CN113672800B - Item recommendation method and storage medium for real-name authentication of natural person user - Google Patents
Item recommendation method and storage medium for real-name authentication of natural person user Download PDFInfo
- Publication number
- CN113672800B CN113672800B CN202110785193.6A CN202110785193A CN113672800B CN 113672800 B CN113672800 B CN 113672800B CN 202110785193 A CN202110785193 A CN 202110785193A CN 113672800 B CN113672800 B CN 113672800B
- Authority
- CN
- China
- Prior art keywords
- user
- item
- natural person
- real
- matters
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 239000011159 matrix material Substances 0.000 claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000013178 mathematical model Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 4
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a real-name authentication natural person user item recommending method and a storage medium, belonging to the field of government service data analysis, the technical problem to be solved by the invention is how to combine two dimensions of users and items, and combine the characteristics of time, region and the like to provide more intelligent service for the office masses, the adopted technical scheme is as follows: the method comprises the steps of taking natural person information services shared by a shared exchange platform, extracting features of all users, taking matters as cores, taking user groups after handling, paying attention to and consulting complaints as main ranges, extracting main feature points and descriptions of matters related to users from the whole province, the whole city and the single county, comprehensively calculating Euclidean distance between the features of the users and the features of the matters to determine matching degree, and obtaining final recommendation indexes through weighted calculation of the matching degree of different features; the method comprises the following steps: constructing a user feature matrix; extracting a crowd feature matrix; the logged-in user matches the event crowd characteristics.
Description
Technical Field
The invention relates to the field of data analysis of government service, in particular to a real-name authentication natural person user item recommendation method and a storage medium.
Background
With the development of government service, the intelligent application of government service has higher and higher requirements, how to accurately locate the characteristics of users, and recommending correct content becomes a difficult problem. Different from the Internet shopping website, the same user of the government service network has the characteristics of less access quantity, strong access destination, head direct for themes and the like, so that the content-based recommendation algorithm is difficult to locate and cannot acquire the items which the user wants to transact. Therefore, a big data analysis method is needed to record and analyze traces left by all the operations of handling, browsing, focusing, searching and the like of the user on the government service platform, specific data comprise search information, region information, handling guide information, history handling information and the like, and information is directly obtained from the data by combining the characteristics of time, region and the like from two dimensions of the user and the item, so as to obtain a conclusion.
With the development of the intellectualization of government service, the conventional recommendation method with simple experience or business popularity cannot meet the current practical application requirements, so that how to combine two dimensions of users and matters and combine the characteristics of time, region and the like to provide more intelligent service for the masses is a technical problem to be solved urgently.
Disclosure of Invention
The technical task of the invention is to provide a real-name authentication natural person user item recommending method and a storage medium, so as to solve the problem of how to combine two dimensions of a user and an item and provide more intelligent service for the office masses by combining the characteristics of time, region and the like.
The technical task of the invention is realized in the following way, a real-name authentication natural person user item recommending method is realized, the method uses the natural person information service shared by a shared exchange platform to extract the characteristics of all users, then uses items as cores and uses the user group with processed, concerned and consultation complaint items as main ranges, extracts main characteristic points and descriptions of items related to users from the whole province, the whole city and the single county, comprehensively calculates Euclidean distance between the characteristics of the users and the characteristics of the items to determine the matching degree, and obtains the final recommendation index through weighted calculation of the matching degree of different characteristics; the method comprises the following steps:
constructing a user feature matrix: the real-name authentication natural person user extracts the user information label through the data sharing service to construct a user characteristic matrix;
Extracting a crowd characteristic matrix: extracting crowd feature matrixes of matters, news and notification notices based on crowd features of matters concerned, browsed and business transacted;
The logged-in user matches the event crowd characteristics.
Preferably, the user feature matrix is constructed specifically as follows:
Collecting real-name authentication natural person user characteristic data;
And constructing a two-dimensional mathematical model of the user characteristics.
More preferably, the collection of real-name authentication natural person user characteristic data is specifically as follows:
Collecting office data from a shared switching platform or a business system;
acquiring user characteristic data, and cleaning to remove abnormal data;
determining the final value of the same characteristic value according to the credibility of the data source;
And extracting the characteristic attribute of the natural person user and marking and storing.
