CN115392603A - Target class object identification method and device, computer equipment and storage medium - Google Patents
Target class object identification method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115392603A CN115392603A CN202110570388.9A CN202110570388A CN115392603A CN 115392603 A CN115392603 A CN 115392603A CN 202110570388 A CN202110570388 A CN 202110570388A CN 115392603 A CN115392603 A CN 115392603A
- Authority
- CN
- China
- Prior art keywords
- order
- target
- group
- target class
- objects
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to a method and a device for identifying a target class object, computer equipment and a storage medium. The method comprises the following steps: dividing order objects of corresponding addresses belonging to the same area into the same group based on order objects corresponding to the target order to obtain a plurality of order object groups; respectively extracting a target class object and area information from each piece of target class information, and dividing the target class objects with the same area information into the same group to obtain a plurality of target class object groups; screening out order object groups to be matched and target class object groups to be matched which belong to the same region based on region information corresponding to each order object group and each target class object group respectively; and performing similarity matching on the order objects in the order object group to be matched and the target class objects in the target class object group to be matched, and judging whether the order objects are newly added target class objects or not according to a matching result. By the method, the efficiency of identifying the enterprise members is improved.
Description
Technical Field
The present application relates to the field of information processing technologies, and in particular, to a method and an apparatus for identifying a target class object, a computer device, and a storage medium.
Background
In the user service, taking the logistics service as an example, objects oriented to a logistics order may be divided into different categories, for example, may be divided into individual users and enterprise organization users, and the demands of different category objects for order service are different, so that a service provider may provide differentiated services for different objects to meet the service demands of each party.
However, in an actual application scenario, the service objects may submit orders with different identities, for example, an enterprise member user submits a logistics order for an enterprise on an individual name, at this time, the logistics service provider cannot provide services suitable for actual needs for the part of service objects, which results in low processing efficiency of the part of logistics order, and therefore, a method capable of identifying whether an object corresponding to an order is a target class object based on order information is urgently needed.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device, and a storage medium for identifying a target class object, which can effectively identify the target class object, in view of the above technical problems.
A method of identifying a target class object, the method comprising:
dividing order objects of which the addresses belong to the same area into the same group according to the area to which the addresses belong on the basis of order objects corresponding to a target order and the addresses corresponding to the order objects extracted from the target order to obtain a plurality of order object groups;
extracting the contained target category objects and the area information from each piece of acquired target category information respectively, and dividing the target category objects with the same area information into the same group to obtain a plurality of target category object groups;
based on the area information corresponding to each order object group and each target category object group, respectively screening out an order object group to be matched and a target category object group to be matched which belong to the same area from the plurality of order object groups and the plurality of target category object groups;
and performing similarity matching on the order objects in the order object group to be matched and the target class objects in the target class object group to be matched, and judging whether the order objects are newly added target class objects or not according to a matching result.
In one embodiment, the method further comprises:
carrying out object group matching on the order object group to be matched and the target class object group to be matched to obtain an object group matching result;
the similarity matching between the order object in the order object group to be matched and the target class object in the target class object group to be matched, and determining whether the order object is a newly added target class object according to a matching result includes:
and when the object group matching result meets the object group matching condition, performing similarity matching on the order object in the order object group to be matched and the target class object in the target class object group to be matched, and judging whether the order object is a newly added target class object according to the matching result.
In one embodiment, the performing object group matching on the order object group to be matched and the target category object group to be matched to obtain an object group matching result includes:
carrying out identification matching on the object identification in the order object group to be matched and the object identification in the target category object group to be matched, and determining an object identification group which is successfully matched;
when the object group matching result meets the object group matching condition, performing similarity matching on the order object in the order object group to be matched and the target class object in the target class object group to be matched, judging whether the order object is a newly added target class object according to the matching result, wherein the judging step comprises the following steps:
and when the number of the successfully matched object identification groups meets the number condition, performing similarity matching on the order object and the target class object corresponding to the successfully matched object identification groups, and judging whether the corresponding order object is a newly added target class object or not according to a matching result.
In one embodiment, the dividing the order objects of which the addresses belong to the same area into the same group according to the area to which the addresses belong to obtain a plurality of order object groups includes:
carrying out format standardization on the address, converting the obtained address data with the standardized format into longitude and latitude, and obtaining a plurality of area units obtained by carrying out unit division on a preset area according to the longitude and latitude;
and dividing the order objects corresponding to the addresses belonging to the same area unit into the same group according to the area unit to which the longitude and latitude corresponding to the address belong, so as to obtain a plurality of order object groups.
In one embodiment, the area of the plurality of zone units is equal.
In one embodiment, the extracting, from each piece of acquired object category information, an object category object and area information included in the piece of acquired object category information, and dividing object category objects having the same area information into the same group to obtain a plurality of object category object groups includes:
extracting a target category object and a target category code contained in each piece of acquired target category information respectively;
extracting a region code from the target category code based on the position of the region code in the target category code;
and dividing the target class objects with the same region codes into the same group to obtain a plurality of target class object groups.
