and/or a feature tag of the customer to be screened; wherein the feature tag includes basic feature information (eg, The city belongs to the northwestern part of China, the eating habits of the cities in which it belongs are spicy, the PM2.5 (fine particles) of the city is often exceeded, the bad weather in the city is too high, and the harmful gas positions are engaged, etc., and the preference information is preferred (for example, prefer to sleep late) , preference for tobacco and alcohol, preference for grilled food, preference for outdoor sports, etc.), behavioral information (for example, more games, more overtime, more take-outs, more medical visits, etc.) and/or social relationship information (for example, unmarried, Living alone, not always in contact with friends, etc.).
  • the screening server After receiving the nasopharyngeal cancer screening request from the client to be screened, the screening server first checks whether the
  • the second obtaining module 102 is configured to obtain, after the failure of acquiring the feature tag from the nasopharyngeal cancer screening request, the customer attribute data of the to-screen customer to be obtained from the nasopharyngeal cancer screening request;
  • the nasopharyngeal cancer screening request does not include the customer's feature tag
  • the feature tag is not obtained from the nasopharyngeal cancer screening request (ie, the feature tag is failed to be acquired)
  • the nasopharyngeal cancer screening is performed.
  • the customer attribute data of the to-screen customer is obtained from the request, to obtain the feature label of the customer to be screened according to the customer attribute data of the screening customer.
  • the extracting module 103 is configured to extract, from a plurality of predetermined service servers, various feature data corresponding to the customer attribute data of the to-be-screened client;
  • the screening server communicates with a plurality of predetermined business servers (eg, a bank server, a medical server, an insurance server, an instant messaging server, a game server, a weather server, a takeaway server, and/or a resume server, etc.); After the customer attribute data of the customer is to be screened, the screening server extracts various characteristic data corresponding to the customer attribute data of the to-screen customer from a plurality of predetermined business servers (for example, bank loan amount and repayment information) , outpatient medical record information "for example, the number of visits in a preset time, the type of disease, the duration of each illness, etc.”, insurance information "for example, the industry, gender, age, marital status, occupation, etc.”
  • Information about the use of the instant messaging tool account for example, information such as the communication tool daily login time information, daily online duration, etc.”, game information "for example, daily game login time information, daily game online duration, etc.”, weather information "for example , in the last three years, the number of days in which PM2.5 (fine
  • the first analysis module 104 is configured to perform feature tag analysis on the extracted feature data according to a preset feature tag extraction rule to analyze the feature tag of the to-screen customer;
  • the extraction rule of the feature tag is preset in the screening server, and after extracting various feature data corresponding to the to-screen customer, the extraction rule is used to perform feature tag analysis on the extracted feature data, thereby analyzing The feature tag of the customer to be screened.
  • the second analysis module 105 is configured to perform quantity analysis on the predetermined significant feature label in the feature tag of the customer to be screened to determine the risk level of the nasopharyngeal cancer of the customer to be screened;
  • the pre-determined significant characteristic label contained therein is quantitatively analyzed, and the nasopharyngeal cancer risk level of the customer to be screened is determined according to the quantitative analysis (for example, the nasopharyngeal cancer risk level includes low The higher the risk level of nasopharyngeal cancer, the higher the risk level of nasopharyngeal cancer, the greater the chance that the client to be screened may have nasopharyngeal cancer.
  • the warning output module 106 is configured to output early warning information corresponding to the determined risk level of nasopharyngeal cancer.
  • the screening server outputs corresponding preset warning information (ie, some precautions and health advice, etc.) based on the determined risk level of nasopharyngeal cancer.
  • the warning information corresponding to the low-risk level can be “****** customers, without significant features of nasopharyngeal cancer. It is recommended to conduct a nasopharyngeal cancer risk screening every year, do more indoor aerobic exercise, and participate less.
  • the warning information corresponding to the medium risk level can be “****** customers, with significant features of nasopharyngeal cancer, suggest further medical examinations, do more indoor aerobic exercise Less participation in outdoor strenuous exercise, early sleep and get up early;
  • the warning information corresponding to the high-risk level can be “****** customers, you are a high-risk target for nasopharyngeal cancer, and must do further medical examination within 7 days” ;and many more.
  • the technical solution of the embodiment after receiving the nasopharyngeal cancer screening request of the client to be screened, according to the nasopharyngeal cancer screening request, obtaining the characteristic label of the customer to be screened, specifically directly screening from the nasopharyngeal cancer Obtaining a feature tag of the to-screen customer in the request, and, when the acquisition fails, acquiring, according to the customer attribute information in the nasopharyngeal cancer screening request, each of the customer attribute information corresponding to each of the predetermined service servers Characteristic data, and extracting the feature tag of the customer to be screened from the feature data according to a preset extraction rule; and then predetermining the distinctive feature tag included in the feature tag (having a significant influence on nasopharyngeal cancer)
  • the number of characteristic tags is analyzed to obtain a risk level of the nasopharyngeal cancer of the customer to be screened, and an early warning information corresponding to the obtained risk level of the nasoph
  • the feature tag is obtained according to a large amount of characteristic data of the customer to be screened, and the risk level of the nasopharyngeal cancer of the client is determined according to the number of feature tags included in the feature tag that have a great influence on the nasopharyngeal cancer.
  • the risk level of the nasopharyngeal cancer of the client is determined according to the number of feature tags included in the feature tag that have a great influence on the nasopharyngeal cancer.
  • FIG. 6 is a program block diagram of a second embodiment of the nasopharyngeal cancer risk warning system of the present application.
  • the nasopharyngeal cancer risk level includes a low risk level, a medium risk level, and a high risk level
  • the second analysis module 105 includes:
  • the first analysis sub-module 1051 is configured to analyze whether there is a predetermined significant feature tag in the feature tag of the to-be-screened client;
  • the screening server first determines whether the feature tag of the to-be-screened customer contains a predetermined significant feature tag based on all the distinctive feature tags determined in advance.
  • the determining sub-module 1052 is configured to determine that the nasopharyngeal cancer risk level of the to-screen customer is a low risk level when there is no predetermined significant feature label in the feature tag of the to-screen customer;
  • nasopharyngeal cancer risk level of the customer to be screened is a low risk level.
  • the second analysis sub-module 1053 is configured to analyze whether the quantity of the predetermined significant feature tag included in the feature tag of the to-be-screened client has a predetermined number of significant feature tags, or Whether the predetermined number of significant feature tags accounts for a percentage of the total number of all predetermined significant feature tags is greater than a preset percentage;
  • the risk level of the nasopharyngeal cancer is further determined according to the quantity of the predetermined significant feature tag included in the feature tag of the to-be-screened client; Specifically, comparing the number of the predetermined significant feature tags included in the feature tag of the to-screen customer to a preset number, or, by using the predetermined distinctive feature tag included in the feature tag of the to-screen customer The percentage of the number of all predetermined significant feature tags is compared to a preset percentage (eg, 80%).
  • the determining sub-module 1052 is further configured to: when the number of predetermined significant feature tags included is greater than a preset number, or the number of predetermined significant feature tags included in the total number of all the predetermined significant feature tags When the percentage is greater than the preset percentage, it is determined that the risk level of the nasopharyngeal cancer of the customer to be screened is a high risk level;
  • the determining sub-module 1052 is further configured to: when the number of the predetermined distinctive feature tags included is less than or equal to the preset number, or the total number of the predetermined significant feature tags included in the total of all the predetermined salient feature tags When the percentage of the quantity is less than or equal to the preset percentage, it is determined that the risk level of the nasopharyngeal cancer of the customer to be screened is the medium risk level.
  • the determining the predetermined distinctive feature label includes the following steps:
  • the screening server selects a first predetermined number (for example, 10,000) of customers from the customer database (selected customers are customers who have determined whether they have nasopharyngeal cancer), and obtains customer attribute information of the customers (for example, the ID number) , or, name and ID number).
  • a first predetermined number for example, 10,000
  • customers are customers who have determined whether they have nasopharyngeal cancer
  • customer attribute information of the customers for example, the ID number
  • name and ID number for example, name and ID number
  • the screening server extracts feature data corresponding to the customer from each of the plurality of predetermined service servers to extract each customer in each predetermined Characteristic data in the business server.
  • the characteristic data is historical behavior data of the customer in the business server (for example, bank loan amount and repayment status information, outpatient medical record information, for example, the number of medical treatments in a preset time period, the type of disease, the disease each time) Duration, etc.”, insurance information "for example, industry, gender, age, marital status, occupation, etc.”, information on the use of instant messaging tool accounts "for example, information such as daily login time of communication tools, daily online duration, etc.” , game information “for example, daily game landing time information, daily game online time and other information", weather information "for example, in the last three years, PM2.5 (fine particles) seriously exceeded the number of days", take-out order information "for example, every day The time information of the takeaway, the type of takeaway that is taken out every day, etc.”, the information filled in the resume of the job search "
  • the screening server After extracting various feature data of each customer, the screening server performs feature tag analysis on each feature data of each customer according to a preset extraction rule, thereby obtaining a feature tag of each customer.
  • the feature tag includes basic feature information (for example, the city belongs to the northwestern region of China, the eating habits of the city to which it belongs is spicy, the PM2.5 (fine particles) of the city is often exceeded, the bad weather in the city is too high, and the hazardous gas positions are engaged, etc.)
  • Habit information for example, preference for late sleep, preference for tobacco and alcohol, preference for grilled food, preference for outdoor sports, etc.
  • behavioral information eg, more games, more overtime, more take-outs, more medical visits, etc.
  • Social relationship information for example, unmarried, living alone, not always in contact with friends, etc.
  • the customer database records the disease label of each customer.
  • the screening server can determine which of the first preset number of customers is an abnormal customer with nasopharyngeal cancer, and which is the customer based on the customer's customer attribute data. A normal client who does not have nasopharyngeal cancer.
  • the feature tag corresponding to each normal customer and the feature tag corresponding to each abnormal customer are used as training samples of the preset salient feature analysis model, and the salient feature analysis model is trained by using each of the training samples to determine various features.
  • the salient feature analysis model used in the embodiment is a gradient promotion decision tree model
  • the training step of the salient feature analysis model includes: training the salient feature analysis model by using each of the training samples to construct multiple trees.
  • Iterative decision tree select the top N decision trees with the highest accuracy as the final training result of the model; output the importance order of all feature tags in the salient feature analysis model according to the selected decision tree (if a feature tag and whether or not If the disease is irrelevant, it is not included in the decision tree model).
  • the preset type analysis for example, BI (Business Intelligence) analysis, can verify whether the different values of each feature tag have a significant difference in the prevalence of nasopharyngeal cancer by BI analysis, if a The difference in the value of the characteristic label has a significant difference in the prevalence of nasopharyngeal carcinoma, and it is determined that the characteristic label is a significant characteristic label.
  • BI Business Intelligence
  • the preset feature label extraction rule is: setting a corresponding label threshold for various characteristic data types of continuous values;
  • the labeling threshold of the number of days in which the city PM2.5 (fine particles) exceeds the standard in the last three years may be 60 days.
  • the tag threshold corresponding to the number of days above the blue warning level of the city in the last three years may be 55 days.
  • the threshold is "55 days", it means that the bad weather in the city is too much; the number of days in the last year after sleeping at 23:00 in the last year may be 100 days.
  • the number of days in the last year is more than 23:00, the number of days is greater than the corresponding one.
  • the label threshold is "100 days", it means that it is preferred to sleep late; the labeling threshold of the number of take-outs of the barbecue in the most recent year may be 80 times.
  • the label threshold corresponding to the number of medical treatments in the last year may be 30 times, when the number of medical treatments in the most recent year is greater than the corresponding label threshold "30 times" , The number of medical representatives and more.
  • the label range corresponding to the city includes: a collection of cities in the northwest region, a collection of cities in the North China region, a collection of cities in the Central China region, a collection of cities in the South China region, etc., when the city to which the customer belongs belongs to the city in the northwest region city collection,
  • the label information corresponding to the city to which the customer belongs is “belonging to Northwest China”;
  • the label range corresponding to the eating habits of the city includes: spicy city collection, partial greasy city collection, partial light city collection, partial sweet/salty city combination, etc.
  • the label information corresponding to the city to which the customer belongs is “the eating habit is spicy”; the label range corresponding to the position includes: the collection of harmful gas positions, non-volatile and harmful The collection of gas positions, the collection of positions that are prone to generate volatile harmful gases, and the collection of harmless gas positions, etc.
  • the label information corresponding to the industry in which the customer is engaged is “working with harmful gases”. post”.
  • the tag information corresponding to the feature data of various continuous values of each client is determined, and the mapping relationship between various feature data types and tag ranges according to non-continuous values is determined.
  • the tag information corresponding to the feature data of various non-continuous values of each client is determined.
  • the present application further provides a computer readable storage medium storing a nasopharyngeal cancer risk warning system, the nasopharyngeal cancer risk warning system being executable by at least one processor to The at least one processor executes the nasopharyngeal cancer risk warning method in any of the above embodiments.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