More preferably, the user characteristic two-dimensional mathematical model is constructed as follows:
Constructing a characteristic data marking model of a user according to all the characteristics which can be extracted by the existing real-name authentication natural person user data sharing;
the construction of the user characteristic data marking model is to construct a characteristic matrix of the user based on all the characteristics; wherein, partial characteristics are attributes or not, and partial characteristics adopt segmentation to form acquired values.
Preferably, the extraction crowd feature matrix is specifically as follows:
building a feature model of the item user group: according to item information and user information data in the existing service handling data, taking user group data of items as a reference, acquiring user feature sets related to all the items to form a feature proportion matrix, namely the overall feature of the item handling crowd, wherein each feature occupies the overall population proportion; wherein, the service handling time is limited to the service in the last 1 year;
Acquiring time sequence characteristics and region characteristics of the transaction service: the transaction of partial matters has territory and periodicity, namely, the business can only be transacted by local user personnel or only be transacted in a specific month, and the territory and the time characteristics of the matters are key characteristics of the matters to determine whether the current user can transact in a certain time period; according to different handling results of business handling data of matters in different time periods, (for example, 1 year is divided into 12 time periods according to months), user application and handling result statistics of each time period are obtained, and crowd analysis that the characteristics and regional characteristics of matters in any time period (month) are not accepted is obtained from application conditions and the matters handling of matters, the matters are applied to extract keywords of local household books, and the business analysis that is not accepted is used for extracting information of the positions of the household books of the applicant.
Preferably, the matching of the logged-in user with the item crowd characteristics is specifically as follows:
Real-name authentication natural person user is matched with item characteristics: matching a characteristic point model constructed by the real-name authentication natural person user with a characteristic point model item of the transaction crowd to acquire the matching degree of the real-name authentication natural person user and the transaction;
recommended item ordering and filtering: the matching degree of the user features and the item features is sequenced from small to large, recommendation degrees of all items are obtained, items which are not processed and do not meet processing conditions in the current month are removed according to the current date and the real-name authenticated natural person user premises, and finally a recommended item list of the user is obtained.
More preferably, the matching degree of the real-name authentication natural person user and the item is determined by calculating the Euclidean distance between two characteristic points of the natural person and the item; and (3) summing the matching Euclidean distances of all the characteristic points, sequentially obtaining the matching degree of matters, and simultaneously balancing errors of the characteristic of the matters acquired by the matters handling staff on different orders by adopting a step weighting coefficient, wherein the formula is as follows:
pm＝∑(|pi-mi|)*Hi；
Wherein p m is the recommendation index for item i; p i represents the value of natural human user feature i; (|p i-mi |) represents the Euclidean distance between two feature points of a natural person and an item, and the shorter the Euclidean distance is, the better the matching degree of the two feature points is represented; m i represents the value of feature i of item m; h i denotes an event handling volume hierarchy weighting coefficient.
More preferably, the transaction amount hierarchy weighting coefficient Hi is specifically set as follows:
① . The transaction traffic is more than or equal to 5000, and H i = 0.9;
② . The transaction traffic is less than 5000 and H i =0.95;
③ . The transaction traffic is less than or equal to 500 and less than 1000, and H i =1.0;
④ . The transaction traffic is less than or equal to 100 and less than 500, and H i =1.05;
⑤ . 100 < transaction traffic, H i =1.1.
More preferably, the recommended item ranking filter is specifically as follows:
Acquiring service handling data through a shared data platform;
obtaining an applicant transaction list through service transaction data;
performing necklace analysis and screening through the applicant transaction list;
acquiring a transaction sequence chain; logging in the real-name authentication natural person user at the same time to obtain a service list which is transacted by the real-name authentication natural person user;
Performing item sequence comparison according to the item sequence chain and the business list transacted by the name authentication natural person user, and acquiring a lower link item list;
Comparing the natural human features with the features of the item crowd in the item list, and removing items with low matching degree;
And acquiring a name authentication natural person user item recommendation list.
A computer readable storage medium having stored therein a computer program executable by a processor to implement an item recommendation method for real-name authentication of natural human users as described above.