In one embodiment, the method further comprises:
constructing a new target class object table according to the object information corresponding to the new target class object;
matching the object information in the newly added target class object table with the acquired target class object sample data, and counting the number of newly added target class objects which fail to be matched in the newly added target class object table;
and judging the availability of the newly added target class object table according to the proportion of the number of the newly added target class objects which fail to be matched to the total number of the newly added target class objects in the newly added target class object table.
An apparatus for identifying an object of a target class, the apparatus comprising:
the order object group building module is used for dividing order objects of which the addresses belong to the same area into the same group according to the area to which the addresses belong on the basis of order objects corresponding to target orders and the addresses, extracted from the target orders, corresponding to the order objects, so as to obtain a plurality of order object groups;
the target category object group building module is used for respectively extracting the contained target category objects and the area information from each piece of acquired target category information, and dividing the target category objects with the same area information into the same group to obtain a plurality of target category object groups;
the object group screening module is used for screening out order object groups to be matched and target class object groups to be matched which belong to the same area from the plurality of order object groups and the plurality of target class object groups respectively based on area information corresponding to each order object group and each target class object group respectively;
and the object matching module is used for performing similarity matching on the order objects in the order object group to be matched and the target class objects in the target class object group to be matched, and judging whether the order objects are the newly added target class objects or not according to a matching result.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
dividing order objects with the addresses belonging to the same area into the same group according to the area to which the addresses belong on the basis of order objects corresponding to target orders and the addresses extracted from the target orders and corresponding to the order objects, and obtaining a plurality of order object groups;
extracting the contained target category objects and the area information from each piece of acquired target category information respectively, and dividing the target category objects with the same area information into the same group to obtain a plurality of target category object groups;
based on the area information corresponding to each order object group and each target class object group, respectively screening out an order object group to be matched and a target class object group to be matched which belong to the same area from the plurality of order object groups and the plurality of target class object groups;
and performing similarity matching on the order objects in the order object group to be matched and the target class objects in the target class object group to be matched, and judging whether the order objects are newly added target class objects or not according to a matching result.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
dividing order objects with the addresses belonging to the same area into the same group according to the area to which the addresses belong on the basis of order objects corresponding to target orders and the addresses extracted from the target orders and corresponding to the order objects, and obtaining a plurality of order object groups;
extracting the contained target category objects and the area information from each piece of acquired target category information respectively, and dividing the target category objects with the same area information into the same group to obtain a plurality of target category object groups;
based on the area information corresponding to each order object group and each target class object group, respectively screening out an order object group to be matched and a target class object group to be matched which belong to the same area from the plurality of order object groups and the plurality of target class object groups;
and performing similarity matching on the order objects in the order object group to be matched and the target class objects in the target class object group to be matched, and judging whether the order objects are newly added target class objects or not according to a matching result.
The method, the device, the computer equipment and the storage medium for identifying the target class object divide the order objects with the addresses belonging to the same area into the same group according to the area to which the addresses belong on the basis of the order object corresponding to the target order and the address extracted from the target order and corresponding to the order object, so as to obtain a plurality of order object groups; the method comprises the steps of extracting object class objects and area information contained in each piece of acquired object class information respectively, dividing the object class objects with the same area information into the same group to obtain a plurality of object class object groups, grouping order objects and object class objects according to areas respectively, and screening out order object groups to be matched and object class object groups to be matched which belong to the same area from the plurality of order object groups and the plurality of object class object groups respectively on the basis of the area information corresponding to each order object group and each object class object group respectively; and performing similarity matching on the order objects in the order object group to be matched and the target class objects in the target class object group to be matched, and judging whether the order objects are newly added target class objects or not according to a matching result. The order information and the target category information are used as a basis, and the relation between the order object and the corresponding area of the target category object is utilized to judge whether the order object in the order information is a newly added target category object, so that the efficiency of identifying the target category object is improved.
Drawings
FIG. 1 is a diagram of an application environment of a method for identifying an object of a target class in one embodiment;
FIG. 2 is a flow diagram illustrating a method for identifying object class objects in one embodiment;
FIG. 3 is a flowchart illustrating a method for identifying an object of the object class according to another embodiment;
FIG. 4 is a flowchart illustrating a method for identifying an object of a target class in accordance with yet another embodiment;
FIG. 5 is a flowchart illustrating a method for identifying an object of the object class according to another embodiment;
FIG. 6 is a flowchart illustrating a method for identifying an object of the object class according to still another embodiment;
FIG. 7 is a block diagram of an apparatus for identifying a target class object in one embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The method for identifying the target class object can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The server 104 divides the order objects with the addresses belonging to the same area into the same group according to the area to which the addresses belong based on the order object corresponding to the target order provided by the terminal 102 and the address corresponding to the order object extracted from the target order, so as to obtain a plurality of order object groups; the server 104 extracts the object class objects and the area information contained in each piece of acquired object class information, and divides the object class objects with the same area information into the same group to obtain a plurality of object class object groups; the server 104 screens out order object groups to be matched and target class object groups to be matched which belong to the same region from the plurality of order object groups and the plurality of target class object groups respectively based on the region information corresponding to each order object group and each target class object group respectively; the server 104 performs similarity matching between the order objects in the order object group to be matched and the target class objects in the target class object group to be matched, determines whether the order objects are newly added target class objects according to the matching result, and feeds the determination result back to the terminal 102.