一种电子装置、鼻咽癌风险预警方法及计算机可读存储介质，该方法包括：在收到一个待筛查客户的鼻咽癌筛查请求后，从鼻咽癌筛查请求中获取该待筛查客户的特征标签（S10）；若从所述鼻咽癌筛查请求中获取特征标签失败，则从鼻咽癌筛查请求中获取该待筛查客户的客户属性数据（S20）；从多个预先确定的业务服务器提取出与该待筛查客户的客户属性数据对应的各种特征数据（S30）；按照预设的特征标签提取规则，对提取出的各种特征数据进行特征标签分析，以分析出该待筛查客户的特征标签（S40）；对该待筛查客户的特征标签中的预先确定的显著特征标签进行数量分析，确定出该待筛查客户的鼻咽癌风险等级（S50）；输出与确定的鼻咽癌风险等级对应的预警信息（S60）。该方法实现了让客户及早的对鼻咽癌进行预防或治疗，有效的改善鼻咽癌的患病情况。

Description

电子装置、鼻咽癌风险预警方法和计算机可读存储介质
本申请基于巴黎公约申明享有2018年4月9日递交的申请号为CN 2018103116455、名称为“电子装置、鼻咽癌风险预警方法和计算机可读存储介质”中国专利申请的优先权，该中国专利申请的整体内容以参考的方式结合在本申请中。
技术领域
本申请涉及大数据分析技术领域，特别涉及一种电子装置、鼻咽癌风险预警方法和计算机可读存储介质。
背景技术
鼻咽癌是一种高发恶性肿瘤，发病率为耳鼻咽喉恶性肿瘤之首，病因复杂。传统医学上对鼻咽癌的发病原因尚不明确，现有的研究大多来自于临床观察(与遗传、环境、病毒有关)。而临床观察获取个人信息有限，同时，现有的研究通常依赖于研究人员专业医学知识和个人经验，因此，研究的准确性无法满足要求，无法形成客观准确的、指标明确的发病原因筛查体系。
因此，如何实现对鼻咽癌致病原因的客观准确的、指标明确的筛查，进而实现及早预防和干预，已经成为一个亟待解决的技术问题。
发明内容
本申请的主要目的是提供一种电子装置、鼻咽癌风险预警方法和计算机可读存储介质，旨在及早的让客户进行预防或治疗，改善鼻咽癌的患病情况。
本申请第一方面提供一种电子装置，包括存储器和处理器，所述存储器上存储有可在所述处理器上运行的鼻咽癌风险预警系统，所述鼻咽癌风险预警系统被所述处理器执行时实现如下步骤：
在收到一个待筛查客户的鼻咽癌筛查请求后，从所述鼻咽癌筛查请求中获取该待筛查客户的特征标签；
若从所述鼻咽癌筛查请求中获取特征标签失败，则从所述鼻咽癌筛查请求中获取该待筛查客户的客户属性数据；
从多个预先确定的业务服务器提取出与该待筛查客户的客户属性数据对应的各种特征数据；
按照预设的特征标签提取规则，对提取出的各种特征数据进行特征标签分析，以分析出该待筛查客户的特征标签；
对该待筛查客户的特征标签中的预先确定的显著特征标签进行数量分析，确定出该待筛查客户的鼻咽癌风险等级；
输出与确定的鼻咽癌风险等级对应的预警信息。
本申请第二方面提供一种鼻咽癌风险预警方法，该方法包括步骤：
在收到一个待筛查客户的鼻咽癌筛查请求后，从所述鼻咽癌筛查请求中 获取该待筛查客户的特征标签；
若从所述鼻咽癌筛查请求中获取特征标签失败，则从所述鼻咽癌筛查请求中获取该待筛查客户的客户属性数据；
从多个预先确定的业务服务器提取出与该待筛查客户的客户属性数据对应的各种特征数据；
按照预设的特征标签提取规则，对提取出的各种特征数据进行特征标签分析，以分析出该待筛查客户的特征标签；
对该待筛查客户的特征标签中的预先确定的显著特征标签进行数量分析，确定出该待筛查客户的鼻咽癌风险等级；
输出与确定的鼻咽癌风险等级对应的预警信息。
本申请第三方面提供一种计算机可读存储介质，所述计算机可读存储介质存储有鼻咽癌风险预警系统，所述鼻咽癌风险预警系统可被至少一个处理器执行，以使所述至少一个处理器执行如下步骤：
在收到一个待筛查客户的鼻咽癌筛查请求后，从所述鼻咽癌筛查请求中获取该待筛查客户的特征标签；
若从所述鼻咽癌筛查请求中获取特征标签失败，则从所述鼻咽癌筛查请求中获取该待筛查客户的客户属性数据；
从多个预先确定的业务服务器提取出与该待筛查客户的客户属性数据对应的各种特征数据；
按照预设的特征标签提取规则，对提取出的各种特征数据进行特征标签分析，以分析出该待筛查客户的特征标签；
对该待筛查客户的特征标签中的预先确定的显著特征标签进行数量分析，确定出该待筛查客户的鼻咽癌风险等级；
输出与确定的鼻咽癌风险等级对应的预警信息。
本申请技术方案，在接收到待筛查客户的鼻咽癌筛查请求后，根据该鼻咽癌筛查请求去获取该待筛查客户的特征标签，具体为先直接从鼻咽癌筛查请求中获取该待筛查客户的特征标签，在获取失败时，则根据该鼻咽癌筛查请求中的客户属性信息，去从各个预先确定的业务服务器中获取该客户属性信息对应的各种特征数据，再按照预设的提取规则从这些特征数据中提取出该待筛查客户的特征标签；再对该特征标签中包含的预先确定的显著特征标签(对患鼻咽癌有显著影响的特征标签)的数量进行分析，从而得出该待筛查客户的鼻咽癌风险等级，输出与该得出的鼻咽癌风险等级对应的预警信息给客户。本申请先采用根据待筛查客户的大量特征数据得出其特征标签，再根据特征标签中的包含的对患鼻咽癌影响大的特征标签的数量确定客户的鼻咽癌风险等级，并给予客户对应的预警信息，让客户可以及早的进行预防或治疗，从而有效的改善鼻咽癌的患病情况。
附图说明
图1为本申请鼻咽癌风险预警方法一实施例的流程示意图；
图2为本申请鼻咽癌风险预警方法二实施例的流程示意图；
图3为本申请本申请鼻咽癌风险预警方法中预先确定的显著特征标签的确认方案的流程示意图；
图4为本申请鼻咽癌风险预警系统一实施例的运行环境示意图；
图5为本申请鼻咽癌风险预警系统一实施例的程序模块图；
图6为本申请鼻咽癌风险预警系统二实施例的程序模块图。
具体实施方式
以下结合附图对本申请的原理和特征进行描述，所举实例只用于解释本申请，并非用于限定本申请的范围。
如图1所示，图1为本申请鼻咽癌风险预警方法一实施例的流程示意图。
本实施例中，该鼻咽癌风险预警方法包括：
步骤S10，在收到一个待筛查客户的鼻咽癌筛查请求后，从所述鼻咽癌筛查请求中获取该待筛查客户的特征标签；
鼻咽癌筛查请求中包含待筛查客户的客户属性数据(例如，证件号码，或者，姓名和证件号码)及/或待筛查客户的特征标签；其中，特征标签包括基本特征信息(例如，所属城市属于中国西北地区、所属城市饮食习惯偏辛辣、所属城市PM2.5(细颗粒物)经常超标、所属城市恶劣天气偏多、从事有害气体岗位等)、偏好习惯信息(例如，偏好晚睡、偏好烟酒、偏好烧烤食物、偏好户外运动等)、行为信息(例如，游戏次数多、加班次数多、点外卖的次数多、就医次数多等)及/或社会关系信息(例如，未婚、独居、不经常与朋友联系等)。筛查服务器在收到一个待筛查客户的鼻咽癌筛查请求后，先看该请求中是否包含了该客户的特征标签，即从中去获取该客户的特征标签。
步骤S20，若从所述鼻咽癌筛查请求中获取特征标签失败，则从所述鼻咽癌筛查请求中获取该待筛查客户的客户属性数据；
如果该鼻咽癌筛查请求中没有包含该客户的特征标签，则从该鼻咽癌筛查请求中获取不到特征标签(即获取特征标签失败)，那么，则从该鼻咽癌筛查请求中获取该待筛查客户的客户属性数据，以根据该带筛查客户的客户属性数据去获得该待筛查客户的特征标签。
步骤S30，从多个预先确定的业务服务器提取出与该待筛查客户的客户属性数据对应的各种特征数据；
筛查服务器与多个预先确定的业务服务器(例如，银行服务器、医疗服务器、保险服务器、即时通讯服务器、游戏服务器、天气服务器、外卖服务器及/或简历服务器等)之间通讯；在获取到该待筛查客户的客户属性数据后，筛查服务器从多个预先确定的业务服务器提取出与该待筛查客户的客户属性数据对应的各种特征数据(例如，银行贷款额度及还款情况信息、门诊病历信息“例如，预设时间内的看病次数、所患的疾病种类、每次患病的持续时间等”、保险信息“例如，所处行业，性别、年龄、婚姻状况、职业等”、即时通讯工具账号的使用信息“例如，通讯工具每天登陆时间信息、每天在线 时长等信息”等等、游戏信息“例如，每天游戏登陆时间信息、每天游戏在线时长等信息”、天气信息“例如，最近三年内，PM2.5(细颗粒物)严重超标的天数”、外卖点餐信息“例如，每天点外卖的时间信息、每天所点外卖的外卖类型等”、求职简历上填写的信息“例如，兴趣爱好、性格、工作经历等信息”)。
步骤S40，按照预设的特征标签提取规则，对提取出的各种特征数据进行特征标签分析，以分析出该待筛查客户的特征标签；
筛查服务器中预先设置了特征标签的提取规则，在提取出该待筛查客户对应的各种特征数据后，利用该提取规则，对提取出的各种特征数据进行特征标签分析，从而分析得到该待筛查客户的特征标签。
步骤S50，对该待筛查客户的特征标签中的预先确定的显著特征标签进行数量分析，确定出该待筛查客户的鼻咽癌风险等级；