The item recommendation method and the storage medium for the real-name authentication of the natural person user have the following advantages:
Based on SURF algorithm, the invention adopts real-name authentication natural person user feature point extraction and item crowd feature point extraction, the user is matched with item crowd feature points, the comprehensive matching condition of the user and items is obtained, a model corresponding to the items of the user is constructed, the items possibly handled by the user are dynamically analyzed and identified, and the content accuracy of inquiry and search service and the like is improved;
The method is applied to intelligent analysis and recommendation in the field of government affair service, and based on user information and event history handling users shared by a shared exchange platform, the characteristics of the users and the events are extracted by utilizing accelerated robust feature learning, so that an effective method for accurately recommending events, policies and notices is realized. The method can realize the accurate pushing of the user information and the service of the natural person, reduce the times of searching and clicking, and avoid the condition that the user leaks the service information;
The third step of the invention is to share the user characteristic data through the data sharing exchange platform, extract the user and the feature points of the business handling crowd, calculate the Euclidean distance between the feature points and give weight, obtain the business recommendation index; the user system based on real-name authentication needs to share the exchange platform to provide natural person user information support;
The method comprises the steps of carrying out feature attribute extraction, feature attribute description and feature attribute weighted matching on natural person users and matters of real-name authentication, finally obtaining the matching index of the matters to form a user recommended government service matters list, wherein the natural person user features of the real-name authentication are based on the forms of interfaces, data sets, files and the like of user information data developed by a data sharing exchange platform, the accuracy of the method depends on the feature attribute acquisition degree of the users, the more the natural person users can share data, the more the government service network access behaviors or the more transacted business, the more the matters recommended by the users are accurate, the characteristics of the users and the matters are extracted by utilizing accelerated robust feature learning, and an effective method for accurately recommending matters, policies and notices is realized;
Based on the characteristics of matters, the invention accurately recommends relevant contents to a user side, the personal space of government service network users needs more intelligent and humanized pushing, and the contents such as business service matters, policy files, notification notices and the like are intelligently recommended to be solved according to the personal characteristic information of real-name registered natural people users, so that the effect of thousands of people and thousands of faces is finally realized.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a flow chart diagram of a real-name authentication natural person user item recommendation method;
FIG. 2 is a flow diagram of recommended item ordering filtering.
Detailed Description
The item recommendation method for real-name authentication of natural person users and the storage medium of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
Example 1:
As shown in figure 1, the real-name authentication natural person user item recommending method of the invention comprises the steps of taking natural person information services shared by a shared exchange platform, extracting characteristics of all users, taking items as cores, taking user groups after handling, paying attention to and consulting complaints as main ranges, extracting main characteristic points and descriptions of items related to users from the whole province, the whole city and the single county, comprehensively calculating Euclidean distance between the characteristics of the users and the characteristics of the items, determining matching degree, and obtaining final recommendation indexes through weighted calculation of the matching degree of different characteristics; the method comprises the following steps:
S1, constructing a user feature matrix: the real-name authentication natural person user extracts the user information label through the data sharing service to construct a user characteristic matrix;
s2, extracting a crowd feature matrix: extracting crowd feature matrixes of matters, news and notification notices based on crowd features of matters concerned, browsed and business transacted;
s3, feature matching: the logged-in user matches the event crowd characteristics.
In this embodiment, the construction of the user feature matrix in step S1 is specifically as follows:
s101, collecting real-name authentication natural person user characteristic data;
s102, constructing a user characteristic two-dimensional mathematical model.
In this embodiment, the collection of real-name authentication natural person user feature data in step S101 is specifically as follows:
S10101, collecting office data from a shared exchange platform or a business system;
s10102, acquiring user characteristic data, and cleaning to remove abnormal data;
S10103, determining the final value of the same characteristic value according to the credibility of the data source;
s10104, extracting characteristic attributes of natural human users and marking and storing.
In this embodiment, the construction of the user characteristic two-dimensional mathematical model in step S102 is specifically as follows:
S10201, constructing a characteristic data marking model of a user according to all the characteristics which can be extracted by the existing real-name authentication natural person user data sharing;
s10202, constructing a characteristic data marking model of the user, wherein the construction of the characteristic data marking model of the user is to construct a characteristic matrix of the user based on all the characteristics; wherein, partial characteristics are attributes or not, and partial characteristics adopt segmentation to form acquired values.
