Home user feature database construction method

Abstract

The invention relates to the technical field of family data analysis, in particular to a family user feature database construction method, which comprises the following steps: S1, collecting health information, behavior information and identity information of family users; s2, extracting the feature data, and analyzing daily features of the user; s3, collecting specific information of the home users according to role types in the identity information of the home users; s4, analyzing specific characteristics of the user according to the collected identity information and specific information of the home user; s5, storing the feature data and the specific features of the user, analyzing the family data features according to the stored feature data, and classifying the family data features to obtain family feature types; s6, analyzing the feature saliency of the home users; and S7, constructing a home user feature database according to the feature saliency of the home users. According to the invention, accurate analysis of the home user features is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of family data analysis, and in particular to a method for constructing a family user feature database. Background Art

[0002] Family member feature analysis collects and stores specific data such as biology, health, and behavior of family members, and uses database technology and data analysis methods to achieve personalized management and services. With the development of the Internet of Things, artificial intelligence, and big data technologies, smart devices and biometrics technologies have facilitated data collection. By building a feature database, it can support applications such as health monitoring, security verification, and personalized recommendations. At the same time, attention should be paid to data privacy and security protection to ensure compliance with relevant laws and regulations.

[0003] Chinese patent publication number: CN112559586A discloses a method and system for obtaining characteristic data of family users, including the following steps: step S1: obtaining the identification of the terminal service before and after the network switching, the network includes a broadband network and a mobile network; step S2: judging whether the broadband network is a family broadband network; step S3: performing data characteristic analysis on the user corresponding to the family broadband network identification, judging whether the user is a family user member under the family broadband network identification; step S4: storing the ID of the family user member and its corresponding fixed network characteristic data and mobile network characteristic data under the family user member identification corresponding to the family broadband network identification, and establishing a data set of all members under the family broadband network tag. This invention realizes the division and identification of data of different members in the family according to network information, but does not realize the extraction of characteristic data according to the daily health data, behavior data and unique data of different roles of the family user, and constructing a family characteristic database according to the characteristic data, and there are problems of low efficiency in analyzing family user data and inaccurate analysis of family user characteristics. Summary of the invention

[0004] The object of the present invention is to provide a method for constructing a family user feature database to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, the present invention adopts the following technical solutions: A method for constructing a family user feature database, comprising: Step S1, collecting health information, behavior information and identity information of family users; Step S2, extracting characteristic data based on the collected health information, behavior information and identity information of the family user, and analyzing the daily characteristics of the family user based on the collected health information, behavior information and identity information of the family user; Step S3, collecting unique information of the family user according to the role type in the identity information of the family user; Step S4, analyzing the user's unique characteristics based on the collected identity information and unique information of the family user; Step S5, storing the characteristic data and the user-specific characteristics, analyzing the family data characteristics according to the stored characteristic data, and classifying the family data characteristics to obtain a family characteristic type; Step S6, analyzing the similarity of similar families according to the family data characteristics and the family characteristic type, and analyzing the characteristic prominence of family users according to the similarity of similar families, the daily characteristics of users and the unique characteristics of users; Step S7, constructing a family user feature database according to the feature significance of the family users.

[0006] Furthermore, the step S2 comprises: Step S21, numbering the family users to obtain a family user number and a family number; Step S22, extracting feature data based on health information, behavior information and identity information; Step S23, analyzing the user's daily characteristics based on health information, behavior information and identity information.

[0007] Furthermore, in step S21, the family users are numbered according to the identity information, each family user is numbered in descending order of age, the family user number is set as i, and different families are numbered, and the family number is set as j; In the step S22, the number of family users in the same family is counted as the family size, and the family size is set as NP(j); the number of food preferences in the same family is counted, and the food preference corresponding to the largest number of food preferences is used as the family food preference. If the food preferences of the users in the same family are different, the family food preference is set to no preference; the number of sports preference types in the same family is counted, and the sports preference type corresponding to the largest number of sports preference types is used as the family sports preference. If the sports preference types of the users in the same family are different, the family sports preference is set to no preference; the family meal time is set to be the same as the user's meal time; In step S23, the user's daily characteristics are analyzed according to the family user's height, weight, blood pressure, exercise time, sleep time, wake-up time and name to obtain the user's daily characteristics D(j,i).

