Fuzzy screening method and system for housing public accumulation fund house purchase address

Abstract

The invention provides a fuzzy screening method and system for house buying addresses of housing accumulation fund, and the method is applied to a server, and comprises the steps: receiving house buying application information sent by a client; detecting the house purchase application information to obtain house address information; extracting from the converted house address information to obtain pure digital information; collecting historical extraction data of the public accumulation fund house purchase class; splitting the house address information to obtain plain text information, and taking the plain text information as a fuzzy query condition; according to the fuzzy query condition, the pure digital information and the query time range, historical extraction data of the public accumulation fund house purchase class is retrieved; if it is screened that similar house purchase extraction records exist in the historical house purchase extraction information and the number of the records exceeds a preset threshold value, the house purchase application information is marked; the matching degree of query results can be effectively improved, the risk prevention and control awareness is improved, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a fuzzy screening method and system for housing provident fund house purchase addresses. Background Art

[0002] In recent years, with the widespread application of information technology in different industries and fields, the amount of information has shown explosive growth, and the withdrawal business volume of provident fund centers has gradually increased. Provident fund centers have also continuously introduced service requirements to increase risk prevention and control, aiming to improve the service quality for depositors when handling provident fund withdrawal business. At the same time, it is necessary to enhance risk prevention and control awareness for related housing purchase withdrawal business when handling withdrawal business approval, so as to avoid excessive withdrawals and fraudulent withdrawals.

[0003] At present, the Housing Provident Fund Center provides multiple channels for housing purchase withdrawal applications, and the detection of housing addresses is still based on the traditional database fuzzy query method. The main shortcomings include: non-standard housing address entry format; low database query result recognition; poor user experience. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a fuzzy screening method and system for housing provident fund house purchase addresses, which can effectively improve the matching degree of query results, enhance risk prevention and control awareness, and increase user experience.

[0005] In a first aspect, an embodiment of the present invention provides a fuzzy screening method for a housing provident fund purchase address, which is applied to a server, and the method includes: Receive the house purchase application information sent by the client; Detecting the house purchase application information to obtain house address information; Different processing strategies are used to process the house address information according to its attributes to obtain converted house address information; Extracting from the converted house address information to obtain pure digital information; Collect historical extraction data of housing provident fund house purchases, the historical extraction data including the query time range and the preset threshold value of house duplication check; Splitting the house address information to obtain plain text information, and using the plain text information as a fuzzy query condition; According to the fuzzy query condition, the pure digital information and the query time range, the historical extracted data of the housing provident fund house purchase category is retrieved; If similar home purchase withdrawal records are found in the historical home purchase withdrawal information, and the number of records exceeds a preset threshold, the home purchase application information will be marked.

[0006] Furthermore, the house address information is split to obtain pure text information, including: The position of the first number appearing in the house address information is taken as a node; Splitting the house address information into a first part and a second part according to the node; The first part is used as the plain text information.

[0007] Furthermore, the converted house address information is extracted to obtain pure digital information, including: The numbers included in the converted house address information are extracted in the order in which they appear in the converted house address information to obtain the pure digital information.

[0008] Further, different processing strategies are adopted according to the attributes of the house address information to obtain the converted house address information, including: When the house address information is street name information, a text preprocessing module in the NLP technology is used to automatically identify and remove redundant spaces, punctuation marks and special characters in the street name information; The removed street name information is converted into a uniform case format through a text standardization function in the NLP technology; When the street name information is an abbreviation or a variant, converting the street name information into a standard form by a morphological restoration module in the NLP technology; or, Calculate the edit distance between the input house address information and the standard house address information in the database using the Levenshtein distance algorithm; Calculating similarity based on the edit distance; When the similarity is greater than a preset threshold, the input house address information matches the standard house address information successfully, and the house address information is converted into a full string to obtain the converted house address information; or, Constructing a standard dictionary library, and detecting the house address information through the standard dictionary library; When it is detected that the house address information is wrong, the standard dictionary library provides correct house address information; The correct house address information is converted into a full character string to obtain the converted house address information.