In this embodiment, the extraction crowd feature matrix of step S2 is specifically as follows:
S201, constructing a feature model of the item user group: according to item information and user information data in the existing service handling data, taking user group data of items as a reference, acquiring user feature sets related to all the items to form a feature proportion matrix, namely the overall feature of the item handling crowd, wherein each feature occupies the overall population proportion; wherein, the service handling time is limited to the service in the last 1 year;
S202, acquiring time sequence characteristics and region characteristics of the transaction service: the transaction of partial matters has territory and periodicity, namely, the business can only be transacted by local user personnel or only be transacted in a specific month, and the territory and the time characteristics of the matters are key characteristics of the matters to determine whether the current user can transact in a certain time period; according to different handling results of business handling data of matters in different time periods, (for example, 1 year is divided into 12 time periods according to months), user application and handling result statistics of each time period are obtained, and crowd analysis that the characteristics and regional characteristics of matters in any time period (month) are not accepted is obtained from application conditions and the matters handling of matters, the matters are applied to extract keywords of local household books, and the business analysis that is not accepted is used for extracting information of the positions of the household books of the applicant.
In this embodiment, the matching between the logged-in user and the item crowd feature in step S3 is specifically as follows:
s301, matching a real-name authentication natural person user with the item characteristics: matching a characteristic point model constructed by the real-name authentication natural person user with a characteristic point model item of the transaction crowd to acquire the matching degree of the real-name authentication natural person user and the transaction;
S302, sorting and filtering recommended items: the matching degree of the user features and the item features is sequenced from small to large, recommendation degrees of all items are obtained, items which are not processed and do not meet processing conditions in the current month are removed according to the current date and the real-name authenticated natural person user premises, and finally a recommended item list of the user is obtained.
In the embodiment, the matching degree of the real-name authentication natural person user and the item in step S301 is determined by calculating the euclidean distance between two feature points of the natural person and the item; and (3) summing the matching Euclidean distances of all the characteristic points, sequentially obtaining the matching degree of matters, and simultaneously balancing errors of the characteristic of the matters acquired by the matters handling staff on different orders by adopting a step weighting coefficient, wherein the formula is as follows:
pm＝∑(|pi-mi|)*Hi；
Wherein p m is the recommendation index for item i; p i represents the value of natural human user feature i; (|p i-mi |) represents the Euclidean distance between two feature points of a natural person and an item, and the shorter the Euclidean distance is, the better the matching degree of the two feature points is represented; m i represents the value of feature i of item m; h i denotes an event handling volume hierarchy weighting coefficient.
In this embodiment, the value of the transaction amount hierarchy weighting coefficient Hi is specifically as follows:
① . The transaction traffic is more than or equal to 5000, and H i = 0.9;
② . The transaction traffic is less than 5000 and H i =0.95;
③ . The transaction traffic is less than or equal to 500 and less than 1000, and H i =1.0;
④ . The transaction traffic is less than or equal to 100 and less than 500, and H i =1.05;
⑤ . 100 < transaction traffic, H i =1.1.
The specific weighting coefficients are as follows:
| Sequence number | Transaction traffic | Weighting coefficient |
| 1 | Greater than or equal to 5 kilo | 0.9 |
| 2 | Less than 5 thousand and equal to or more than 1 thousand | 0.95 |
| 3 | Less than 1 thousand and equal to or more than 5 hundred | 1.0 |
| 4 | Less than 5 hundred and equal to or more than 1 hundred | 1.05 |
| 5 | Less than 1 hundred | 1.1 |
As shown in fig. 2, the recommendation ordering filtering in step S302 in this embodiment is specifically as follows:
S30201, acquiring service handling data through a shared data platform;
s30202, obtaining an applicant transaction list through the service transaction data;
S30203, performing necklace analysis and screening through an applicant transaction list;
S30304, acquiring a transaction sequence chain; logging in the real-name authentication natural person user at the same time to obtain a service list which is transacted by the real-name authentication natural person user;
S30305, performing item sequence comparison according to the item sequence chain and the business list transacted by the name authentication natural person user to obtain a lower link item list;
S30306, comparing the natural person characteristics with the item crowd characteristics in the item list, and removing items with low matching degree;
s30307, acquiring a name authentication natural person user item recommendation list.
Wherein, the item chain analysis and screening adopts personnel duty ratio analysis, and specific comparison examples are as follows:
one of the to-be-selected necklaces is item A-, item B-, item C
The number of the transacted items A is M, the number of the transacted items A and the number of the transacted items B is N, and P is the proportion of the coincidence condition, and the dynamic calculation is carried out for 1 time every day at any time. If M/N > =p, then transaction B meets the requirements, otherwise transaction a to transaction B chain breaks.