[0008] Furthermore, in step S3, specific information of the family user is collected based on the identity information. If the role type is a child, the education information of the family user currently being analyzed is collected. If the role type is a father, the work information and living habit information of the family user currently being analyzed is collected. If the role type is a mother, the shopping information and parenting information of the family user currently being analyzed is collected. If the role type is an elderly person, the disease information and medication information of the family user currently being analyzed is collected.

[0009] Furthermore, in step S4, the user-specific features are analyzed according to the name, role type and specific information to obtain the user-specific features S(j,i).

[0010] Furthermore, the step S5 comprises: Step S51, storing feature data and user-specific features; Step S52, analyzing the family data characteristics according to the stored characteristic data; Step S53, counting the number of similar families according to family data characteristics; Step S54, classifying the family data features according to the number of similar families to obtain family feature types.

[0011] Furthermore, in the step S52, the family data feature is analyzed according to the stored feature data to obtain the family data feature F(j); In the step S53, the families corresponding to the non-currently analyzed family data features satisfying α≤F(j)·F(k)≤1 are extracted as similar families, and the number of similar families is counted as the number of similar families N(j), where F(k) represents the non-currently analyzed family data features, k represents the non-currently analyzed family number, and α represents the family extraction parameter; In the step S54, the family data features are classified according to the number of similar families to obtain family feature types, and the family feature types include one category and two categories.

[0012] Furthermore, the step S6 comprises: Step S61, analyzing feature prominence according to the user's daily features and the user's unique features; Step S62, analyzing the similarity of similar families according to family data characteristics; Step S63, improving the feature significance analysis process according to the similarity of similar families; Step S64, improving the similarity analysis process of similar families according to the family feature type.

[0013] Furthermore, in the step S61, the feature prominence is analyzed according to the user's daily feature D(j,i) and the user's unique feature S(j,i) to obtain the feature prominence G(j,i); In the step S62, the similarity of similar families is analyzed according to the similar families and the daily characteristics of the user D(j,i) to obtain the similarity of similar families W(j); In the step S63, the feature significance analysis process is improved according to the similarity W(j) of the similar families. When W(j)≤w, the feature significance analysis process is improved. The improved feature significance is G1(j,i), where w represents the similarity threshold. In the step S64, the analysis process of similarity of similar families is improved according to the family feature type. When the family feature type is one type, the analysis process of similarity of similar families is improved, and the improved similarity of similar families is W1(j).

[0014] Furthermore, in step S7, a family user feature database is constructed based on the feature significance, and the collected health information, behavior information and identity information of the family users are used as the basic data of the family user feature database, and the user's biometric characteristics are used as verification data for accessing the family user feature database. If G(j,i)>g, the collected unique information of the current family user is used as the feature data of the family user feature database; otherwise, the collected unique information of the current family user is used as the basic data of the family user feature database, wherein g represents the feature construction threshold.

[0015] The beneficial effects of the present invention are as follows: by collecting and analyzing the health information, behavior information and identity information of family users, as well as the unique data according to the role type of the family users, it is possible to determine whether each data has significant characteristics for each family user by combining the daily data characteristics of the users and the data characteristics of their unique data, and to analyze and extract the data reflecting the characteristics of the family users, so that the data in the constructed family user feature database can clearly reflect the user characteristics, and provide effective data for subsequent analysis of the family users, thereby improving the analysis efficiency of the family user data and improving the accuracy of the family user feature analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 This is a flow chart of the method for constructing a family user feature database in this embodiment.

[0018] Figure 2 Flow chart of the method for analyzing characteristic data and user daily characteristics in this embodiment.

[0019] Figure 3 This is a flow chart of the analysis of household data features in this embodiment.

[0020] Figure 4 Flow chart of feature significance analysis of this embodiment. DETAILED DESCRIPTION

[0021] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present invention.