[0009] Furthermore, the method further comprises: If no similar home purchase withdrawal record is found in the historical home purchase withdrawal information, the home purchase application information will not be marked.

[0010] Furthermore, the method further comprises: When the reviewer reviews the housing purchase application information, the server automatically determines whether the housing purchase application information has a mark; If it exists, a prompt box will pop up.

[0011] Furthermore, the historical extraction data also includes applicant information, extraction time, approver information, extraction amount, whether the matter is valid and the house address information.

[0012] In a second aspect, an embodiment of the present invention provides a fuzzy screening system for housing provident fund purchase addresses, which is applied to a server, and the system includes: The receiving module is used to receive the house purchase application information sent by the client; A detection module, used to detect the house purchase application information and obtain the house address information; A conversion module, used for converting the house address information into a full string to obtain converted house address information; An extraction module, used for extracting from the converted house address information to obtain pure digital information; A collection module, used to collect historical extraction data of housing purchases with provident funds, wherein the historical extraction data includes a query time range and a preset threshold for house duplication checking; A splitting module, used for splitting the house address information to obtain pure text information, and using the pure text information as a fuzzy query condition; A retrieval module, for retrieving the historical extracted data of the housing purchase category of the provident fund according to the fuzzy query condition, the pure digital information and the query time range; The marking module is used to mark the house purchase application information when similar house purchase extraction records are found in the historical house purchase extraction information and the number of records exceeds a preset threshold.

[0013] Furthermore, the splitting module is specifically used for: The position of the first number appearing in the house address information is taken as a node; Splitting the house address information into a first part and a second part according to the node; The first part is used as the plain text information.

[0014] In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be executed on the processor, and when the processor executes the computer program, the fuzzy screening method for housing provident fund purchase addresses as described above is implemented.

[0015] In a fourth aspect, an embodiment of the present invention provides a computer-readable medium having a non-volatile program code executable by a processor, wherein the program code enables the processor to execute the fuzzy screening method for housing provident fund housing purchase addresses as described above.

[0016] The embodiment of the present invention provides a fuzzy screening method and system for housing provident fund house purchase addresses, which are applied to a server and include: receiving house purchase application information sent by a client; detecting the house purchase application information to obtain house address information; extracting from the converted house address information to obtain pure digital information; collecting historical extraction data of provident fund house purchases, the historical extraction data including the query time range and a preset threshold for house duplicate checking; splitting the house address information to obtain pure text information, and using the pure text information as a fuzzy query condition; searching the historical extraction data of provident fund house purchases according to the fuzzy query condition, the pure digital information and the query time range; marking the house purchase application information if similar house purchase extraction records are found in the historical house purchase extraction information and the number of records exceeds the preset threshold; the matching degree of the query results can be effectively improved, the risk prevention and control awareness can be improved, and the user experience can be increased.

[0017] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0018] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A flow chart of a fuzzy screening method for housing provident fund purchase addresses provided in the first embodiment of the present invention; Figure 2 A schematic diagram of a fuzzy screening system for housing provident fund housing purchase addresses provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] To facilitate understanding of this embodiment, the embodiment of the present invention is described in detail below.

[0023] Embodiment 1: Figure 1 This is a flow chart of the fuzzy screening method for housing provident fund house purchase addresses provided in the first embodiment of the present invention.

[0024] Reference Figure 1 , applied to a server, the method comprises the following steps: Step S101, receiving housing purchase application information sent by the client; Step S102, detecting the house purchase application information to obtain the house address information; Step S103, using different processing strategies to process the house address information according to its attributes to obtain converted house address information; Here, considering that the housing purchase application information submitted by users comes from different channels and the input standards are uneven, the house address information is converted from a full-width string to a half-width string to obtain the converted house address information.