The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a method for identifying an object of a target category is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
The target order may be an order whose order object needs to be determined whether or not it belongs to the target category object. The target class is a class in which the order service provider provides a specified service for the service object. The server stores a target category object set formed by order objects corresponding to the target category orders, and is used for recording the order objects belonging to the target category objects, it should be noted that, based on the identification method of the target category objects, it may be determined whether the order objects not belonging to the target category object set corresponding to the target orders belong to newly added target category objects. For convenience of description, the following embodiments describe the method for identifying the target category object by taking the order object of the target order as an individual user, the target category as an enterprise, and the target category object of the target category as an enterprise user. It will be appreciated that in other embodiments, the order object and the target category object may be of other categories as well.
The order information of the individual user order may be information containing characteristics of the individual user subjected to an encryption process and a desensitization process. The personal user order information comprises user information and article information; for example, the user information in the take-away order may be the name, telephone, delivery address of the take-away person, etc., and the article information may be the name, quantity, price, etc. of the specific take-away food; the user information in the logistics order can be the name, telephone, address, etc. of the receiving/sending person, and the item information can be the name, quantity, weight, etc. of the specific receiving/sending item.
Taking a logistics order as an example, the order object corresponding to the target order comprises a receiver and a sender, and the address corresponding to the order object extracted from the target order comprises a receiver address corresponding to the receiver and a sender address corresponding to the sender. It should be noted that the recipient and the recipient address in the same order belong to the same group of user information, and the sender name and the sender address belong to another group of user information.
Further, according to the area to which the address belongs, the order objects of which the addresses belong to the same area are divided into the same group, and a plurality of order object groups are obtained.
The area may be a geographic unit obtained by dividing a preset area formed by a certain range according to address and location in advance, specifically, the area may be an administrative district, a street area, a community jurisdiction area, or a latitude and longitude limited area, and the preset area may be determined according to an approximate area range where enterprise members needing to be identified are located.
In an embodiment, the geographic units obtained by the division may be equal in size or different in size, and the division of the geographic units should be as small as possible, so that order information is conveniently aggregated according to a user address, and a corresponding enterprise user in the geographic unit is judged. If the preset area is an administrative area, the area unit may be an area formed between streets, or an office building or an industrial garden.
In a specific application, according to the characteristics of the preset area and the registered address or actual operation address of the enterprises in the area, the preset area is divided into area units which are as small as possible and are independent as possible among the enterprises, such as a certain office building or a certain technology park. And dividing all the user information corresponding to the same area into the same group according to the user address to obtain a plurality of user information groups.
The number of pieces of target category information acquired by the server may be plural, and the target category information may be acquired from a publishing system that specifies category information. The object category object refers to an object described in the object category information, which is capable of generating an order transaction with an order service provider in a different identity. Such as a member of the enterprise that generates order transactions with order service providers in personal and member identities.
Taking the target category information as the enterprise business information as an example, the enterprise business information refers to registration and operation information about the enterprise, which can be acquired from the open system, and includes enterprise annual newspaper, enterprise news, enterprise credit information, enterprise directory, stockholder information and the like. The company name, the enterprise code (such as a unified social credit code), the address of the enterprise, the names, positions, and contact addresses of the members of the enterprise can be identified from the enterprise business information.
Because a plurality of enterprise members may be included in the same enterprise, and the goal of the scheme is to identify the enterprise members, in order to ensure the accuracy in the information processing process, the information of the enterprise members corresponding to each enterprise member included in the enterprise business information is determined respectively. For example, if a certain enterprise business information includes a president a, a chief manager B, and a business department supervisor C, corresponding enterprise member information is respectively established for the president a, the chief manager B, and the business department supervisor C, where the enterprise member information corresponding to the president a, the chief manager B, and the business department supervisor C may have the same enterprise code and the same enterprise address, but the names of the enterprise members are different.
In a specific application, the server divides enterprise member information with the same area information into the same group based on the area information carried in the target category information, and obtains an enterprise member information table including a plurality of enterprise member information groups.
Specifically, the enterprise business information includes an enterprise code, which is an example of a unified social credit code, which is an "identification number" of a legal person and other organizations. For example, the standard stipulates that the unified social credit code is represented by 18-digit arabic numerals or capital english letters, and is a 1-digit registration management department code, a 1-digit mechanism category code, a 6-digit registration management organization administration division code, a 9-digit body identification code, and a 1-digit check code. The region information carried by the enterprise code can be a 6-bit registration management authority administrative division code, and the enterprise member information with the same region information is divided into the same group, so that the enterprise member information with the same registration management authority administrative division code is classified, and an enterprise member information table comprising a plurality of enterprise member information groups is obtained.