[0022] It should be noted that, although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0023] See also Figure 1 As shown, the method for constructing a family user feature database in this embodiment includes: Step S1, collecting health information, behavior information and identity information of family users, wherein the health information includes but is not limited to data on the physiological state of family users, such as height, weight and blood pressure, wherein the height unit is meter, the weight unit is kilogram, the blood pressure unit is millimeter of mercury, and the blood pressure includes diastolic pressure and systolic pressure. The behavior information includes but is not limited to data on the daily habit preferences of family users, such as diet information, exercise information and work and rest information, wherein the diet information includes food preference and diet time, the exercise information includes exercise preference type, exercise time and exercise intensity, the exercise time unit is minute, the exercise preference type includes but is not limited to running and playing basketball and other sports, the exercise intensity includes low intensity, medium intensity and high intensity, and the work and rest information includes sleeping time and waking up time, the identity information includes but is not limited to name, age, role type and user biometrics and other data about the family user's identity, the role type includes but is not limited to father, mother, child and other data about the role information of the family user in the family, the user biometrics includes but is not limited to fingerprints, facial features and voiceprints and other biometrics for identifying the family user's identity. It should be noted that the family user information (including but not limited to family user device information, family user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the subject or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant national and regional laws, regulations and standards.

[0024] Specifically, in step S1 of this embodiment, by collecting the health information (such as height, weight, blood pressure, etc.), behavior information (such as diet, exercise, work and rest, etc.) and identity information (such as name, age, role type, etc.) of the family users, a comprehensive data foundation is provided for subsequent feature extraction and analysis. The diversity of these data ensures that the database can cover multiple dimensions of family users, thereby providing rich information support for subsequent personalized management and services.

[0025] Specifically, this embodiment is applied to the family data management server cloud, and through collecting data from different groups of people to extract characteristic data of users of each role type, comprehensive extraction of characteristic data of each member in the family is achieved.

[0026] Please continue reading Figure 1 As shown, the method for constructing a family user feature database further includes: Step S2, extracting characteristic data based on the collected health information, behavior information and identity information of the family users, and analyzing the daily characteristics of the family users based on the collected health information, behavior information and identity information of the family users.

[0027] Specifically, in step S2 of this embodiment, by extracting and analyzing health information, behavior information and identity information, the daily characteristics of the family user (such as exercise time, sleep time, dietary preferences, etc.) can be identified. These daily characteristics are the core of the family user's behavior pattern, which can help the database better reflect the user's daily habits and preferences, thereby improving the accuracy and practicality of the database.

[0028] See also Figure 2 As shown, it is an analysis method of feature data and user daily features, including: Step S21, numbering the family users to obtain a family user number and a family number.

[0029] Specifically, in step S21 of this embodiment, the family users are numbered according to their identity information, and each family user is numbered in descending order of age, and the family user number is set to i, i∈N + , and number different families, set the family number to j, j∈N + .

[0030] Please continue reading Figure 2 As shown, the method for analyzing the characteristic data and the daily characteristics of the user also includes: Step S22, extracting feature data based on health information, behavior information and identity information.

[0031] Specifically, in step S22 described in this embodiment, the number of family users in the same family is counted as the family size, and the family size is set as NP(j); the number of food preferences in the same family is counted, and the food preference corresponding to the largest number of food preferences is used as the family food preference; if the food preferences of the users in the same family are different, the family food preference is set to no preference; the number of sports preference types in the same family is counted, and the sports preference type corresponding to the largest number of sports preference types is used as the family sports preference; if the sports preference types of the users in the same family are different, the family sports preference is set to no preference; the family meal time is set to be the same as the user's meal time.

[0032] It is understandable that the present embodiment does not impose any specific limitation on the extraction of characteristic data. It is only necessary to extract data that can reflect family characteristics. For example, the extraction of data such as family consumption habits and the use of equipment in the family can also be set.

[0033] Please continue reading Figure 2 As shown, the method for analyzing the characteristic data and the daily characteristics of the user also includes: Step S23, analyzing the user's daily characteristics based on health information, behavior information and identity information.

[0034] Specifically, in step S23 of this embodiment, the daily characteristics of the user are analyzed according to the height, weight, blood pressure, exercise time, sleep time, wake-up time and name of the family user, and the daily characteristics of the user are set as D(j,i). , where M(j,i) represents weight, H(j,i) represents height, T1(j,i) represents exercise time, mh represents body mass parameter, 20≤mh≤22, BP1(j,i) represents systolic blood pressure, BP2(j,i) represents diastolic blood pressure, ST1(j,i) represents sleep time, and ST2(j,i) represents wake-up time. It can be understood that the value of body mass parameter is not specifically limited in this embodiment, and technicians in this field can freely set it as long as they meet the analysis of the user's daily characteristics. The optimal value of body mass parameter is: mh=21.