[0025] Step S104, extracting from the converted house address information to obtain pure digital information; Step S105, collecting historical extraction data of housing purchases with provident funds, the historical extraction data including the query time range and the preset threshold for house duplication check; wherein the historical extraction data also includes applicant information, extraction time, approver information, extraction amount, whether the matter is valid and house address information; Step S106, splitting the house address information to obtain pure text information, and using the pure text information as a fuzzy query condition; Step S107, searching historical extracted data of housing purchase with housing provident fund according to fuzzy query conditions, pure digital information and query time range; Specifically, the system uses the position of the first number in the house address information as a node, and splits the house address information into two parts according to the node. The first part is the pure text part, and the pure text part is used as the fuzzy query condition, and the extracted pure digital information and the query time range (the time dimension set by the parameter) are added to retrieve the historical data of housing purchases with provident funds.

[0026] Step S108: If similar house purchase extraction records are found in the historical house purchase extraction information, and the number of records exceeds a preset threshold, the house purchase application information is marked.

[0027] When applying for a withdrawal for a house purchase, the system automatically detects the house address information and processes it to reach the application approval. Then the system automatically prompts the approval personnel whether there is a withdrawal record for a similar house, reducing the approval personnel's manual query of the house address, which is conducive to the system's security, high performance, and high availability requirements, and is also conducive to showing customers the complete historical withdrawal records.

[0028] Further, step S106 includes the following steps: Step S201, taking the position of the first number appearing in the house address information as a node; Step S202, splitting the house address information into a first part and a second part according to the node; Step S203: treating the first part as pure text information.

[0029] Further, step S104 includes: The numbers included in the converted house address information are extracted in the order in which they appear in the converted house address information to obtain pure digital information.

[0030] Furthermore, the method further comprises the following steps: Step S301: If no similar house purchase extraction record is found in the historical house purchase extraction information, the house purchase application information will not be marked.

[0031] Furthermore, the method further comprises the following steps: Step S401, when the approver approves the housing purchase application information, the server automatically determines whether the housing purchase application information has a mark; Step S402: If it exists, a prompt box pops up.

[0032] Specifically, when the reviewer is reviewing the application information for purchasing a house, the server (system) automatically determines whether there is a mark on the application information for purchasing a house; if so, a prompt box will pop up to display similar house application records, assisting the operator in making the basis for approval, and can either reject the application or approve it.

[0033] This application is illustrated by the following information: A user submits a withdrawal for house purchase, and the house address information in the application information is: Room 203, Unit 4, Building 99, Wool Textile Factory Staff Quarters, Haidian District.

[0034] After receiving the application information, the system converts the house address information into half-width characters through the full character string, extracts 994203 from the house address, and saves it as a feature item of the house address.

[0035] The system reads the time range of 12 months and the threshold of house duplicate checking in the system parameters. The system intercepts the position of the first number in the house address information as a node to obtain "Haidian District Woolen Mill Family Building". Finally, the system uses "Haidian District Woolen Mill Family Building" as the fuzzy query condition of the database, plus the number contained in the address equals 994203, and adds the time dimension to screen the information extracted from the historical housing purchase of provident funds.

[0036] If the historical house purchase extraction records include "Building 99, Room 4-203, Wool Textile Factory Family Building, Haidian District", "Building 99#4, Floor 203, Wool Textile Factory Family Building, Haidian District" and "Building 99, Room 4, Door 203, Wool Textile Factory Family Building, Haidian District" the system will screen out 3 records and if they are greater than the preset threshold, the system will mark the application information, indicating that similar extraction records exist for the house.