And step 206, screening out order object groups to be matched and target category object groups to be matched which belong to the same area from the plurality of order object groups and the plurality of target category object groups respectively based on the area information corresponding to each order object group and each target category object group respectively.
The area information corresponding to the order object group is area information of a common area to which an address corresponding to an order object in the order object group belongs. The area information corresponding to the target category object group is area information corresponding to the target category object in the target category object group. The order object group to be matched and the target class object group to be matched which belong to the same region refer to an order object group and a target class object group having the same region information.
The areas corresponding to the order object group and the object type object group may be areas divided based on longitude and latitude, areas divided based on administrative areas, or areas defined in other manners, as long as the same area division standard is used for the areas corresponding to the order objects in the order object group and the areas corresponding to the object type objects in the object type object group.
And 208, performing similarity matching on the order objects in the order object group to be matched and the target class objects in the target class object group to be matched, and judging whether the order objects are newly added target class objects according to a matching result.
Specifically, the similarity comparison between the order object and the target category object may be performed from multiple angles, for example, the same type of information content in the order object and the target category object, and for example, the number of objects with the same name in the order object group to be matched and the target category object group to be matched.
In a specific application, the server can screen out user information corresponding to the user address and enterprise member information corresponding to the enterprise through the user address and the enterprise which belong to the same region, and judge whether the user corresponding to the user information is a new enterprise member or not by comparing the similarity of the user information and the enterprise member information.
The method for identifying the target class object divides the order objects with the addresses belonging to the same area into the same group according to the area to which the addresses belong on the basis of the order object corresponding to the target order and the address corresponding to the order object extracted from the target order, so as to obtain a plurality of order object groups; the method comprises the steps of extracting object class objects and area information contained in each piece of acquired object class information respectively, dividing the object class objects with the same area information into the same group to obtain a plurality of object class object groups, grouping order objects and object class objects according to areas respectively, and screening out order object groups to be matched and object class object groups to be matched which belong to the same area from the plurality of order object groups and the plurality of object class object groups respectively on the basis of the area information corresponding to each order object group and each object class object group respectively; and performing similarity matching on the order objects in the order object group to be matched and the target class objects in the target class object group to be matched, and judging whether the order objects are newly added target class objects or not according to a matching result. The order information and the target category information are used as a basis, and the relation between the order object and the corresponding area of the target category object is utilized to judge whether the order object in the order information is a newly added target category object, so that the efficiency of identifying the target category object is improved.
In one embodiment, the method further comprises: carrying out object group matching on the order object group to be matched and the target class object group to be matched to obtain an object group matching result;
similarity matching is carried out on the order objects in the order object group to be matched and the target class objects in the target class object group to be matched, and whether the order objects are newly added target class objects or not is judged according to a matching result, wherein the similarity matching comprises the following steps:
and when the object group matching result meets the object group matching condition, performing similarity matching on the order object in the order object group to be matched and the target class object in the target class object group to be matched, and judging whether the order object is a newly added target class object according to the matching result.
The object group matching may be to perform identifier matching on an object identifier in the order object group to be matched and an object identifier in the target category object group to be matched, and determine an object identifier group with successful matching.
In this embodiment, matching is performed according to the object group, object matching is further performed when the object group matching result meets the object group matching condition, and whether the order object is a newly added object type object is determined by setting a plurality of conditions, so that the accuracy of the determination result is improved.
In one particular application, the plurality of user information sets form a user information table and the plurality of enterprise membership information sets form an enterprise membership information table. And when the target user address and the target enterprise address which have the same area exist in the user information table and the enterprise member information table, the user information group where the target user address is located and the enterprise member information group where the target enterprise address is located accord with the information group matching condition, and the user information corresponding to the target user address and the enterprise member information corresponding to the target enterprise address accord with the information matching condition, determining the user corresponding to the user information corresponding to the target user address as a newly-added enterprise member.
Judging whether a user is a newly added enterprise member, wherein a plurality of conditions are required to be met, a first condition is that a target user address and a target enterprise address with the same area exist in a user information table and an enterprise member information table, a second condition is that a user information group where the target user address is located and an enterprise member information group where the target enterprise address is located accord with an information group matching condition, wherein the information group matching condition can be that the user and the enterprise member have at least two pairs of same names or contact modes or other unique identity information, and a third condition is that user information corresponding to the target user address and enterprise member information corresponding to the target enterprise address accord with an information matching condition, wherein the information matching condition can be that the user information and the same type of information content in the enterprise member information are the same or the similarity meets a similarity threshold value. It should be noted that, if the above three conditions are simultaneously satisfied, that is, the user is regarded as a new member of the enterprise, and if any one of the conditions is not satisfied, the user is regarded as not a new member of the enterprise.
In the embodiment, whether the user is a new enterprise member is judged by setting a plurality of conditions, so that the accuracy of the judgment result is improved.
It should be noted that the above conditions may be sequentially determined according to a sequential order, or may be determined synchronously, for example, whether the three conditions are satisfied is determined according to the order of the first condition, the second condition, and the third condition, respectively, and if the first condition is not satisfied, the second condition and the third condition are not determined. In another embodiment, two of the plurality of conditions may be judged in synchronization, for example, the second condition and the third condition are judged in synchronization.