[0035] Please continue reading Figure 1 As shown, the method for constructing a family user feature database further includes: Step S3, collecting unique information of the family user according to the role type in the identity information of the family user, the unique information includes but is not limited to education information, work information, life habit information, shopping information, parenting information, disease information, medication information and other data for different user concerns, the education information includes but is not limited to subject grades and hobbies, the work information includes but is not limited to work stress level and working hours, the unit of working hours is hour, the work stress level includes low, medium and high, the life habit information includes but is not limited to smoking information and drinking information, the smoking information is the daily smoking amount, the drinking information includes the daily drinking amount and the daily drinking frequency, the shopping information includes but is not limited to shopping preferences and shopping frequency, the parenting information includes but is not limited to the companionship time and family activity arrangements, the disease information includes but is not limited to hypertension and arthritis, the medication information includes but is not limited to the medication amount and medication records, etc.

[0036] Specifically, in step S3 described in this embodiment, the unique information of the family user is collected based on the identity information. If the role type is a child, the education information of the family user currently being analyzed is collected. If the role type is a father, the work information and living habit information of the family user currently being analyzed is collected. If the role type is a mother, the shopping information and parenting information of the family user currently being analyzed is collected. If the role type is an elderly person, the disease information and medication information of the family user currently being analyzed is collected.

[0037] It can be understood that the present embodiment does not specifically limit the content of the collection of unique information, and technical personnel in this field can set it freely. Family users can set the unique information according to the composition of family members and the distribution of family tasks. When setting the collection of unique information for children, it should be noted that the unique data is related to the children's education and healthy growth data. When setting the collection of unique information for fathers or mothers, it should be noted that the unique information is related to their life health data and work pressure data. When setting the collection of unique information for the elderly, it should be noted that the unique information is related to the health and safety of the elderly.

[0038] Specifically, in step S3 described in this embodiment, specific information related to the role (such as education information, work information, shopping information, disease information, etc.) of the family user is collected according to the role type (such as father, mother, child, elderly, etc.). Targeted data collection can more accurately reflect the specific needs and behavior patterns of different roles, thereby enhancing the personalized analysis capabilities of the database.

[0039] Please continue reading Figure 1 As shown, the method for constructing a family user feature database further includes: Step S4, analyzing the user's unique characteristics based on the collected identity information and unique information of the family user.

[0040] Specifically, in step S4 of this embodiment, the user's unique characteristics are analyzed according to the name, role type and unique information, and the user's unique characteristics are set to S(j,i). If the role type is a child, S(j,i)=σ(s(j,i)) is set; if the role type is a father, S(j,i)=σ(s(j,i)) is set. , if the role type is mother, set S(j,i)=[f3(j,i)]·[T3(j,i)], if the role type is old, set , where s(j,i) represents academic performance, σ(s(j,i)) represents the standard deviation of academic performance, T2(j,i) represents working hours, A1(j,i) represents daily smoking, A2(j,i) represents daily alcohol consumption, f2(j,i) represents daily drinking frequency, f3(j,i) represents shopping frequency, T3(j,i) represents companionship time, n(j,i) represents the number of diseases, A4(j,i) represents medication dosage, and E(j,i) represents age.

[0041] It can be understood that the present embodiment does not specifically limit the analysis method of user-specific characteristics, and technical personnel in this field can set it freely, and only needs to meet the requirements for target feature extraction set according to different role types. For example, the unique characteristics of children should focus on the education and growth data of children, the unique characteristics of fathers should focus on the work pressure and physical health data of fathers, the unique characteristics of mothers should focus on the mother's daily shopping habits and parenting data, and the unique characteristics of the elderly should focus on the elderly's physical health data.

[0042] Specifically, in step S4 described in this embodiment, by analyzing the unique information of home users, the unique characteristics of users can be extracted. These unique characteristics are the key to distinguishing different users and can help the database more accurately identify and classify the characteristics of home users, thereby improving the accuracy of the database and the level of personalized services.

[0043] Please continue reading Figure 1 As shown, the method for constructing a family user feature database further includes: Step S5, storing the characteristic data and the user-specific characteristics, analyzing the family data characteristics according to the stored characteristic data, and classifying the family data characteristics to obtain the family characteristic type.

[0044] Specifically, in step S5 described in this embodiment, by storing feature data and user-specific features and analyzing and classifying family data features, the feature types of different families can be identified, which can help the database better understand the similarities and differences between families, thereby improving the classification accuracy and analysis efficiency of the database.