Example 2:
Taking the application of a certain provincial government service system as an example, the steps of configuration implementation are as follows:
(1) Configuring natural person user scheduling service, and acquiring registered natural person user characteristic information from a shared exchange platform, wherein the registered natural person user information comprises data resources such as population libraries, marital, work, household books and the like;
(2) Extracting a part handling library, a user access behavior library and a user information attention library, and extracting user group basic information such as user matters, news, notices and the like for storage;
(3) Training and acquiring a user group feature matrix of each item, news and notification according to the item, news and notification, and warehousing and storing the item, news and notification features;
(4) Calculating the matching degree of matters, news and notices and users, calculating the news and notices to obtain the labels of the attention browser of the users, and subsequently updating and reminding news, notices or policy files of the same kind; the items are directly stored in an item recommendation library according to the industry region;
(5) And the release service is provided for the government service network, and the recommended item list and the recommended news, notification and policy file labels are directly acquired through the identity card number.
Example 3:
The embodiment of the invention also provides a computer readable storage medium, wherein a plurality of instructions are stored, and the instructions are loaded by a processor, so that the processor executes the item recommendation method for real-name authentication of natural human users in any embodiment of the invention. Specifically, a system or apparatus provided with a storage medium on which a software program code realizing the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or apparatus may be caused to read out and execute the program code stored in the storage medium.
In this case, the program code itself read from the storage medium may realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code form part of the present invention.
Examples of storage media for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (e.g., CD-ROMs, CD-R, CD-RW, DVD-ROMs, DVD-RYM, DVD-RW, DVD+RW), magnetic tapes, nonvolatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer by a communication network.
Further, it should be apparent that the functions of any of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform part or all of the actual operations based on the instructions of the program code.
Further, it is understood that the program code read out by the storage medium is written into a memory provided in an expansion board inserted into a computer or into a memory provided in an expansion unit connected to the computer, and then a CPU or the like mounted on the expansion board or the expansion unit is caused to perform part and all of actual operations based on instructions of the program code, thereby realizing the functions of any of the above embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (5)
1. The method is characterized in that the method uses natural person information service shared by a shared exchange platform to extract characteristics of all users, uses a user group with treated, concerned and consultated matters as a main range, extracts main characteristic points and description of matters related to users from the whole province, the whole city, the state and the single county, comprehensively calculates Euclidean distance between the characteristics of the users and the characteristics of the matters to determine matching degree, and obtains final recommendation indexes through weighted calculation of the matching degree of different characteristics; the method comprises the following steps:
constructing a user feature matrix: the real-name authentication natural person user extracts the user information label through the data sharing service to construct a user characteristic matrix;
Extracting a crowd characteristic matrix: extracting crowd feature matrixes of matters, news and notification notices based on crowd features of matters concerned, browsed and business transacted;
the logged-in user is matched with the characteristics of the item crowd;
the construction of the user characteristic matrix is specifically as follows:
collecting real-name authentication natural person user characteristic data; the method comprises the following steps:
Collecting office data from a shared switching platform or a business system;
acquiring user characteristic data, and cleaning to remove abnormal data;
determining the final value of the same characteristic value according to the credibility of the data source;
Extracting the characteristic attribute of the natural person user and marking and storing;
constructing a user characteristic two-dimensional mathematical model; the method comprises the following steps:
Constructing a characteristic data marking model of a user according to all the characteristics which can be extracted by the existing real-name authentication natural person user data sharing;
The construction of the user characteristic data marking model is to construct a characteristic matrix of the user based on all the characteristics; wherein, part of the characteristics are attributes or not, and part of the characteristics adopt segmentation to form an acquired numerical value;
The extraction of the crowd characteristic matrix is specifically as follows:
building a feature model of the item user group: according to item information and user information data in the existing service handling data, taking user group data of items as a reference, acquiring user feature sets related to all the items to form a feature proportion matrix, namely the overall feature of the item handling crowd, wherein each feature occupies the overall population proportion; wherein, the service handling time is limited to the service in the last 1 year;
acquiring time sequence characteristics and region characteristics of the transaction service: obtaining user application and handling result statistics of each time period according to different handling results of business handling data of matters in different time periods, and obtaining characteristics and regional characteristics of matters in any time period in time sequence from application conditions of matters and crowd analysis of the non-accepted business handling, wherein the matters are applied for extracting keywords of local household registration, and the non-accepted business analysis is used for extracting information of the household registration of the applicant;
the matching of the logged-in user and the item crowd characteristics is specifically as follows:
Real-name authentication natural person user is matched with item characteristics: matching a characteristic point model constructed by the real-name authentication natural person user with a characteristic point model item of the transaction crowd to acquire the matching degree of the real-name authentication natural person user and the transaction;
recommended item ordering and filtering: the matching degree of the user features and the item features is sequenced from small to large, recommendation degrees of all items are obtained, items which are not processed and do not meet processing conditions in the current month are removed according to the current date and the real-name authenticated natural person user premises, and finally a recommended item list of the user is obtained.