筛查服务器中预先确定了哪些特征标签为显著特征标签(即对患鼻咽癌有显著影响的特征标签)，预先确定的显著特征标签为对鼻咽癌有显著影响的特征标签；在得到该待筛查客户的特征标签后，对其中包含的预先确定的显著特征标签进行数量分析，根据数量分析，确定出该待筛查客户的鼻咽癌风险等级(例如，鼻咽癌风险等级包括低风险等级、中风险等级和高风险等级)，鼻咽癌风险等级越高，表示该待筛查客户可能会患鼻咽癌的几率越大。
步骤S60，输出与确定的鼻咽癌风险等级对应的预警信息。
筛查服务器根据所确定的鼻咽癌风险等级，输出相对应的预设预警信息(即一些注意事项和健康建议等)。例如，低风险等级对应的预警信息可以为“******客户，不带有鼻咽癌显著特征标签，建议每年进行一次鼻咽癌风险筛查，多做室内有氧运动，少参加室外剧烈运动，早睡早起”；与中风险等级对应的预警信息可以为“******客户，带有鼻咽癌显著特征标签，建议做进一步的医学检查，多做室内有氧运动，少参加室外剧烈运动，早睡早起”；与高风险等级对应的预警信息可以为“******客户，您属于鼻咽癌的高危对象，务必于7天内做进一步的医学检查”；等等。
本实施例技术方案，在接收到待筛查客户的鼻咽癌筛查请求后，根据该鼻咽癌筛查请求去获取该待筛查客户的特征标签，具体为先直接从鼻咽癌筛查请求中获取该待筛查客户的特征标签，在获取失败时，则根据该鼻咽癌筛查请求中的客户属性信息，去从各个预先确定的业务服务器中获取该客户属性信息对应的各种特征数据，再按照预设的提取规则从这些特征数据中提取出该待筛查客户的特征标签；再对该特征标签中包含的预先确定的显著特征标签(对患鼻咽癌有显著影响的特征标签)的数量进行分析，从而得出该待筛查客户的鼻咽癌风险等级，输出与该得出的鼻咽癌风险等级对应的预警信息给客户。本实施例先采用根据待筛查客户的大量特征数据得出其特征标签，再根据特征标签中的包含的对患鼻咽癌影响大的特征标签的数量确定客户的鼻咽癌风险等级，并给予客户对应的预警信息，让客户可以及早的进行预防或治疗，从而有效的改善鼻咽癌的患病情况。
如图2所示，图2为本申请鼻咽癌风险预警方法二实施例的流程示意图。
本实施例中，所述鼻咽癌风险等级包括低风险等级、中风险等级和高风险等级，所述步骤S50包括：
步骤S51，分析该待筛查客户的特征标签中是否有预先确定的显著特征标签；
筛查服务器首先根据预先确定的所有显著特征标签判断该待筛查客户的特征标签中有没有含有预先确定的显著特征标签。
步骤S52，若无预先确定的显著特征标签，则确定该待筛查客户的鼻咽癌风险等级为低风险等级；
如果该待筛查客户的所有特征标签中没有包含任何一个预先确定的显著特征标签，则判定该待筛查客户的鼻咽癌风险等级为低风险等级。
步骤S53，若有预先确定的显著特征标签，则分析含有的预先确定的显著特征标签的数量是否大于预设数量，或者，分析含有的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总数量的百分比是否大于预设百分比；
若判定得该待筛查客户的特征标签中含有预先确定的显著特征标签，则进一步根据该待筛查客户的特征标签中包含的预先确定的显著特征标签的数量判断其鼻咽癌风险等级；具体为，将该待筛查客户的特征标签中包含的预先确定的显著特征标签的数量与预设数量比较，或者，将该待筛查客户的特征标签中包含的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的数量的百分比，与预设百分比(例如，80％)进行比较。
步骤S54，若含有的预先确定的显著特征标签的数量大于预设数量，或者，含有的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总数量的百分比大于预设百分比，则确定该待筛查客户的鼻咽癌风险等级为高风险等级；
步骤S55，若含有的预先确定的显著特征标签的数量小于或者等于预设数量，或者，含有的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总数量的百分比小于或者等于预设百分比，则确定该待筛查客户的鼻咽癌风险等级为中风险等级。
如图3所示，图3为本申请中预先确定的显著特征标签的确认方案的流程示意图，所述预先确定的显著特征标签的确定步骤包括：
步骤S1，选取第一预设数量的客户，并获取选取的各个客户的客户属性数据；
筛查服务器从客户数据库中选取第一预设数量(例如10000个)的客户(选取的客户都是已经确定是否患鼻咽癌的客户)，并获取这些客户的客户属性信息(例如，证件号码，或者，姓名和证件号码)。
步骤S2，从多个预先确定的业务服务器分别提取出与各个客户的客户属 性数据对应的各种特征数据；
针对这第一预设数量的客户中的每一个客户，筛查服务器从多个预先确定的业务服务器中的每一个服务器分别提取该客户对应的特征数据，以提取出每一个客户在各个预先确定的业务服务器中的特征数据。该特征数据即客户在业务服务器中的历史行为数据(例如，银行贷款额度及还款情况信息、门诊病历信息“例如，预设时间内的看病次数、所患的疾病种类、每次患病的持续时间等”、保险信息“例如，所处行业，性别、年龄、婚姻状况、职业等”、即时通讯工具账号的使用信息“例如，通讯工具每天登陆时间信息、每天在线时长等信息”等等、游戏信息“例如，每天游戏登陆时间信息、每天游戏在线时长等信息”、天气信息“例如，最近三年内，PM2.5(细颗粒物)严重超标的天数”、外卖点餐信息“例如，每天点外卖的时间信息、每天所点外卖的外卖类型等”、求职简历上填写的信息“例如，兴趣爱好、性格、工作经历等信息”)。
步骤S3，按照预设的特征标签提取规则，对提取出的各种特征数据进行特征标签分析，以分析出各个客户的特征标签；
在提取得到各个客户的各种特征数据后，筛查服务器按照预设的提取规则，对每个客户的各种特征数据分别进行特征标签分析，从而得出每个客户的特征标签。特征标签包括基本特征信息(例如，所属城市属于中国西北地区、所属城市饮食习惯偏辛辣、所属城市PM2.5(细颗粒物)经常超标、所属城市恶劣天气偏多、从事有害气体岗位等)、偏好习惯信息(例如，偏好晚睡、偏好烟酒、偏好烧烤食物、偏好户外运动等)、行为信息(例如，游戏次数多、加班次数多、点外卖的次数多、就医次数多等)及/或社会关系信息(例如，未婚、独居、不经常与朋友联系等)。
步骤S4，根据预先确定的鼻咽癌与客户属性数据的映射关系，确定所述第一预设数量的客户中患有鼻咽癌的异常客户和未患鼻咽癌的正常客户；
客户数据库中记录了每个客户的患病标签，筛查服务器根据客户的客户属性数据通过查找数据库就可确定该第一预设数量的客户中，哪些为患有鼻咽癌的异常客户，哪些为未患鼻咽癌的正常客户。
步骤S5，将各个正常客户对应的特征标签和各个异常客户对应的特征标签作为预设的显著特征分析模型的训练样本，利用各个所述训练样本训练所述显著特征分析模型，以确定出各种特征标签在所述显著特征分析模型中的重要性排序；
也就是，每一个正常客户对应的所有特征标签作为一个训练样本，每一个异常客户对应的所有特征标签作为一个训练样本，正常客户对应的特征标签是对应不患鼻咽癌的，异常客户的特征标签是对应患鼻咽癌的，这样总共有第一预设数量的训练样本去训练预设的显著特征分析模型，通过训练得到各个特征标签在该显著特征分析模型中的重要性排序。优选地，本实施例中采用的所述显著特征分析模型为梯度提升决策树模型，所述显著特征分析模型的训练步骤包括：利用各个所述训练样本训练所述显著特征分析模型，构 建多棵迭代决策树，选择精确率最高的前N棵决策树作为模型的最终训练结果；根据选择的决策树输出所有特征标签在所述显著特征分析模型中的重要性排序(若一个特征标签和是否患病无关，则不纳入决策树模型中)。
步骤S6，对各种特征标签按照在所述显著特征分析模型中的重要性排序顺序，进行预设类型分析，分析出对鼻咽癌有显著影响的显著特征标签。
所述预设类型分析，例如为BI(Business Intelligence，商业智能)分析，通过BI分析可以验证每种特征标签的不同取值对鼻咽癌的患病率是否有显著性的差别，若一种特征标签的不同取值对鼻咽癌的患病率有显著性的差别，则确定该种特征标签即为显著特征标签。
本申请鼻咽癌风险预警方法中预设的特征标签提取规则为：对于连续数值的各种特征数据种类设置对应的标签阈值；
例如，所属城市PM2.5(细颗粒物)最近三年每年超标的天数对应的标签阈值可以为60天，当所属城市PM2.5最近三年每年超标的天数大于对应的标签阈值“60天”时，代表所属城市PM2.5经常超标；所属城市最近三年每年蓝色以上预警等级的天数对应的标签阈值可以为55天，当所属城市最近三年每年蓝色以上预警等级的天数大于对应的标签阈值“55天”时，代表所属城市恶劣天气偏多；最近一年晚于23:00睡觉的天数对应的标签阈值可以是100天，当最近一年晚于23:00睡觉的天数大于对应的标签阈值“100天”时，代表偏好晚睡；最近一年点烧烤类的外卖次数对应的标签阈值可以是80次，当最近一年点烧烤类的外卖次数大于对应的标签阈值“80次”时，代表偏好烧烤食物；最近一年就医次数对应的标签阈值可以是30次，当最近一年就医次数大于对应的标签阈值“30次”时，代表就医次数多。