[0037] Further, step S103 includes the following steps: Step S501, when the house address information is street name information, a text preprocessing module in the NLP technology is used to automatically identify and remove redundant spaces, punctuation marks and special characters in the street name information; Step S502, converting the removed street name information into a uniform case format through a text standardization function in NLP technology; for example, converting all to lowercase or capitalizing the first letter; Step S503, when the street name information is an abbreviation or a variant, converting the street name information into a standard form through a morphological restoration module in the NLP technology; or, Step S601, using the Levenshtein distance algorithm to calculate the edit distance between the input house address information and the standard house address information in the database; Step S602, calculating similarity according to the edit distance; Step S603, when the similarity is greater than a preset threshold, the input house address information matches the standard house address information successfully, and the house address information is converted into a full string to obtain the converted house address information; or, Step S701, constructing a standard dictionary library, and detecting the house address information through the standard dictionary library; Step S702, when it is detected that the house address information is wrong, the standard dictionary library provides the correct house address information; Here, when the standard dictionary library provides correct house address information, the user can select the correct house address information.

[0038] Step S703, converting the correct house address information into a full character string to obtain converted house address information.

[0039] This application converts the house address information, intelligently splits the house address information into two parts, uses pure text information as fuzzy query conditions, reads the time dimension and preset threshold of system parameters, and customizes combined query information, which can effectively improve the matching degree of query results, enhance risk prevention and control awareness, and increase user experience.

[0040] Embodiment 2: Figure 2 A schematic diagram of a fuzzy screening system for housing provident fund housing purchase addresses provided in the second embodiment of the present invention.

[0041] Reference Figure 2 , applied to a server, the system comprises: The receiving module is used to receive the house purchase application information sent by the client; A detection module is used to detect the house purchase application information and obtain the house address information; A conversion module, used to process the house address information using different processing strategies according to the attributes of the house address information to obtain converted house address information; An extraction module, used for extracting from the converted house address information to obtain pure digital information; The collection module is used to collect historical data extracted from housing purchases with provident funds. The historical data includes the query time range and the preset threshold for house duplication checking. A splitting module is used to split the house address information to obtain pure text information, and use the pure text information as a fuzzy query condition; The retrieval module is used to retrieve historical data extracted from housing purchases with housing provident funds based on fuzzy query conditions, pure digital information, and the time range of the query; The marking module is used to mark the housing purchase application information when similar housing purchase extraction records are found in the historical housing purchase extraction information and the number of records exceeds a preset threshold.

[0042] Furthermore, the split module is specifically used for: The first number in the house address information is used as a node; Split the house address information into the first part and the second part according to the node; Treat the first part as a plain text message.

[0043] This application adopts a fuzzy screening algorithm. The main features of the fuzzy screening algorithm are: unified conversion of house address information, automatic splitting of house address information, extracting and saving the numbers in the house address information in sequence as feature items of the house address information, and increasing the query matching degree; flexibly customizing the time dimension and preset threshold through parameters, and dynamically controlling the fuzzy screening range; automatically providing historical extraction records of similar houses to assist operators in approval and improve user experience.

[0044] An embodiment of the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the fuzzy screening method for housing provident fund housing purchase addresses provided in the above embodiment are implemented.

[0045] An embodiment of the present invention also provides a computer-readable medium having a non-volatile program code executable by a processor, wherein a computer program is stored on the computer-readable medium, and when the computer program is executed by the processor, the steps of the fuzzy screening method for housing provident fund purchase addresses of the above embodiment are executed.

[0046] The computer program product provided in the embodiment of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method described in the previous method embodiment. The specific implementation can be found in the method embodiment and will not be repeated here.

[0047] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0048] In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0049] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0050] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0051] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A fuzzy screening method for housing provident fund purchase addresses, characterized in that: Applied to a server, the method comprises: Receive the house purchase application information sent by the client; Detecting the house purchase application information to obtain house address information; Different processing strategies are used to process the house address information according to its attributes to obtain converted house address information; Extracting from the converted house address information to obtain pure digital information; Collect historical extraction data of housing provident fund house purchases, the historical extraction data including the query time range and the preset threshold value of house duplication check; Splitting the house address information to obtain plain text information, and using the plain text information as a fuzzy query condition; According to the fuzzy query condition, the pure digital information and the query time range, the historical extracted data of the housing provident fund house purchase category is retrieved; If similar home purchase extraction records are found in the historical home purchase extraction information, and the number of records exceeds the preset threshold, the home purchase application information will be marked.

2. The fuzzy screening method for housing provident fund house purchase address according to claim 1 is characterized in that: The house address information is split to obtain pure text information, including: The position of the first number appearing in the house address information is taken as a node; Splitting the house address information into a first part and a second part according to the node; The first part is used as the plain text information.

3. The fuzzy screening method for housing provident fund purchase address according to claim 1 is characterized in that: Extract from the converted house address information to obtain pure digital information, including: The numbers included in the converted house address information are extracted in the order in which they appear in the converted house address information to obtain the pure digital information.

4. The fuzzy screening method for housing provident fund house purchase address according to claim 1 is characterized in that: Different processing strategies are used according to the attributes of the house address information to obtain converted house address information, including: When the house address information is street name information, a text preprocessing module in the NLP technology is used to automatically identify and remove redundant spaces, punctuation marks and special characters in the street name information; The removed street name information is converted into a uniform case format through a text standardization function in the NLP technology; When the street name information is an abbreviation or a variant, converting the street name information into a standard form by a morphological restoration module in the NLP technology; or, Calculate the edit distance between the input house address information and the standard house address information in the database using the Levenshtein distance algorithm; Calculating similarity based on the edit distance; When the similarity is greater than a preset threshold, the input house address information matches the standard house address information successfully, and the house address information is converted into a full string to obtain the converted house address information; or, Constructing a standard dictionary library, and detecting the house address information through the standard dictionary library; When it is detected that the house address information is wrong, the standard dictionary library provides correct house address information; The correct house address information is converted into a full character string to obtain the converted house address information.

5. The fuzzy screening method for housing provident fund house purchase address according to claim 1 is characterized in that: The method further comprises: If no similar home purchase withdrawal record is found in the historical home purchase withdrawal information, the home purchase application information will not be marked.

6. The fuzzy screening method for housing provident fund purchase address according to claim 1 is characterized in that: The method further comprises: When the reviewer reviews the housing purchase application information, the server automatically determines whether the housing purchase application information has a mark; If it exists, a prompt box will pop up.

7. The fuzzy screening method for housing provident fund house purchase address according to claim 1 is characterized in that: The historical extraction data also includes applicant information, extraction time, approver information, extraction amount, whether the matter is valid and the house address information.

8. A fuzzy screening system for housing provident fund purchase addresses, characterized in that: Applied to a server, the system comprises: The receiving module is used to receive the house purchase application information sent by the client; A detection module, used to detect the house purchase application information and obtain the house address information; A conversion module, used for processing the house address information using different processing strategies according to the attributes of the house address information to obtain converted house address information; An extraction module, used for extracting from the converted house address information to obtain pure digital information; A collection module, used to collect historical extraction data of housing purchases with provident funds, wherein the historical extraction data includes a query time range and a preset threshold for house duplication checking; A splitting module, used for splitting the house address information to obtain pure text information, and using the pure text information as a fuzzy query condition; A retrieval module, for retrieving the historical extracted data of the housing purchase category of the provident fund according to the fuzzy query condition, the pure digital information and the query time range; The marking module is used to mark the house purchase application information when similar house purchase extraction records are found in the historical house purchase extraction information and the number of records exceeds the preset threshold.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, wherein: When the processor executes the computer program, the fuzzy screening method for housing provident fund purchase addresses described in any one of claims 1 to 7 is implemented.

10. A computer readable medium having a non-volatile program code executable by a processor, characterized in that: The program code enables the processor to execute the fuzzy screening method for housing provident fund purchase address as described in any one of claims 1 to 7.

Images