[0045] See also Figure 3 As shown, it is an analysis method of family data characteristics, including: Step S51, storing the characteristic data and user-specific characteristics.

[0046] Step S52, analyzing the characteristics of the family data according to the stored characteristic data.

[0047] Specifically, in step S52 described in this embodiment, the family data characteristics are analyzed according to the stored characteristic data, and the family data characteristics are set to F(j), and F(j)=[NP(j), ET(j), P1(j), P2(j)] is set, wherein ET(j) represents the family's eating time, P1(j) represents the family's food preference, and P2(j) represents the family's exercise preference.

[0048] Specifically, in this embodiment, when analyzing family data characteristics, different numbers can be set for different family food preferences and family exercise preferences, and the numbers are matched one-to-one with different preferences, such as 0 for no preference, 1 for family food preference for pasta or family exercise preference for running, etc.

[0049] Specifically, in step S52 described in this embodiment, the stored characteristic data is analyzed to analyze the family data characteristics, thereby achieving a comprehensive analysis of the characteristic data of different families, and the data characteristics of the family's characteristic data are expressed using the same set of data, thereby improving the efficiency of analyzing the family user data and improving the accuracy of the family user characteristic analysis.

[0050] Please continue reading Figure 3 As shown, the method for analyzing family data characteristics also includes: Step S53, counting the number of similar families based on family data characteristics.

[0051] Specifically, in step S53 of this embodiment, the families corresponding to the non-currently analyzed family data features satisfying α≤F(j)·F(k)≤1 are extracted as similar families, and the number of similar families is counted as the number of similar families, and the number of similar families is set to N(j), where F(k) represents the non-currently analyzed family data features, k represents the non-currently analyzed family number, and k∈N + And k≠j, α represents the family extraction parameter, 0.9≤α<1. It can be understood that the value of the family extraction parameter is not specifically limited in this embodiment, and those skilled in the art can freely set it as long as it satisfies the extraction of similar families. The optimal value of the family extraction parameter is: α=0.95.

[0052] Please continue reading Figure 3 As shown, the method for analyzing family data characteristics also includes: Step S54, classifying the family data features according to the number of similar families to obtain family feature types.

[0053] Specifically, in step S54 of this embodiment, the family data features are classified according to the number of similar families. If N(j) / j max <β, the family characteristic type of the current analyzed family is determined to be one type, if N(j) / j max ≥β, the family characteristics of the current analyzed family are determined to be of type II, where j maxrepresents the maximum value of the family number, β represents the family classification threshold, 0.05≤β≤0.08. It can be understood that the optimal value of the family classification threshold is not specifically limited in this embodiment, and those skilled in the art can freely set it as long as it meets the judgment of the family feature type. The optimal value of the family classification threshold is: β=0.06.

[0054] Specifically, in step S54 described in this embodiment, by analyzing similar families, it is determined whether the number of families similar to the currently analyzed family is large, so as to extract families with specific stronger characteristics, thereby improving the analysis efficiency of family user data and the accuracy of family user feature analysis.

[0055] Please continue reading Figure 1 As shown, the method for constructing a family user feature database further includes: Step S6, analyzing the similarity of similar families according to the family data characteristics and the family characteristic types, and analyzing the characteristic prominence of family users according to the similarity of similar families, the daily characteristics of users and the unique characteristics of users.

[0056] Specifically, in step S6 described in this embodiment, by analyzing the feature significance of home users, it is possible to identify which features are most significant to home users, which can help the database more accurately extract the most representative features for users, thereby improving the accuracy of the database and personalized recommendation capabilities.

[0057] See also Figure 4 As shown, it is a method for analyzing feature significance, including: Step S61, analyzing the feature prominence according to the user's daily features and the user's unique features.

[0058] Specifically, in step S61 of this embodiment, the feature prominence is analyzed according to the user's daily characteristics and the user's unique characteristics, and the feature prominence is set to G(j,i). , Q(j,i) represents the user characteristic parameter, Q(j,i)=D(j,i)·S(j,i), u represents the number of the non-current analyzed family user, u∈N + And u≠i,i max Indicates the maximum value of the home user number.

[0059] Please continue reading Figure 4 As shown, the feature significance analysis method also includes: Step S62, analyzing the similarity of similar families according to the family data characteristics.

[0060] Specifically, in step S62 of this embodiment, the similarity of similar families is analyzed according to the daily characteristics of similar families and users, and the similarity of similar families is set as W(j). , where D(K,i) represents the user daily characteristics of family users in similar families whose role type is the same as the role type of the current analyzed family user, and K represents the family number of the similar family.

[0061] Please continue reading Figure 4 As shown, the feature significance analysis method also includes: Step S63, improving the feature prominence analysis process according to the similarity of similar families.

[0062] Specifically, in step S63 of this embodiment, the feature significance analysis process is improved according to the similarity of similar families. If W(j)>w, the feature significance analysis process is not improved. Otherwise, the feature significance analysis process is improved. The improved feature significance is G1(j,i), and G1(j,i)=G(j,i)×e W(j) ; Wherein, w represents the similarity threshold, 0.4≤w≤0.6. It can be understood that the value of the similarity threshold is not specifically limited in this embodiment, and those skilled in the art can freely set it, as long as the improvement of the feature significance analysis process is satisfied. The optimal value of the similarity threshold is: w=0.5.

[0063] Please continue reading Figure 4 As shown, the feature significance analysis method also includes: Step S64, improving the similarity analysis process of similar families according to the family feature type.

[0064] Specifically, in step S64 of this embodiment, the analysis process of similarity of similar families is improved according to the family feature type. If the family feature type is one type, the analysis process of similarity of similar families is improved, and the improved similarity of similar families is W1(j), and W1(j)=[W(j)+R(j)] / 2 is set. If the family feature type is two types, the analysis process of similarity of similar families is not improved, where R(j) represents the unique feature similarity. , S(K,i) represents the user-specific characteristics of family users in similar families whose role type is the same as the role type of the current analyzed family user.

[0065] Please continue reading Figure 1 As shown, the method for constructing a family user feature database further includes: Step S7, constructing a family user feature database according to the feature significance of the family users.

[0066] Specifically, in step S7 described in this embodiment, a family user feature database is constructed according to the feature significance, and the collected health information, behavior information and identity information of the family user are used as the basic data of the family user feature database, and the user's biometrics are used as the verification data for accessing the family user feature database. If G(j,i)>g, the collected unique information of the current family user is used as the feature data of the family user feature database, and vice versa, the collected unique information of the current family user is used as the basic data of the family user feature database, wherein g represents the feature construction threshold, 0.7≤g≤0.9. It can be understood that in this embodiment, the value of the feature construction threshold is not specifically limited, and those skilled in the art can freely set it, as long as it satisfies the construction of the family user feature database. The optimal value of the feature construction threshold is: g=0.8.

[0067] Specifically, the feature data in the family user feature database is feature data that can reflect the differences between family users and other users. The data content can better reflect the characteristics of users and provide necessary analysis data for understanding user needs and optimizing user service experience.

[0068] Specifically, in step S7 described in this embodiment, a family user feature database is constructed based on feature significance, which can ensure that the data in the database can accurately reflect the characteristics and needs of family users. By taking significant features as the core data of the database, the practicality and personalized service level of the database can be improved, thereby providing strong data support for subsequent health monitoring, security verification, personalized recommendations and other applications.

[0069] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the embodiments of the present invention. For ordinary technicians in this field, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the embodiments here. All obvious changes or modifications derived from the technical solution of the present invention are still within the protection scope of the present invention.

Claims

1. A method for constructing a family user feature database, characterized in that: include: Step S1, collecting health information, behavior information and identity information of family users; Step S2, extracting characteristic data based on the collected health information, behavior information and identity information of the family user, and analyzing the daily characteristics of the family user based on the collected health information, behavior information and identity information of the family user; Step S3, collecting unique information of the family user according to the role type in the identity information of the family user; Step S4, analyzing the user's unique characteristics based on the collected identity information and unique information of the family user; Step S5, storing the characteristic data and the user-specific characteristics, analyzing the family data characteristics according to the stored characteristic data, and classifying the family data characteristics to obtain the family characteristic type; Step S6, analyzing the similarity of similar families according to the family data characteristics and the family characteristic type, and analyzing the characteristic prominence of family users according to the similarity of similar families, the daily characteristics of users and the unique characteristics of users; Step S7, constructing a family user feature database according to the feature significance of the family users.

2. The method for constructing a family user characteristic database according to claim 1, characterized in that: The step S2 comprises: Step S21, numbering the family users to obtain a family user number and a family number; Step S22, extracting feature data based on health information, behavior information and identity information; Step S23, analyzing the user's daily characteristics based on health information, behavior information and identity information.

3. The method for constructing a family user characteristic database according to claim 2, characterized in that: In the step S21, the family users are numbered according to their identity information, and each family user is numbered in descending order of age, and the family user number is set as i, and different families are numbered, and the family number is set as j; In step S22, the number of household users in the same household is counted as the household size, and the household size is set as NP(j); the number of times of each food preference in the same household is counted, and the food preference corresponding to the largest number of food preferences is taken as the household food preference; if the food preferences of the users in the same household are different, the household food preference is set as no preference; Count the number of times of each sports preference type in the same family, and take the sports preference type corresponding to the largest number of sports preference types as the family sports preference. If the sports preference types of users in the same family are different, set the family sports preference to no preference; set the family meal time to be the same as the user's meal time; In step S23, the user's daily characteristics are analyzed according to the family user's height, weight, blood pressure, exercise time, sleep time, wake-up time and name to obtain the user's daily characteristics D(j,i).

4. The method for constructing a family user characteristic database according to claim 3, characterized in that: In step S3, specific information of the family user is collected based on the identity information. If the role type is a child, the education information of the family user currently being analyzed is collected. If the role type is a father, the work information and living habit information of the family user currently being analyzed is collected. If the role type is a mother, the shopping information and parenting information of the family user currently being analyzed is collected. If the role type is an elderly person, the disease information and medication information of the family user currently being analyzed is collected.

5. The method for constructing a family user characteristic database according to claim 4, characterized in that: In the step S4, the user-specific features are analyzed according to the name, role type and specific information to obtain the user-specific features S(j,i).

6. The method for constructing a family user characteristic database according to claim 5, characterized in that: The step S5 comprises: Step S51, storing feature data and user-specific features; Step S52, analyzing the family data characteristics according to the stored characteristic data; Step S53, counting the number of similar families according to family data characteristics; Step S54, classifying the family data features according to the number of similar families to obtain family feature types.

7. The method for constructing a family user characteristic database according to claim 6, characterized in that: In the step S52, the family data feature is analyzed according to the stored feature data to obtain the family data feature F(j); In the step S53, the families corresponding to the non-currently analyzed family data features satisfying α≤F(j)·F(k)≤1 are extracted as similar families, and the number of similar families is counted as the number of similar families N(j), where F(k) represents the non-currently analyzed family data features, k represents the non-currently analyzed family number, and α represents the family extraction parameter; In the step S54, the family data features are classified according to the number of similar families to obtain family feature types, and the family feature types include one category and two categories.

8. The method for constructing a family user characteristic database according to claim 7, characterized in that: The step S6 comprises: Step S61, analyzing feature prominence according to the user's daily features and the user's unique features; Step S62, analyzing the similarity of similar families according to family data characteristics; Step S63, improving the feature significance analysis process according to the similarity of similar families; Step S64, improving the similarity analysis process of similar families according to the family feature type.

9. The method for constructing a family user characteristic database according to claim 8, characterized in that: In the step S61, the feature prominence is analyzed according to the user's daily features D(j,i) and the user's unique features S(j,i) to obtain the feature prominence G(j,i); In the step S62, the similarity of similar families is analyzed according to the similar families and the daily characteristics of the user D(j,i) to obtain the similarity of similar families W(j); In the step S63, the feature significance analysis process is improved according to the similarity W(j) of the similar families. When W(j)≤w, the feature significance analysis process is improved. The improved feature significance is G1(j,i), where w represents the similarity threshold. In the step S64, the analysis process of similarity of similar families is improved according to the family feature type. When the family feature type is one type, the analysis process of similarity of similar families is improved, and the improved similarity of similar families is W1(j).

10. The method for constructing a family user characteristic database according to claim 9, characterized in that: In the step S7, a family user feature database is constructed according to the feature significance, the collected health information, behavior information and identity information of the family user are used as the basic data of the family user feature database, and the user's biometric characteristics are used as the verification data for accessing the family user feature database. If G(j,i)>g, the collected unique information of the current family user is used as the feature data of the family user feature database, otherwise, the collected unique information of the current family user is used as the basic data of the family user feature database, wherein g represents the feature construction threshold.

Images