对于非为连续数值的各种特征数据种类设置对应的标签范围；
例如，所属城市对应的标签范围包括：西北地区城市集合、华北地区城市集合、华中地区城市集合、华南地区城市集合等等，当客户所属城市属于所述西北地区城市集合中的城市时，代表该客户所属城市对应的标签信息是“属于中国西北地区”；所属城市饮食习惯对应的标签范围包括：偏辛辣城市集合、偏油腻城市集合、偏清淡城市集合、偏甜/咸城市结合等，当客户所属城市属于所述偏辛辣城市集合中的城市时，代表该客户所属城市对应的标签信息是“饮食习惯偏辛辣”；从事岗位对应的标签范围包括：有害气体岗位集合、非易产生挥发性有害气体的岗位集合、易产生挥发性有害气体的岗位集合、无害气体岗位集合等，当客户从事岗位属于有害气体岗位集合中的岗位，代表该客户所从事行业对应的标签信息是“从事有害气体岗位”。
根据连续数值的各种特征数据种类与标签阈值的映射关系，确定出各个客户的各种连续数值的特征数据对应的标签信息，及根据非连续数值的各种特征数据种类与标签范围的映射关系，确定出各个客户的各种非连续数值的特征数据对应的标签信息。
此外，本申请还提出一种鼻咽癌风险预警系统。
请参阅图4，是本申请鼻咽癌风险预警系统10一实施例的运行环境示意图。
在本实施例中，鼻咽癌风险预警系统10安装并运行于电子装置1中。电子装置1可以是桌上型计算机、笔记本、掌上电脑及服务器等计算设备。该电子装置1可包括，但不仅限于，存储器11、处理器12及显示器13。图4仅示出了具有组件11-13的电子装置1，但是应理解的是，并不要求实施所有示出的组件，可以替代的实施更多或者更少的组件。
存储器11在一些实施例中可以是电子装置1的内部存储单元，例如该电子装置1的硬盘或内存。存储器11在另一些实施例中也可以是电子装置1的外部存储设备，例如电子装置1上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。进一步地，存储器11还可以既包括电子装置1的内部存储单元也包括外部存储设备。存储器11用于存储安装于电子装置1的应用软件及各类数据，例如鼻咽癌风险预警系统10的程序代码等。存储器11还可以用于暂时地存储已经输出或者将要输出的数据。
处理器12在一些实施例中可以是一中央处理器(Central Processing Unit,CPU)，微处理器或其他数据处理芯片，用于运行存储器11中存储的程序代码或处理数据，例如执行鼻咽癌风险预警系统10等。
显示器13在一些实施例中可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(Organic Light-Emitting Diode，有机发光二极管)触摸器等。显示器13用于显示在电子装置1中处理的信息以及用于显示可视化的用户界面。电子装置1的部件11-13通过系统总线相互通信。
请参阅图5，是本申请鼻咽癌风险预警系统10较佳实施例的程序模块图。在本实施例中，鼻咽癌风险预警系统10可以被分割成一个或多个模块，一个或者多个模块被存储于存储器11中，并由一个或多个处理器(本实施例为处理器12)所执行，以完成本申请。例如，在图5中，鼻咽癌风险预警系统10可以被分割成第一获取模块101、第二获取模块102、提取模块103、第一分析模块104、第二分析模块105及预警输出模块106。本申请所称的模块是指能够完成特定功能的一系列计算机程序指令段，比程序更适合于描述鼻咽癌风险预警系统10在电子装置1中的执行过程，其中：
第一获取模块101，用于在收到一个待筛查客户的鼻咽癌筛查请求后，从所述鼻咽癌筛查请求中获取该待筛查客户的特征标签；
鼻咽癌筛查请求中包含待筛查客户的客户属性数据(例如，证件号码，或者，姓名和证件号码)及/或待筛查客户的特征标签；其中，特征标签包括基本特征信息(例如，所属城市属于中国西北地区、所属城市饮食习惯偏辛辣、所属城市PM2.5(细颗粒物)经常超标、所属城市恶劣天气偏多、从事有害气体岗位等)、偏好习惯信息(例如，偏好晚睡、偏好烟酒、偏好烧烤食物、偏好户外运动等)、行为信息(例如，游戏次数多、加班次数多、点外卖 的次数多、就医次数多等)及/或社会关系信息(例如，未婚、独居、不经常与朋友联系等)。筛查服务器在收到一个待筛查客户的鼻咽癌筛查请求后，先看该请求中是否包含了该客户的特征标签，即从中去获取该客户的特征标签。
第二获取模块102，用于在从所述鼻咽癌筛查请求中获取特征标签失败后，从所述鼻咽癌筛查请求中获取该待筛查客户的客户属性数据；
如果该鼻咽癌筛查请求中没有包含该客户的特征标签，则从该鼻咽癌筛查请求中获取不到特征标签(即获取特征标签失败)，那么，则从该鼻咽癌筛查请求中获取该待筛查客户的客户属性数据，以根据该带筛查客户的客户属性数据去获得该待筛查客户的特征标签。
提取模块103，用于从多个预先确定的业务服务器提取出与该待筛查客户的客户属性数据对应的各种特征数据；
筛查服务器与多个预先确定的业务服务器(例如，银行服务器、医疗服务器、保险服务器、即时通讯服务器、游戏服务器、天气服务器、外卖服务器及/或简历服务器等)之间通讯；在获取到该待筛查客户的客户属性数据后，筛查服务器从多个预先确定的业务服务器提取出与该待筛查客户的客户属性数据对应的各种特征数据(例如，银行贷款额度及还款情况信息、门诊病历信息“例如，预设时间内的看病次数、所患的疾病种类、每次患病的持续时间等”、保险信息“例如，所处行业，性别、年龄、婚姻状况、职业等”、即时通讯工具账号的使用信息“例如，通讯工具每天登陆时间信息、每天在线时长等信息”等等、游戏信息“例如，每天游戏登陆时间信息、每天游戏在线时长等信息”、天气信息“例如，最近三年内，PM2.5(细颗粒物)严重超标的天数”、外卖点餐信息“例如，每天点外卖的时间信息、每天所点外卖的外卖类型等”、求职简历上填写的信息“例如，兴趣爱好、性格、工作经历等信息”)。
第一分析模块104，用于按照预设的特征标签提取规则，对提取出的各种特征数据进行特征标签分析，以分析出该待筛查客户的特征标签；
筛查服务器中预先设置了特征标签的提取规则，在提取出该待筛查客户对应的各种特征数据后，利用该提取规则，对提取出的各种特征数据进行特征标签分析，从而分析得到该待筛查客户的特征标签。
第二分析模块105，用于对该待筛查客户的特征标签中的预先确定的显著特征标签进行数量分析，确定出该待筛查客户的鼻咽癌风险等级；
筛查服务器中预先确定了哪些特征标签为显著特征标签(即对患鼻咽癌有显著影响的特征标签)，预先确定的显著特征标签为对鼻咽癌有显著影响的特征标签；在得到该待筛查客户的特征标签后，对其中包含的预先确定的显著特征标签进行数量分析，根据数量分析，确定出该待筛查客户的鼻咽癌风险等级(例如，鼻咽癌风险等级包括低风险等级、中风险等级和高风险等级)，鼻咽癌风险等级越高，表示该待筛查客户可能会患鼻咽癌的几率越大。
预警输出模块106，用于输出与确定的鼻咽癌风险等级对应的预警信息。
筛查服务器根据所确定的鼻咽癌风险等级，输出相对应的预设预警信息 (即一些注意事项和健康建议等)。例如，低风险等级对应的预警信息可以为“******客户，不带有鼻咽癌显著特征标签，建议每年进行一次鼻咽癌风险筛查，多做室内有氧运动，少参加室外剧烈运动，早睡早起”；与中风险等级对应的预警信息可以为“******客户，带有鼻咽癌显著特征标签，建议做进一步的医学检查，多做室内有氧运动，少参加室外剧烈运动，早睡早起”；与高风险等级对应的预警信息可以为“******客户，您属于鼻咽癌的高危对象，务必于7天内做进一步的医学检查”；等等。
本实施例技术方案，在接收到待筛查客户的鼻咽癌筛查请求后，根据该鼻咽癌筛查请求去获取该待筛查客户的特征标签，具体为先直接从鼻咽癌筛查请求中获取该待筛查客户的特征标签，在获取失败时，则根据该鼻咽癌筛查请求中的客户属性信息，去从各个预先确定的业务服务器中获取该客户属性信息对应的各种特征数据，再按照预设的提取规则从这些特征数据中提取出该待筛查客户的特征标签；再对该特征标签中包含的预先确定的显著特征标签(对患鼻咽癌有显著影响的特征标签)的数量进行分析，从而得出该待筛查客户的鼻咽癌风险等级，输出与该得出的鼻咽癌风险等级对应的预警信息给客户。本实施例先采用根据待筛查客户的大量特征数据得出其特征标签，再根据特征标签中的包含的对患鼻咽癌影响大的特征标签的数量确定客户的鼻咽癌风险等级，并给予客户对应的预警信息，让客户可以及早的进行预防或治疗，从而有效的改善鼻咽癌的患病情况。
如图6所示，图6为本申请鼻咽癌风险预警系统二实施例的程序模块图。
本实施例中，所述鼻咽癌风险等级包括低风险等级、中风险等级和高风险等级，所述第二分析模块105包括：
第一分析子模块1051，用于分析该待筛查客户的特征标签中是否有预先确定的显著特征标签；
筛查服务器首先根据预先确定的所有显著特征标签判断该待筛查客户的特征标签中有没有含有预先确定的显著特征标签。
确定子模块1052，用于在该待筛查客户的特征标签中没有预先确定的显著特征标签时，确定该待筛查客户的鼻咽癌风险等级为低风险等级；
如果该待筛查客户的所有特征标签中没有包含任何一个预先确定的显著特征标签，则判定该待筛查客户的鼻咽癌风险等级为低风险等级。
第二分析子模块1053，用于在该待筛查客户的特征标签中有预先确定的显著特征标签时，分析含有的预先确定的显著特征标签的数量是否大于预设数量，或者，分析含有的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总数量的百分比是否大于预设百分比；
若判定得该待筛查客户的特征标签中含有预先确定的显著特征标签，则进一步根据该待筛查客户的特征标签中包含的预先确定的显著特征标签的数量判断其鼻咽癌风险等级；具体为，将该待筛查客户的特征标签中包含的预先确定的显著特征标签的数量与预设数量比较，或者，将该待筛查客户的特 征标签中包含的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的数量的百分比，与预设百分比(例如，80％)进行比较。
所述确定子模块1052还用于在含有的预先确定的显著特征标签的数量大于预设数量时，或者，含有的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总数量的百分比大于预设百分比时，确定该待筛查客户的鼻咽癌风险等级为高风险等级；
所述确定子模块1052还用于在含有的预先确定的显著特征标签的数量小于或者等于预设数量时，或者，含有的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总数量的百分比小于或者等于预设百分比时，确定该待筛查客户的鼻咽癌风险等级为中风险等级。
本实施例中，所述预先确定的显著特征标签的确定方案包括以下步骤：
1、选取第一预设数量的客户，并获取选取的各个客户的客户属性数据；
筛查服务器从客户数据库中选取第一预设数量(例如10000个)的客户(选取的客户都是已经确定是否患鼻咽癌的客户)，并获取这些客户的客户属性信息(例如，证件号码，或者，姓名和证件号码)。
2、从多个预先确定的业务服务器分别提取出与各个客户的客户属性数据对应的各种特征数据；
针对这第一预设数量的客户中的每一个客户，筛查服务器从多个预先确定的业务服务器中的每一个服务器分别提取该客户对应的特征数据，以提取出每一个客户在各个预先确定的业务服务器中的特征数据。该特征数据即客户在业务服务器中的历史行为数据(例如，银行贷款额度及还款情况信息、门诊病历信息“例如，预设时间内的看病次数、所患的疾病种类、每次患病的持续时间等”、保险信息“例如，所处行业，性别、年龄、婚姻状况、职业等”、即时通讯工具账号的使用信息“例如，通讯工具每天登陆时间信息、每天在线时长等信息”等等、游戏信息“例如，每天游戏登陆时间信息、每天游戏在线时长等信息”、天气信息“例如，最近三年内，PM2.5(细颗粒物)严重超标的天数”、外卖点餐信息“例如，每天点外卖的时间信息、每天所点外卖的外卖类型等”、求职简历上填写的信息“例如，兴趣爱好、性格、工作经历等信息”)。
3、按照预设的特征标签提取规则，对提取出的各种特征数据进行特征标签分析，以分析出各个客户的特征标签；
在提取得到各个客户的各种特征数据后，筛查服务器按照预设的提取规则，对每个客户的各种特征数据分别进行特征标签分析，从而得出每个客户的特征标签。特征标签包括基本特征信息(例如，所属城市属于中国西北地区、所属城市饮食习惯偏辛辣、所属城市PM2.5(细颗粒物)经常超标、所属城市恶劣天气偏多、从事有害气体岗位等)、偏好习惯信息(例如，偏好晚睡、偏好烟酒、偏好烧烤食物、偏好户外运动等)、行为信息(例如，游戏次数多、加班次数多、点外卖的次数多、就医次数多等)及/或社会关系信息(例 如，未婚、独居、不经常与朋友联系等)。
4、根据预先确定的鼻咽癌与客户属性数据的映射关系，确定所述第一预设数量的客户中患有鼻咽癌的异常客户和未患鼻咽癌的正常客户；
客户数据库中记录了每个客户的患病标签，筛查服务器根据客户的客户属性数据通过查找数据库就可确定该第一预设数量的客户中，哪些为患有鼻咽癌的异常客户，哪些为未患鼻咽癌的正常客户。
5、将各个正常客户对应的特征标签和各个异常客户对应的特征标签作为预设的显著特征分析模型的训练样本，利用各个所述训练样本训练所述显著特征分析模型，以确定出各种特征标签在所述显著特征分析模型中的重要性排序；
也就是，每一个正常客户对应的所有特征标签作为一个训练样本，每一个异常客户对应的所有特征标签作为一个训练样本，正常客户对应的特征标签是对应不患鼻咽癌的，异常客户的特征标签是对应患鼻咽癌的，这样总共有第一预设数量的训练样本去训练预设的显著特征分析模型，通过训练得到各个特征标签在该显著特征分析模型中的重要性排序。优选地，本实施例中采用的所述显著特征分析模型为梯度提升决策树模型，所述显著特征分析模型的训练步骤包括：利用各个所述训练样本训练所述显著特征分析模型，构建多棵迭代决策树，选择精确率最高的前N棵决策树作为模型的最终训练结果；根据选择的决策树输出所有特征标签在所述显著特征分析模型中的重要性排序(若一个特征标签和是否患病无关，则不纳入决策树模型中)。
6、对各种特征标签按照在所述显著特征分析模型中的重要性排序顺序，进行预设类型分析，分析出对鼻咽癌有显著影响的显著特征标签。
所述预设类型分析，例如为BI(Business Intelligence，商业智能)分析，通过BI分析可以验证每种特征标签的不同取值对鼻咽癌的患病率是否有显著性的差别，若一种特征标签的不同取值对鼻咽癌的患病率有显著性的差别，则确定该种特征标签即为显著特征标签。
本申请鼻咽癌风险预警系统中，预设的特征标签提取规则为：对于连续数值的各种特征数据种类设置对应的标签阈值；
例如，所属城市PM2.5(细颗粒物)最近三年每年超标的天数对应的标签阈值可以为60天，当所属城市PM2.5最近三年每年超标的天数大于对应的标签阈值“60天”时，代表所属城市PM2.5经常超标；所属城市最近三年每年蓝色以上预警等级的天数对应的标签阈值可以为55天，当所属城市最近三年每年蓝色以上预警等级的天数大于对应的标签阈值“55天”时，代表所属城市恶劣天气偏多；最近一年晚于23:00睡觉的天数对应的标签阈值可以是100天，当最近一年晚于23:00睡觉的天数大于对应的标签阈值“100天”时，代表偏好晚睡；最近一年点烧烤类的外卖次数对应的标签阈值可以是80次，当最近一年点烧烤类的外卖次数大于对应的标签阈值“80次”时，代表偏好烧烤食物；最近一年就医次数对应的标签阈值可以是30次，当最近一年就医 次数大于对应的标签阈值“30次”时，代表就医次数多。
对于非为连续数值的各种特征数据种类设置对应的标签范围；
例如，所属城市对应的标签范围包括：西北地区城市集合、华北地区城市集合、华中地区城市集合、华南地区城市集合等等，当客户所属城市属于所述西北地区城市集合中的城市时，代表该客户所属城市对应的标签信息是“属于中国西北地区”；所属城市饮食习惯对应的标签范围包括：偏辛辣城市集合、偏油腻城市集合、偏清淡城市集合、偏甜/咸城市结合等，当客户所属城市属于所述偏辛辣城市集合中的城市时，代表该客户所属城市对应的标签信息是“饮食习惯偏辛辣”；从事岗位对应的标签范围包括：有害气体岗位集合、非易产生挥发性有害气体的岗位集合、易产生挥发性有害气体的岗位集合、无害气体岗位集合等，当客户从事岗位属于有害气体岗位集合中的岗位，代表该客户所从事行业对应的标签信息是“从事有害气体岗位”。
根据连续数值的各种特征数据种类与标签阈值的映射关系，确定出各个客户的各种连续数值的特征数据对应的标签信息，及根据非连续数值的各种特征数据种类与标签范围的映射关系，确定出各个客户的各种非连续数值的特征数据对应的标签信息。
进一步地，本申请还提出一种计算机可读存储介质，所述计算机可读存储介质存储有鼻咽癌风险预警系统，所述鼻咽癌风险预警系统可被至少一个处理器执行，以使所述至少一个处理器执行上述任一实施例中的鼻咽癌风险预警方法。
以上所述仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是在本申请的发明构思下，利用本申请说明书及附图内容所作的等效结构变换，或直接/间接运用在其他相关的技术领域均包括在本申请的专利保护范围内。

Claims (20)

  1. 一种电子装置，其特征在于，所述电子装置包括存储器和处理器，所述存储器上存储有可在所述处理器上运行的鼻咽癌风险预警系统，所述鼻咽癌风险预警系统被所述处理器执行时实现如下步骤：
    在收到一个待筛查客户的鼻咽癌筛查请求后，从所述鼻咽癌筛查请求中获取该待筛查客户的特征标签；
    若从所述鼻咽癌筛查请求中获取特征标签失败，则从所述鼻咽癌筛查请求中获取该待筛查客户的客户属性数据；
    从多个预先确定的业务服务器提取出与该待筛查客户的客户属性数据对应的各种特征数据；
    按照预设的特征标签提取规则，对提取出的各种特征数据进行特征标签分析，以分析出该待筛查客户的特征标签；
    对该待筛查客户的特征标签中的预先确定的显著特征标签进行数量分析，确定出该待筛查客户的鼻咽癌风险等级；
    输出与确定的鼻咽癌风险等级对应的预警信息。
  2. 如权利要求1所述的电子装置，其特征在于，所述预设的特征标签提取规则为：
    对于连续数值的各种特征数据种类设置对应的标签阈值；
    对于非为连续数值的各种特征数据种类设置对应的标签范围；
    根据连续数值的各种特征数据种类与标签阈值的映射关系，确定出各个客户的各种连续数值的特征数据对应的标签信息，及根据非连续数值的各种特征数据种类与标签范围的映射关系，确定出各个客户的各种非连续数值的特征数据对应的标签信息。
  3. 如权利要求1所述的电子装置，其特征在于，所述鼻咽癌风险等级包括低风险等级、中风险等级和高风险等级，所述对该待筛查客户的特征标签中的预先确定的显著特征标签进行数量分析，确定出该待筛查客户的鼻咽癌风险等级的步骤包括：
    分析该待筛查客户的特征标签中是否有预先确定的显著特征标签；
    若无预先确定的显著特征标签，则确定该待筛查客户的鼻咽癌风险等级为低风险等级；
    若有预先确定的显著特征标签，则分析含有的预先确定的显著特征标签的数量是否大于预设数量，或者，分析含有的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总数量的百分比是否大于预设百分比；
    若含有的预先确定的显著特征标签的数量大于预设数量，或者，含有的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总数量的百分比大于预设百分比，则确定该待筛查客户的鼻咽癌风险等级为高风险等级；
    若含有的预先确定的显著特征标签的数量小于或者等于预设数量，或者，含有的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总 数量的百分比小于或者等于预设百分比，则确定该待筛查客户的鼻咽癌风险等级为中风险等级。
  4. 如权利要求3所述的电子装置，其特征在于，所述预设的特征标签提取规则为：
    对于连续数值的各种特征数据种类设置对应的标签阈值；
    对于非为连续数值的各种特征数据种类设置对应的标签范围；
    根据连续数值的各种特征数据种类与标签阈值的映射关系，确定出各个客户的各种连续数值的特征数据对应的标签信息，及根据非连续数值的各种特征数据种类与标签范围的映射关系，确定出各个客户的各种非连续数值的特征数据对应的标签信息。
  5. 如权利要求1所述的电子装置，其特征在于，所述预先确定的显著特征标签的确定步骤包括：
    选取第一预设数量的客户，并获取选取的各个客户的客户属性数据；
    从多个预先确定的业务服务器分别提取出与各个客户的客户属性数据对应的各种特征数据；
    按照预设的特征标签提取规则，对提取出的各种特征数据进行特征标签分析，以分析出各个客户的特征标签；
    根据预先确定的鼻咽癌与客户属性数据的映射关系，确定所述第一预设数量的客户中患有鼻咽癌的异常客户和未患鼻咽癌的正常客户；
    将各个正常客户对应的特征标签和各个异常客户对应的特征标签作为预设的显著特征分析模型的训练样本，利用各个所述训练样本训练所述显著特征分析模型，以确定出各种特征标签在所述显著特征分析模型中的重要性排序；
    对各种特征标签按照在所述显著特征分析模型中的重要性排序顺序，进行预设类型分析，分析出对鼻咽癌有显著影响的显著特征标签。
  6. 如权利要求5所述的电子装置，其特征在于，所述预设的特征标签提取规则为：
    对于连续数值的各种特征数据种类设置对应的标签阈值；
    对于非为连续数值的各种特征数据种类设置对应的标签范围；
    根据连续数值的各种特征数据种类与标签阈值的映射关系，确定出各个客户的各种连续数值的特征数据对应的标签信息，及根据非连续数值的各种特征数据种类与标签范围的映射关系，确定出各个客户的各种非连续数值的特征数据对应的标签信息。
  7. 如权利要求5所述的电子装置，其特征在于，所述显著特征分析模型为梯度提升决策树模型，所述显著特征分析模型的训练步骤包括：
    利用各个所述训练样本训练所述显著特征分析模型，构建多棵迭代决策树，选择精确率最高的前N棵决策树作为模型的最终训练结果；
    根据选择的决策树输出所有特征标签在所述显著特征分析模型中的重要性排序。
  8. 如权利要求7所述的电子装置，其特征在于，所述预设的特征标签提取规则为：
    对于连续数值的各种特征数据种类设置对应的标签阈值；
    对于非为连续数值的各种特征数据种类设置对应的标签范围；
    根据连续数值的各种特征数据种类与标签阈值的映射关系，确定出各个客户的各种连续数值的特征数据对应的标签信息，及根据非连续数值的各种特征数据种类与标签范围的映射关系，确定出各个客户的各种非连续数值的特征数据对应的标签信息。
  9. 一种鼻咽癌风险预警方法，其特征在于，该方法包括步骤：
    在收到一个待筛查客户的鼻咽癌筛查请求后，从所述鼻咽癌筛查请求中获取该待筛查客户的特征标签；
    若从所述鼻咽癌筛查请求中获取特征标签失败，则从所述鼻咽癌筛查请求中获取该待筛查客户的客户属性数据；
    从多个预先确定的业务服务器提取出与该待筛查客户的客户属性数据对应的各种特征数据；
    按照预设的特征标签提取规则，对提取出的各种特征数据进行特征标签分析，以分析出该待筛查客户的特征标签；
    对该待筛查客户的特征标签中的预先确定的显著特征标签进行数量分析，确定出该待筛查客户的鼻咽癌风险等级；
    输出与确定的鼻咽癌风险等级对应的预警信息。
  10. 如权利要求9所述的鼻咽癌风险预警方法，其特征在于，所述预设的特征标签提取规则为：
    对于连续数值的各种特征数据种类设置对应的标签阈值；
    对于非为连续数值的各种特征数据种类设置对应的标签范围；
    根据连续数值的各种特征数据种类与标签阈值的映射关系，确定出各个客户的各种连续数值的特征数据对应的标签信息，及根据非连续数值的各种特征数据种类与标签范围的映射关系，确定出各个客户的各种非连续数值的特征数据对应的标签信息。
  11. 如权利要求9所述的鼻咽癌风险预警方法，其特征在于，所述鼻咽癌风险等级包括低风险等级、中风险等级和高风险等级，所述对该待筛查客户的特征标签中的预先确定的显著特征标签进行数量分析，确定出该待筛查客户的鼻咽癌风险等级的步骤包括：
    分析该待筛查客户的特征标签中是否有预先确定的显著特征标签；
    若无预先确定的显著特征标签，则确定该待筛查客户的鼻咽癌风险等级为低风险等级；
    若有预先确定的显著特征标签，则分析含有的预先确定的显著特征标签的数量是否大于预设数量，或者，分析含有的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总数量的百分比是否大于预设百分比；
    若含有的预先确定的显著特征标签的数量大于预设数量，或者，含有的 预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总数量的百分比大于预设百分比，则确定该待筛查客户的鼻咽癌风险等级为高风险等级；
    若含有的预先确定的显著特征标签的数量小于或者等于预设数量，或者，含有的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总数量的百分比小于或者等于预设百分比，则确定该待筛查客户的鼻咽癌风险等级为中风险等级。
  12. 如权利要求11所述的鼻咽癌风险预警方法，其特征在于，所述预设的特征标签提取规则为：
    对于连续数值的各种特征数据种类设置对应的标签阈值；
    对于非为连续数值的各种特征数据种类设置对应的标签范围；
    根据连续数值的各种特征数据种类与标签阈值的映射关系，确定出各个客户的各种连续数值的特征数据对应的标签信息，及根据非连续数值的各种特征数据种类与标签范围的映射关系，确定出各个客户的各种非连续数值的特征数据对应的标签信息。
  13. 如权利要求9所述的鼻咽癌风险预警方法，其特征在于，所述预先确定的显著特征标签的确定步骤包括：
    选取第一预设数量的客户，并获取选取的各个客户的客户属性数据；
    从多个预先确定的业务服务器分别提取出与各个客户的客户属性数据对应的各种特征数据；
    按照预设的特征标签提取规则，对提取出的各种特征数据进行特征标签分析，以分析出各个客户的特征标签；
    根据预先确定的鼻咽癌与客户属性数据的映射关系，确定所述第一预设数量的客户中患有鼻咽癌的异常客户和未患鼻咽癌的正常客户；
    将各个正常客户对应的特征标签和各个异常客户对应的特征标签作为预设的显著特征分析模型的训练样本，利用各个所述训练样本训练所述显著特征分析模型，以确定出各种特征标签在所述显著特征分析模型中的重要性排序；
    对各种特征标签按照在所述显著特征分析模型中的重要性排序顺序，进行预设类型分析，分析出对鼻咽癌有显著影响的显著特征标签。
  14. 如权利要求13所述的鼻咽癌风险预警方法，其特征在于，所述预设的特征标签提取规则为：
    对于连续数值的各种特征数据种类设置对应的标签阈值；
    对于非为连续数值的各种特征数据种类设置对应的标签范围；
    根据连续数值的各种特征数据种类与标签阈值的映射关系，确定出各个客户的各种连续数值的特征数据对应的标签信息，及根据非连续数值的各种特征数据种类与标签范围的映射关系，确定出各个客户的各种非连续数值的特征数据对应的标签信息。
  15. 如权利要求13所述的鼻咽癌风险预警方法，其特征在于，所述显著 特征分析模型为梯度提升决策树模型，所述显著特征分析模型的训练步骤包括：
    利用各个所述训练样本训练所述显著特征分析模型，构建多棵迭代决策树，选择精确率最高的前N棵决策树作为模型的最终训练结果；
    根据选择的决策树输出所有特征标签在所述显著特征分析模型中的重要性排序。
  16. 如权利要求15所述的鼻咽癌风险预警方法，其特征在于，所述预设的特征标签提取规则为：
    对于连续数值的各种特征数据种类设置对应的标签阈值；
    对于非为连续数值的各种特征数据种类设置对应的标签范围；
    根据连续数值的各种特征数据种类与标签阈值的映射关系，确定出各个客户的各种连续数值的特征数据对应的标签信息，及根据非连续数值的各种特征数据种类与标签范围的映射关系，确定出各个客户的各种非连续数值的特征数据对应的标签信息。
  17. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有鼻咽癌风险预警系统，所述鼻咽癌风险预警系统可被至少一个处理器执行，以使所述至少一个处理器执行如下步骤：
    在收到一个待筛查客户的鼻咽癌筛查请求后，从所述鼻咽癌筛查请求中获取该待筛查客户的特征标签；
    若从所述鼻咽癌筛查请求中获取特征标签失败，则从所述鼻咽癌筛查请求中获取该待筛查客户的客户属性数据；
    从多个预先确定的业务服务器提取出与该待筛查客户的客户属性数据对应的各种特征数据；
    按照预设的特征标签提取规则，对提取出的各种特征数据进行特征标签分析，以分析出该待筛查客户的特征标签；
    对该待筛查客户的特征标签中的预先确定的显著特征标签进行数量分析，确定出该待筛查客户的鼻咽癌风险等级；
    输出与确定的鼻咽癌风险等级对应的预警信息。
  18. 如权利要求17所述的计算机可读存储介质，其特征在于，所述鼻咽癌风险等级包括低风险等级、中风险等级和高风险等级，所述对该待筛查客户的特征标签中的预先确定的显著特征标签进行数量分析，确定出该待筛查客户的鼻咽癌风险等级的步骤包括：
    分析该待筛查客户的特征标签中是否有预先确定的显著特征标签；
    若无预先确定的显著特征标签，则确定该待筛查客户的鼻咽癌风险等级为低风险等级；
    若有预先确定的显著特征标签，则分析含有的预先确定的显著特征标签的数量是否大于预设数量，或者，分析含有的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总数量的百分比是否大于预设百分比；
    若含有的预先确定的显著特征标签的数量大于预设数量，或者，含有的 预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总数量的百分比大于预设百分比，则确定该待筛查客户的鼻咽癌风险等级为高风险等级；
    若含有的预先确定的显著特征标签的数量小于或者等于预设数量，或者，含有的预先确定的显著特征标签的数量占所有预先确定的显著特征标签的总数量的百分比小于或者等于预设百分比，则确定该待筛查客户的鼻咽癌风险等级为中风险等级。
  19. 如权利要求17所述的计算机可读存储介质，其特征在于，所述预先确定的显著特征标签的确定步骤包括：
    选取第一预设数量的客户，并获取选取的各个客户的客户属性数据；
    从多个预先确定的业务服务器分别提取出与各个客户的客户属性数据对应的各种特征数据；
    按照预设的特征标签提取规则，对提取出的各种特征数据进行特征标签分析，以分析出各个客户的特征标签；
    根据预先确定的鼻咽癌与客户属性数据的映射关系，确定所述第一预设数量的客户中患有鼻咽癌的异常客户和未患鼻咽癌的正常客户；
    将各个正常客户对应的特征标签和各个异常客户对应的特征标签作为预设的显著特征分析模型的训练样本，利用各个所述训练样本训练所述显著特征分析模型，以确定出各种特征标签在所述显著特征分析模型中的重要性排序；
    对各种特征标签按照在所述显著特征分析模型中的重要性排序顺序，进行预设类型分析，分析出对鼻咽癌有显著影响的显著特征标签。
  20. 如权利要求17所述的计算机可读存储介质，其特征在于，所述预设的特征标签提取规则为：
    对于连续数值的各种特征数据种类设置对应的标签阈值；
    对于非为连续数值的各种特征数据种类设置对应的标签范围；
    根据连续数值的各种特征数据种类与标签阈值的映射关系，确定出各个客户的各种连续数值的特征数据对应的标签信息，及根据非连续数值的各种特征数据种类与标签范围的映射关系，确定出各个客户的各种非连续数值的特征数据对应的标签信息。
PCT/CN2018/102107 2018-04-09 2018-08-24 电子装置、鼻咽癌风险预警方法和计算机可读存储介质 Ceased WO2019196299A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810311645.5 2018-04-09
CN201810311645.5A CN108831553A (zh) 2018-04-09 2018-04-09 电子装置、鼻咽癌风险预警方法和计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2019196299A1 true WO2019196299A1 (zh) 2019-10-17