2. The item recommendation method of the real-name authenticated natural person user according to claim 1, wherein the matching degree of the real-name authenticated natural person user and the item is determined by calculating the euclidean distance between two feature points of the natural person and the item; and (3) summing the matching Euclidean distances of all the characteristic points, sequentially obtaining the matching degree of matters, and simultaneously balancing errors of the characteristic of the matters acquired by the matters handling staff on different orders by adopting a step weighting coefficient, wherein the formula is as follows:
pm=∑(|pi-mi|)*Hi；
Wherein p m is the recommendation index for item i; p i represents the value of natural human user feature i; (|p i-mi |) represents the Euclidean distance between two feature points of a natural person and an item, and the shorter the Euclidean distance is, the better the matching degree of the two feature points is represented; m i represents the value of feature i of item m; h i denotes an event handling volume hierarchy weighting coefficient.
3. The item recommendation method for real-name authentication of natural person users according to claim 2, wherein the item handling amount hierarchy weighting coefficient H i has the following values:
① . The transaction traffic is more than or equal to 5000, and H i = 0.9;
② . The transaction traffic is less than 5000 and H i =0.95;
③ . The transaction traffic is less than or equal to 500 and less than 1000, and H i =1.0;
④ . The transaction traffic is less than or equal to 100 and less than 500, and H i =1.05;
⑤ . 100 < transaction traffic, H i =1.1.
4. The method for recommending items for real-name authentication of natural person users according to claim 1, wherein the recommended item ordering filtering is specifically as follows:
Acquiring service handling data through a shared data platform;
obtaining an applicant transaction list through service transaction data;
performing necklace analysis and screening through the applicant transaction list;
acquiring a transaction sequence chain; logging in the real-name authentication natural person user at the same time to obtain a service list which is transacted by the real-name authentication natural person user;
Performing item sequence comparison according to the item sequence chain and the business list transacted by the name authentication natural person user, and acquiring a lower link item list;
Comparing the natural human features with the features of the item crowd in the item list, and removing items with low matching degree;
And acquiring a name authentication natural person user item recommendation list.
5. A computer-readable storage medium, in which a computer program is stored, the computer program being executable by a processor to implement the item recommendation method of real-name authentication of natural human users as claimed in any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110785193.6A CN113672800B (en) | 2021-07-12 | 2021-07-12 | Item recommendation method and storage medium for real-name authentication of natural person user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110785193.6A CN113672800B (en) | 2021-07-12 | 2021-07-12 | Item recommendation method and storage medium for real-name authentication of natural person user |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113672800A CN113672800A (en) | 2021-11-19 |
| CN113672800B true CN113672800B (en) | 2024-09-06 |
Family
ID=78538865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110785193.6A Active CN113672800B (en) | 2021-07-12 | 2021-07-12 | Item recommendation method and storage medium for real-name authentication of natural person user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113672800B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245301A (en) * | 2018-11-29 | 2019-09-17 | 腾讯科技（深圳）有限公司 | A kind of recommended method, device and storage medium |
| KR102171103B1 (en) * | 2019-06-03 | 2020-10-28 | 신한대학교 산학협력단 | Apparatus for Matching Person Service based on Social Network Service and Driving Method Thereof |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002288330A (en) * | 2001-03-28 | 2002-10-04 | Casio Comput Co Ltd | Method, device and program for providing consultant service |
| US20090210475A1 (en) * | 2008-02-18 | 2009-08-20 | Motorola Inc. | Recommendation system and method of operation therefor |