In one embodiment, the object group matching of the order object group to be matched and the object class object group to be matched to obtain an object group matching result includes: carrying out identification matching on the object identification in the order object group to be matched and the object identification in the target category object group to be matched, and determining an object identification group which is successfully matched;
when the object group matching result meets the object group matching condition, performing similarity matching between the order object in the order object group to be matched and the target class object in the target class object group to be matched, and judging whether the order object is a newly added target class object according to the matching result, wherein the method comprises the following steps: and when the number of the successfully matched object identification groups meets the number condition, performing similarity matching on the order object and the target class object corresponding to the successfully matched object identification groups, and judging whether the corresponding order object is the newly added target class object or not according to a matching result.
In a specific application, when the server detects that the target user address and the target enterprise address in the same area exist in the user information table and the enterprise member information table, the server obtains the user name in the user information group where the target user address is located and the enterprise member name in the enterprise member information group where the target enterprise address is located. When at least two pairs of users and enterprise members with the same name exist in the user information group where the target user address is located and the enterprise member information group where the target enterprise address is located, extracting the user information corresponding to the target user address and the enterprise member information corresponding to the target enterprise address. And calculating the similarity between the user information corresponding to the target user address and the enterprise member information corresponding to the target enterprise address, and determining the user corresponding to the user information corresponding to the target user address as a newly-added enterprise member when the similarity meets a preset similarity condition.
In one embodiment, based on the order object corresponding to the target order and the address extracted from the target order and corresponding to the order object, the order objects having the addresses in the same area are divided into the same group according to the area to which the address belongs, so as to obtain a plurality of order object groups, that is, step 202 includes steps 302 to 306.
and step 304, carrying out format standardization on the address, converting the obtained address data with the standardized format into longitude and latitude, and obtaining a plurality of area units obtained by dividing the preset area according to the longitude and latitude.
And step 306, dividing the order objects corresponding to the addresses belonging to the same area unit into the same group according to the area unit to which the longitude and latitude corresponding to the address belong, so as to obtain a plurality of order object groups.
Specifically, the address data in the standardized format is a result of standardizing the address in the same format, for example, expressed in a standardized manner in a province-city-district-street-cell manner or the like. The longitude and latitude information can realize the unification of data display forms corresponding to the addresses, and the area units to which the addresses belong can be accurately determined through the unified longitude and latitude information.
In one embodiment, the object category objects and the area information included in each piece of acquired object category information are extracted respectively, the object category objects with the same area information are divided into the same group, so as to obtain a plurality of object category object groups, and step 204 includes steps 402 to 406.
The object category code may be an enterprise code in the enterprise business information, the position of the area code in the enterprise code is fixed, and the area code is extracted from the enterprise code based on the position of the area code in the enterprise code. And dividing the same enterprise member information with the same area code into the same group to obtain an enterprise member information table comprising a plurality of enterprise member information groups.
Taking enterprise codes as unified social credit codes as an example, the unified social credit codes are 18 digits, are represented by Arabic numerals or English letters, and are composed of five parts, wherein the first part (1 st digit) is a registration management department code, the second part (2 nd digit) is a taxpayer category code of an enterprise and the like, the third part (3 rd to 8 th digits) is a registration management authority administrative division code, the fourth part (9 th to 17 th digits) is a main body identification code, and the fifth part (18 th digit) is a check code, and is automatically generated by the system.
In this embodiment, according to the positions of the area codes in the enterprise code, which are 3 rd to 8 th, the area codes are obtained by extracting the 3 rd to 8 th positions of the unified social credit code, and then the enterprise member information with the same area codes is divided into the same group and corresponds to one enterprise member information group, so that an enterprise member information table including a plurality of enterprise member information groups is obtained.
In one embodiment, the method for identifying the target class object further includes steps 502 to 506.
In a specific application, the server constructs a new enterprise member table according to user information and enterprise member information corresponding to the new enterprise members, matches the new enterprise member table with the acquired enterprise member information sample data, counts the number of new enterprise member information which fails to be matched in the new enterprise member table, and judges the availability of the new enterprise member table according to the proportion of the number of the new enterprise member information which fails to be matched to the total number of the new enterprise member information in the new enterprise member table.
The information type of the enterprise member information sample data comprises various information types in a newly added enterprise member table, for example, the newly added enterprise member table comprises a company name, a unified social credit code, a name, a position, a contact telephone and a registration address; the enterprise member information sample data includes company name, unified social credit code, name, job title, contact phone number, registered address and mailbox.
Comparing each piece of information in the newly added enterprise member table with information in the enterprise member information sample data one by one, and when all the information of one piece of data in the newly added enterprise member table can be completely matched with one piece of information in the information sample data of the enterprise member, determining that the piece of data in the newly added enterprise member table is correct; if any data is not matched, the data is considered to be incorrect; and counting the correct number and the incorrect number, calculating the proportion of the number of the incorrect new enterprise member information to the total number of the new enterprise member information in the new enterprise member table to obtain the correct rate, if the correct rate is in a preset reasonable interval, judging that the new enterprise member table is available, otherwise, judging that the new enterprise member table is unavailable.
In order to facilitate understanding of the present application by those skilled in the art, another embodiment is provided below with reference to fig. 6 to describe the method for identifying the object class object of the present application, where the embodiment includes the following steps:
s1, names, telephones and addresses of waybill senders and consignors in a preset area range are extracted from a logistics waybill database.
S2, only keeping the complete name (name) and the telephone number (tel) with the correct digit for the name and the telephone extracted in the S1; and analyzing the address extracted in the S1, outputting an address (address) in a standardized format, and converting the address into longitude and latitude (gps).
S3, establishing a relational structure table a1 of name, tel, address and gps on the basis of the S1 and the S2; the logistics waybill database is personal user order information, the names, the telephones and the addresses of the senders and the senders respectively correspond to user names, user contact numbers and user addresses, and the relational structure table a1 can be a data form of the order information.
S4, dividing the preset area into a plurality of area units with the same area according to the longitude and latitude, and placing the data in the table a1 into the corresponding area units according to the corresponding relation of the longitude and latitude for grouping to obtain N groups b1, b2 and b3 … … bN; the N packets b1, b2, and b3 … … bN are a plurality of user information groups corresponding to a plurality of areas.
And S5, extracting the company name (company _ name), the unified social credit code (code), the name of the grand manager, the corresponding position information (position) and the company registration address from the public company information base. The unified social credit code (code), the high-authority name (name), and the enterprise registration address correspond to an enterprise code, an enterprise member name, and an enterprise address, respectively.
S6, analyzing the enterprise registration address extracted in the S5, outputting an address (reg _ address) in a standardized format, and converting the address into a longitude and latitude (gps);
s7, establishing a relational structure table a2 of company _ name, code, name, position, reg _ address and gps on the basis of S5 and S6;
s8, grouping the data in the a2 table according to the unified social credit codes to obtain N groups c1, c2, c3 … cN which correspond to N enterprise member information groups;
s9, comparing the address of the a1 table with the address of the a2 table, comparing all names of a bX group where the address X is located with all high-pipe names of a cX group where the reg _ address X is located when the address X and the reg _ address X belong to the same administrative region, and extracting the whole data of the a1 table corresponding to the address X and the whole data of the a2 table corresponding to the reg _ address X when 2 or more names are consistent in a certain X group;
s10, comprehensively evaluating the data of the a1 and a2 tables according to the name and the address based on the data extracted in the S9, comparing the similarity between the name and the address, and assigning values to the similarity;
s11, setting a similarity threshold, and when the similarity threshold is reached, considering that the data in the a1 table and the data in the a2 table are data of the same company and the same high-level management;
s12, taking the name + code as a main key for all the data reaching the threshold, and combining the data of the a1 table and the a2 table into a3 table, namely, company _ name, code, name, tel, position and reg _ address
S13, carrying out accuracy evaluation on the data of the a3 table, selecting a batch of known and correct sample data samples, wherein the data content comprises the information content of the a3 table, such as: company name, unified social credit code, name, job title, contact phone, and registration address;
s14, comparing the data in the a3 table with sample data samples one by one, and when all information of one piece of data can be completely matched with the sample data, considering that the piece of data is correct; if any data is not matched, the data is considered to be incorrect; counting the correct number and the incorrect number;
and S15, calculating the data accuracy of the a3 table, wherein the accuracy = the correct number/(the correct number + the incorrect number), and if the accuracy is in a reasonable interval, the data of the a3 table is considered to be available.
It should be understood that, although the various steps in the flowcharts related to the above embodiments are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in each flowchart related to the above embodiments may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
In one embodiment, as shown in fig. 7, there is provided an apparatus for identifying an object of a target category, including: an order object group construction module 702, a target category object group construction module 704, an object group screening module 706, and an object matching module 708, wherein:
the order object group construction module 702 is configured to divide, according to an area to which an address belongs, order objects having addresses that belong to the same area into the same group based on an order object corresponding to the target order and the address extracted from the target order and corresponding to the order object, so as to obtain a plurality of order object groups.
And the object class object group building module 704 is configured to extract the object class objects and the area information included in each piece of acquired object class information, and divide the object class objects with the same area information into the same group to obtain a plurality of object class object groups.
And an object group screening module 706, configured to screen out an order object group to be matched and an object class group to be matched, which belong to the same area, from the multiple order object groups and the multiple object class object groups, respectively, based on area information corresponding to each order object group and each object class object group.
And the object matching module 708 is configured to perform similarity matching between the order object in the order object group to be matched and the target class object in the target class object group to be matched, and determine whether the order object is a newly added target class object according to a matching result.
The identification device of the target class object divides the order objects with the addresses belonging to the same area into the same group according to the area to which the addresses belong on the basis of the order object corresponding to the target order and the address corresponding to the order object extracted from the target order, so as to obtain a plurality of order object groups; the method comprises the steps of extracting object class objects and area information contained in each piece of acquired object class information respectively, dividing the object class objects with the same area information into the same group to obtain a plurality of object class object groups, grouping order objects and object class objects according to areas respectively, and screening out order object groups to be matched and object class object groups to be matched which belong to the same area from the plurality of order object groups and the plurality of object class object groups respectively on the basis of the area information corresponding to each order object group and each object class object group respectively; and performing similarity matching on the order objects in the order object group to be matched and the target class objects in the target class object group to be matched, and judging whether the order objects are newly added target class objects or not according to a matching result. The order information and the target category information are used as a basis, and the relation between the order object and the corresponding area of the target category object is utilized to judge whether the order object in the order information is a newly added target category object, so that the efficiency of identifying the target category object is improved.
In one embodiment, the device for identifying the target class object further comprises an object group matching module, configured to perform object group matching on the order object group to be matched and the target class object group to be matched, so as to obtain an object group matching result;
and the object matching module is also used for matching the similarity of the order object in the order object group to be matched and the target class object in the target class object group to be matched when the object group matching result meets the object group matching condition, and judging whether the order object is a newly added target class object according to the matching result.
In one embodiment, the object group matching module is further configured to perform identifier matching on an object identifier in the order object group to be matched and an object identifier in the target category object group to be matched, and determine an object identifier group with successful matching; and the object matching module is also used for matching the similarity of the order object corresponding to the successfully matched object identification group and the target class object when the number of the successfully matched object identification group meets the number condition, and judging whether the corresponding order object is a newly added target class object according to the matching result.
In one embodiment, the order object group building module is further configured to standardize a format of an address, convert the obtained address data with the standardized format into latitude and longitude, and obtain a plurality of area units obtained by performing unit division on a preset area according to the latitude and longitude; and dividing the order objects corresponding to the addresses belonging to the same area unit into the same group according to the area unit to which the longitude and latitude corresponding to the address belong, so as to obtain a plurality of order object groups.
In one embodiment, the area of the plurality of zone units is equal.
In one embodiment, the object category object group building module is further configured to extract an object category object and an object category code included in each piece of acquired object category information; extracting the area code from the target category code based on the position of the area code in the target category code; and dividing the target class objects with the same area code into the same group to obtain a plurality of target class object groups.
In one embodiment, the apparatus for identifying a target class object further includes a newly added target class object table construction and availability judgment module, configured to construct a newly added target class object table according to object information corresponding to the newly added target class object; matching the object information in the newly added target class object table with the acquired target class object sample data, and counting the number of newly added target class objects which fail to be matched in the newly added target class object table; and judging the availability of the newly added target class object table according to the proportion of the number of the newly added target class objects which are failed to be matched to the total number of the newly added target class objects in the newly added target class object table.
For the specific definition of the identification device of the target class object, reference may be made to the above definition of the identification method of the target class object, and details are not described herein again. The modules in the device for identifying the target class object can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store the target order. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of identifying an object of a target class.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, the computer program may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for identifying an object of a target category, the method comprising:
dividing order objects with the addresses belonging to the same area into the same group according to the area to which the addresses belong on the basis of order objects corresponding to target orders and the addresses extracted from the target orders and corresponding to the order objects, and obtaining a plurality of order object groups;
extracting the contained target category objects and the area information from each piece of acquired target category information respectively, and dividing the target category objects with the same area information into the same group to obtain a plurality of target category object groups;
based on the area information corresponding to each order object group and each target class object group, respectively screening out an order object group to be matched and a target class object group to be matched which belong to the same area from the plurality of order object groups and the plurality of target class object groups;
and performing similarity matching on the order objects in the order object group to be matched and the target class objects in the target class object group to be matched, and judging whether the order objects are newly added target class objects or not according to a matching result.
2. The method of claim 1, further comprising:
carrying out object group matching on the order object group to be matched and the target class object group to be matched to obtain an object group matching result;
the matching of the similarity between the order object in the order object group to be matched and the target class object in the target class object group to be matched, and determining whether the order object is a newly added target class object according to the matching result, includes:
and when the object group matching result meets the object group matching condition, performing similarity matching on the order object in the order object group to be matched and the target class object in the target class object group to be matched, and judging whether the order object is a newly added target class object according to the matching result.
3. The method according to claim 2, wherein the performing object group matching on the order object group to be matched and the target category object group to be matched to obtain an object group matching result comprises:
carrying out identification matching on the object identification in the order object group to be matched and the object identification in the target category object group to be matched, and determining an object identification group which is successfully matched;
when the object group matching result meets the object group matching condition, similarity matching is performed between the order object in the order object group to be matched and the target class object in the target class object group to be matched, and whether the order object is a newly added target class object is judged according to the matching result, including:
and when the number of the successfully matched object identification groups meets the number condition, performing similarity matching on the order object and the target class object corresponding to the successfully matched object identification groups, and judging whether the corresponding order object is the newly added target class object or not according to a matching result.
4. The method according to claim 1, wherein the dividing the order objects belonging to the same area into the same group according to the area to which the address belongs to obtain a plurality of order object groups comprises:
carrying out format standardization on the address, converting the obtained address data with the standardized format into longitude and latitude, and obtaining a plurality of area units obtained by carrying out unit division on a preset area according to the longitude and latitude;
and dividing the order objects corresponding to the addresses belonging to the same area unit into the same group according to the area unit to which the longitude and latitude corresponding to the address belong, so as to obtain a plurality of order object groups.
5. The method of claim 4, wherein the area of the plurality of zone units is equal.
6. The method according to claim 1, wherein the extracting, from each piece of obtained object category information, an object category object and area information included in the piece of obtained object category information, and dividing object category objects having the same area information into the same group to obtain a plurality of object category object groups includes:
extracting a target category object and a target category code contained in each piece of acquired target category information respectively;
extracting a region code from the target category code based on the position of the region code in the target category code;
and dividing the target class objects with the same area code into the same group to obtain a plurality of target class object groups.
7. The method of claim 1, further comprising:
constructing a new target class object table according to the object information corresponding to the new target class object;
matching the object information in the newly added target class object table with the acquired target class object sample data, and counting the number of newly added target class objects which fail to be matched in the newly added target class object table;
and judging the availability of the newly added target class object table according to the proportion of the number of the newly added target class objects which fail to be matched to the total number of the newly added target class objects in the newly added target class object table.
8. An apparatus for identifying an object of a target class, the apparatus comprising:
the order object group building module is used for dividing order objects of which the addresses belong to the same area into the same group according to the area to which the addresses belong on the basis of order objects corresponding to target orders and the addresses, extracted from the target orders, corresponding to the order objects, so as to obtain a plurality of order object groups;
the target category object group building module is used for respectively extracting the contained target category objects and the area information from each piece of acquired target category information, and dividing the target category objects with the same area information into the same group to obtain a plurality of target category object groups;
the object group screening module is used for screening out order object groups to be matched and target class object groups to be matched which belong to the same region from the plurality of order object groups and the plurality of target class object groups respectively based on the region information corresponding to each order object group and each target class object group respectively;
and the object matching module is used for performing similarity matching on the order objects in the order object group to be matched and the target class objects in the target class object group to be matched, and judging whether the order objects are the newly added target class objects or not according to a matching result.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110570388.9A CN115392603A (en) | 2021-05-25 | 2021-05-25 | Target class object identification method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110570388.9A CN115392603A (en) | 2021-05-25 | 2021-05-25 | Target class object identification method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115392603A true CN115392603A (en) | 2022-11-25 |
Family
ID=84114151
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110570388.9A Pending CN115392603A (en) | 2021-05-25 | 2021-05-25 | Target class object identification method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115392603A (en) |
-
2021
- 2021-05-25 CN CN202110570388.9A patent/CN115392603A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107679684B (en) | Policy allocation method, policy allocation device, storage medium and computer equipment | |
| US8131652B2 (en) | Residential delivery indicator | |
| US7523133B2 (en) | Data model and applications | |
| CN112882699B (en) | Service processing method, device, equipment and medium based on flow configuration engine | |
| US11386224B2 (en) | Method and system for managing personal digital identifiers of a user in a plurality of data elements | |
| US20200286168A1 (en) | Two device authentication for a credit application | |
| US11681744B2 (en) | Methods and systems for updating a database based on object recognition | |
| WO2019051946A1 (en) | Node task data display method and apparatus, storage medium and computer equipment | |
| WO2019024496A1 (en) | Enterprise recommendation method and application server | |
| US8255392B2 (en) | Real time data collection system and method | |
| US11468508B2 (en) | Capturable code for automatically formatting and addressing a text message to apply for an offer | |
| US20210019742A1 (en) | Customer acquisition without initially receiving personally identifiable information (pii) | |
| CN109145050B (en) | Computing device | |
| US20240095734A1 (en) | Embedded data transaction exchange platform | |
| CN109902129B (en) | Insurance agent classifying method and related equipment based on big data analysis | |
| US20110202542A1 (en) | Integration of voter and contributor data into political software and compliance systems for purposes of solicitation, compliance, vetting, and calls to action | |
| US8918422B2 (en) | Method and system for using email domains to improve quality of name and postal address matching | |
| CN115392603A (en) | Target class object identification method and device, computer equipment and storage medium | |
| CN109636578A (en) | Risk checking method, device, equipment and the readable storage medium storing program for executing of credit information | |
| CN109919811B (en) | Insurance agent culture scheme generation method based on big data and related equipment | |
| CN109885710B (en) | User image depicting method based on differential evolution algorithm and server | |
| CN115392602A (en) | Associated information processing method, associated information processing device, computer equipment and storage medium | |
| CN113743838A (en) | Target user identification method and device, computer equipment and storage medium | |
| CN109561406B (en) | SIM card selection method, device, system, electronic equipment and medium | |
| CN110765118B (en) | Data revision method, revision device and readable storage medium |
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 |