Family

ID=64154418

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/102107 Ceased WO2019196299A1 (zh) 2018-04-09 2018-08-24 电子装置、鼻咽癌风险预警方法和计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN108831553A (zh)
WO (1) WO2019196299A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009156936A2 (en) * 2008-06-27 2009-12-30 Koninklijke Philips Electronics N.V. System and method for determining a personal health related risk
CN102930163A (zh) * 2012-11-01 2013-02-13 北京理工大学 一种2型糖尿病风险状态判定方法
CN105574337A (zh) * 2015-12-16 2016-05-11 上海亿保健康管理有限公司 一种健康评估装置
CN106066938A (zh) * 2016-06-03 2016-11-02 贡京京 一种疾病预防和健康管理方法及系统
CN107301326A (zh) * 2017-08-29 2017-10-27 北斗云谷（北京）科技有限公司 基于常规因子的个性化疾病风险等级分析方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105744005A (zh) * 2016-04-30 2016-07-06 平安证券有限责任公司 客户定位分析方法及服务器
CN107247887A (zh) * 2017-07-27 2017-10-13 点内（上海）生物科技有限公司 基于人工智能帮助肺癌筛查的方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009156936A2 (en) * 2008-06-27 2009-12-30 Koninklijke Philips Electronics N.V. System and method for determining a personal health related risk
CN102930163A (zh) * 2012-11-01 2013-02-13 北京理工大学 一种2型糖尿病风险状态判定方法
CN105574337A (zh) * 2015-12-16 2016-05-11 上海亿保健康管理有限公司 一种健康评估装置
CN106066938A (zh) * 2016-06-03 2016-11-02 贡京京 一种疾病预防和健康管理方法及系统
CN107301326A (zh) * 2017-08-29 2017-10-27 北斗云谷（北京）科技有限公司 基于常规因子的个性化疾病风险等级分析方法

Also Published As

Publication number Publication date
CN108831553A (zh) 2018-11-16

Similar Documents

Publication Publication Date Title
Carter et al. Correcting for bias in psychology: A comparison of meta-analytic methods
JP6181360B2 (ja) マーケティング装置、マーケティング方法、プログラム、及び記録媒体
CN108876636B (zh) 理赔智能风控方法、系统、计算机设备及存储介质
WO2019169756A1 (zh) 产品推荐方法、装置及存储介质
US20140006044A1 (en) System and method for preparing healthcare service bundles
WO2019071906A1 (zh) 金融产品推荐装置、方法及计算机可读存储介质
JP6038727B2 (ja) 分析システム及び分析方法
Beatty et al. Is diet quality improving? Distributional changes in the United States, 1989–2008
Shah et al. Quality of chronic disease care for older people in care homes and the community in a primary care pay for performance system: retrospective study
Wunsch et al. Validation of intensive care and mechanical ventilation codes in Medicare data
US11366927B1 (en) Computing system for de-identifying patient data
US20220215129A1 (en) Information processing apparatus, information processing method and program
Soljak et al. Does higher quality primary health care reduce stroke admissions? A national cross-sectional study
WO2021151273A1 (zh) 疾病预测方法、装置、电子设备及存储介质
CN114756669A (zh) 问题意图的智能分析方法、装置、电子设备及存储介质
US10867249B1 (en) Method for deriving variable importance on case level for predictive modeling techniques
Weeda et al. Rates of major bleeding with rivaroxaban in real-world studies of nonvalvular atrial fibrillation patients: a meta-analysis
WO2019196502A1 (zh) 营销活动质量评估方法、服务器及计算机可读存储介质
WO2019062186A1 (zh) 糖尿病分析方法、应用服务器和计算机可读存储介质
JP7121276B2 (ja) データ管理レベル判定プログラム、およびデータ管理レベル判定方法
CN111078883A (zh) 危险指数分析方法、装置、电子设备和存储介质
CN113312482B (zh) 问题分类方法、装置、电子设备及可读存储介质
WO2019196300A1 (zh) 电子装置、鼻咽癌筛查分析方法和计算机可读存储介质
WO2019196299A1 (zh) 电子装置、鼻咽癌风险预警方法和计算机可读存储介质
Reuben et al. A model for estimating the population size of disproportionate two sample capture recapture methods

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: 18914855

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 26/01/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18914855

Country of ref document: EP

Kind code of ref document: A1