| KR20130033505A (en) * | 2011-09-09 | 2013-04-04 | 유비벨록스(주) | System for providing user oriented recommendation service |
| US8843430B2 (en) * | 2011-10-20 | 2014-09-23 | Comcast Cable Communications, Llc | Recommendation system |
| CN103824179A (en) * | 2014-02-21 | 2014-05-28 | 联想(北京)有限公司 | Information processing method and information processing device |
| JP5986129B2 (en) * | 2014-03-18 | 2016-09-06 | Ｎｅｃプラットフォームズ株式会社 | RECOMMENDATION INFORMATION DISTRIBUTION DEVICE, RECOMMENDATION INFORMATION DISTRIBUTION SYSTEM, RECOMMENDATION INFORMATION DISTRIBUTION METHOD, AND RECOMMENDATION INFORMATION DISTRIBUTION PROGRAM |
| EP3119094A1 (en) * | 2015-07-17 | 2017-01-18 | Thomson Licensing | Methods and systems for clustering-based recommendations |
| CN108304435B (en) * | 2017-09-08 | 2020-08-25 | 腾讯科技（深圳）有限公司 | Information recommendation method and device, computer equipment and storage medium |
| CN108846641A (en) * | 2018-06-21 | 2018-11-20 | 甘肃万维信息技术有限责任公司 | A kind of method and system of government affairs service item distribution |
| CN109885770B (en) * | 2019-02-20 | 2022-01-07 | 杭州威佩网络科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN112528130A (en) * | 2019-09-02 | 2021-03-19 | 中国移动通信有限公司研究院 | Information recommendation method, device, equipment and computer readable storage medium |
| CN111444424A (en) * | 2020-03-25 | 2020-07-24 | 深圳市分期乐网络科技有限公司 | Information recommendation method and information recommendation system |
| CN112632405B (en) * | 2020-12-31 | 2024-05-10 | 数字广东网络建设有限公司 | Recommendation method, recommendation device, recommendation equipment and storage medium |
-
2021
- 2021-07-12 CN CN202110785193.6A patent/CN113672800B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245301A (en) * | 2018-11-29 | 2019-09-17 | 腾讯科技（深圳）有限公司 | A kind of recommended method, device and storage medium |
| KR102171103B1 (en) * | 2019-06-03 | 2020-10-28 | 신한대학교 산학협력단 | Apparatus for Matching Person Service based on Social Network Service and Driving Method Thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113672800A (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200050968A1 (en) | Interactive interfaces for machine learning model evaluations | |
| CN109345399B (en) | Method, device, computer equipment and storage medium for evaluating risk of claim settlement | |
| CN105447184B (en) | Information extraction method and device | |
| US20170235820A1 (en) | System and engine for seeded clustering of news events | |
| CN107862022B (en) | Culture resource recommendation system | |
| CN112632405B (en) | Recommendation method, recommendation device, recommendation equipment and storage medium | |
| CN109255000B (en) | Dimension management method and device for label data | |
| CN112148843B (en) | Text processing method and device, terminal equipment and storage medium | |
| US9069880B2 (en) | Prediction and isolation of patterns across datasets | |
| CN104361102A (en) | Expert recommendation method and system based on group matching | |
| CN108153824A (en) | The determining method and device of targeted user population | |
| WO2018011895A1 (en) | Data processing flow management system and method | |
| CN112269805A (en) | Data processing method, device, equipment and medium | |
| CN113722611A (en) | Method, device and equipment for recommending government affair service and computer readable storage medium | |
| US11836331B2 (en) | Mathematical models of graphical user interfaces | |
| CN107977678A (en) | Method and apparatus for output information | |
| CN111310032A (en) | Resource recommendation method and device, computer equipment and readable storage medium | |
| CN111447575A (en) | Short message pushing method, device, equipment and storage medium | |
| CN116610853A (en) | Search recommendation method, search recommendation system, computer device, and storage medium | |
| CN111383072A (en) | User credit scoring method, storage medium and server | |
| CN109902129A (en) | Insurance agent's classifying method and relevant device based on big data analysis | |
| CN115204881A (en) | Data processing method, device, equipment and storage medium | |
| CN107766537A (en) | A kind of position search ordering method and computing device | |
| JP6031165B1 (en) | Promising customer prediction apparatus, promising customer prediction method, and promising customer prediction program | |
| Wu et al. | Event evolution model based on random walk model with hot topic extraction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |