CN113657111A

CN113657111A - Address recognition method, system, storage medium and electronic device

Info

Publication number: CN113657111A
Application number: CN202110870674.7A
Authority: CN
Inventors: 安达; 唐大闰
Original assignee: Shanghai Minglue Artificial Intelligence Group Co Ltd
Current assignee: Shanghai Minglue Artificial Intelligence Group Co Ltd
Priority date: 2021-07-30
Filing date: 2021-07-30
Publication date: 2021-11-16

Abstract

The application discloses an address identification method, a system, a storage medium and an electronic device, wherein the method comprises the following steps: a data preparation step: using NER to identify the collected sample address information and then generating ternary group data; the construction steps are as follows: constructing a knowledge graph according to the triple data by using a relational database; and a relation searching step, namely, identifying the address information in the data through the relation of the data searched by the knowledge graph. The invention can judge the relation between the addresses by using a knowledge graph reasoning method, thereby clearly and quickly judging the relation between different addresses and saving the cost.

Description

Address recognition method, system, storage medium and electronic device

Technical Field

The invention belongs to the field of address identification, and particularly relates to an address identification method, an address identification system, a storage medium and electronic equipment.

Background

In the business card recognition, the content of the character recognition needs to be classified and information extraction is needed, wherein the address is a very important information. When identifying addresses in business cards, there are often rows of address information that may need to be stitched together or may be two addresses. The invention introduces an address identification method based on knowledge graph reasoning to solve the problem that the relation of multiple lines of addresses is difficult to judge according to keywords.

Disclosure of Invention

The embodiment of the invention provides an address identification method, which comprises the following steps:

a data preparation step: using NER to identify the collected sample address information and then generating ternary group data;

the construction steps are as follows: constructing a knowledge graph according to the triple data by using a relational database;

and a relation searching step, namely, identifying the address information in the data through the relation of the data searched by the knowledge graph.

The above address recognition method, wherein the relational database includes:

neo4j database, Oracle database, DB2 database, MySQL database, and Microsoft SQL Server database.

The address identification method described above, wherein the data preparation step includes:

the collection step comprises: collecting a plurality of sample address information;

and generating triple data, namely, after the NER is used for identifying the sample address information, generating triple data according to the relation among the sample address information.

The above address identification method, wherein the relationship searching step includes: when the same data comprises a plurality of pieces of address information to be identified, judging whether the plurality of pieces of address information to be identified have inclusion relations or not through the knowledge graph; if the at least two pieces of address information to be recognized have an inclusion relationship, searching a complete path on the knowledge graph to obtain one piece of address information corresponding to the at least two pieces of address information to be recognized; if the inclusion relationship does not exist between at least two pieces of address information to be identified, searching a complete path on the knowledge graph to obtain one piece of address information corresponding to each piece of address information to be identified.

The invention also provides an address identification system, which comprises:

the data preparation module is used for identifying the acquired sample address information by using NER and then generating ternary group data;

a construction module for constructing a knowledge graph according to the triple data by using a relational database;

and the relation searching module is used for identifying the address information in the data through the relation of the knowledge graph searched data.

The above address recognition system, wherein the relational database comprises:

The above address recognition system, wherein the data preparation module comprises:

an acquisition unit that acquires a plurality of the sample address information;

and generating a triple data unit, wherein the triple data unit generates triple data according to the relation among the sample address information after identifying the sample address information by using the NER.

The above address identification system, wherein the relationship searching module comprises: when the same data comprises a plurality of pieces of address information to be identified, judging whether the plurality of pieces of address information to be identified have inclusion relations or not through the knowledge graph; if the at least two pieces of address information to be recognized have an inclusion relationship, searching a complete path on the knowledge graph to obtain one piece of address information corresponding to the at least two pieces of address information to be recognized; if the inclusion relationship does not exist between at least two pieces of address information to be identified, searching a complete path on the knowledge graph to obtain one piece of address information corresponding to each piece of address information to be identified.

A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the address recognition method as described in any one of the above when executing the computer program.

A storage medium having stored thereon a computer program, wherein the program, when executed by a processor, implements an address recognition method as in any one of the above.

The invention belongs to the field of knowledge inference in the knowledge graph technology, and can judge the relation between addresses by using a knowledge graph inference method, clearly and quickly judge the relation between different addresses by using a knowledge graph, thereby saving the labor cost.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application.

In the drawings:

FIG. 1 is a flow chart of an address identification method of the present invention;

FIG. 2 is a flow chart illustrating the substeps of step S1 in FIG. 1;

FIG. 3 is one of the graphs of a sample of data acquired;

FIG. 4 is one of the graphs of a sample of data acquired;

FIG. 5 is a schematic diagram of a partial knowledge graph;

FIG. 6 is a sample diagram of addresses with containment relationships;

FIG. 7 is a sample diagram of addresses without containment relationships;

FIG. 8 is a triplet construction map;

FIG. 9 is a schematic diagram of the structure of the address recognition system of the present invention;

fig. 10 is a block diagram of a computer apparatus according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated 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. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.

It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.

Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.

Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.

The present invention is described in detail with reference to the embodiments shown in the drawings, but it should be understood that these embodiments are not intended to limit the present invention, and those skilled in the art should understand that functional, methodological, or structural equivalents or substitutions made by these embodiments are within the scope of the present invention.

Before describing in detail the various embodiments of the present invention, the core inventive concepts of the present invention are summarized and described in detail by the following several embodiments.

The first embodiment is as follows:

referring to fig. 1, fig. 1 is a flowchart of an address identification method. As shown in fig. 1, the address recognition method of the present invention includes:

data preparation step S1: using NER to identify the collected sample address information and then generating ternary group data;

a construction step S2: constructing a knowledge graph according to the triple data by using a relational database;

and a relation searching step S3, namely identifying the address information in the data through the relation of the knowledge map searching data.

Wherein the relational database comprises:

Referring to fig. 2, fig. 2 is a flowchart illustrating a sub-step of step S1 in fig. 1. As shown in fig. 2, the data preparation step S1 includes:

a collection step S11: collecting a plurality of sample address information;

and a step S12 of generating triple data, namely, after the NER is used for identifying a plurality of sample address information, generating triple data according to the relationship among the sample address information.

Wherein the relationship searching step comprises: when the same data comprises a plurality of pieces of address information to be identified, judging whether the plurality of pieces of address information to be identified have inclusion relations or not through the knowledge graph; if the at least two pieces of address information to be recognized have an inclusion relationship, searching a complete path on the knowledge graph to obtain one piece of address information corresponding to the at least two pieces of address information to be recognized; if the inclusion relationship does not exist between at least two pieces of address information to be identified, searching a complete path on the knowledge graph to obtain one piece of address information corresponding to each piece of address information to be identified.

Specifically, the method comprises the following steps:

preparing data of an inference map;

constructing a knowledge graph;

searching the relation;

further, the method of the invention comprises the following specific steps:

data preparation

Several hundred to several thousand pieces of address information (multiple rows of addresses need not be merged) are collected as shown in fig. 3 and 4.

Using NER to identify address information therein and generating ternary group data according to context, e.g. using NER to identify address information therein

(nation → inclusion → province), (province → inclusion → city), (city → inclusion → region), (region → inclusion → road), (road → inclusion → number)

Constructing a map using a relational database such as neo4j or the like;

a part of the map is shown in FIG. 5 (only a part of the map is cut out due to more data)

And (3) relation finding:

case 1 as shown in fig. 6:

the two-row addresses are respectively:

fujian province, Fuzhou city, drumbeat district software Daodao No. 89;

(province → city), (city → district), (district → road), (road → district → number)

Floor 23 of No. 5 building in software garden F;

(circle → contain → region), (region → contain → building), (building → contain → layer)

The inclusion relationship between the number of the first line and the garden of the second line can be found according to the map, so that the complete address is as follows:

fujian province Fuzhou city drumbeat area software Dadao No. 89 software garden No. 5 floor No. 23 floor

Meanwhile, a complete path can be searched on the map.

(province → city), (city → district), (district → city → street), (street → city → sign); (number → comprises → garden), (garden → comprises → region), (region → comprises → floor), (floor → comprising → floor)

Case 2 as shown in fig. 7:

the two-row addresses are respectively:

shenzhen nan shan region 212 room;

guangzhou city continent avenue;

according to the map, the fact that the first row of rooms and the second row of cities do not have inclusion relations can be found, so that the two rows of addresses are in parallel relation, and the business card has two addresses.

Still further, named entity identification includes:

named Entity Recognition (NER), the focus of interest is the information extraction (information extraction) problem, i.e. extracting structured information about company activities and defense-related activities from unstructured text such as chapters, while names of people, place names, organization names, time and numerical expressions (including time, date, currency amount and percentage, etc.) are key contents of the structured information. It is the boundaries and categories that these entities refer to.

Understanding of knowledge-graph triplets, entities, types, attributes, relationships, domains, values

Definition of the triplets:

the entity is an abstraction of an objective individual, and a person, a movie and a sentence can be regarded as an entity. For example: yaoming and Lian.

A type is an abstraction of a collection of entities having the same characteristics or attributes.

Examples are: china is an entity, the united states is an entity and france is an entity. These entities all have common characteristics of capital, population, area, etc., so that entities having characteristics of capital, population, area, etc., such as china, usa, france, etc., for example, can be abstracted as a "national" type

The attribute is an abstraction of the relationship between the entities, for example, liaan is an entity, liaan is a character (type), the fantasy drift of the youth pie is an entity, the fantasy drift of the youth pie is a movie (type), and it is obvious that the relationship between the two entities is: lie → director → the fantasy drift of the youth party so the relationship between lie and fantasy drift of the youth party can be characterized by the attribute "director". Then a layer of relationships, people (type) → director (property) → movie (type), can be built from the properties.

The relationship is an abstraction of the relationship between the entities, namely lie (entry) → director (relationship) → fantasy drift of the youth party, and the director (relationship) is the relationship describing the fantasy drift of lie and the youth party.

A domain is a collection of types, overriding a type, and is an abstraction of all types in a domain, such as: a country is an abstraction of such entities as china and the united states, and is a type, and a geographic location includes other types in addition to country types: city, region, continent, etc., while all of these types: the types of continents, countries, cities, regions, etc. are abstracted to form the geographic location domain.

Values are used to describe entities and can be classified into textual and numeric types, EG: yaoangg (entry) → height (relation) → 226cm (value).

Based on the above concept, a basic map is constructed

From the triplet-building map as shown in fig. 8 it can be derived:

a company, a stock, is a ribbon of Alibara;

zhang Yong is a character;

the Payment is a product.

The CEO of Ali baba is Zhang courage;

the main marketing product of the Ali baba is Paibao;

the number of members of the Alibara staff was 60000.

Example two:

referring to fig. 9, fig. 9 is a schematic structural diagram of an address recognition system according to the present invention. As shown in fig. 9, an address recognition system of the present invention includes:

the data preparation module 11 is used for identifying the acquired sample address information by using NER and then generating ternary group data;

a construction module 12 for constructing a knowledge graph from the triple data using a relational database;

and the relation searching module 13 is used for identifying the address information in the data through the relation of the knowledge graph searched data.

Wherein the relational database comprises:

Wherein, the data preparation module 11 includes:

an acquisition unit 111 that acquires a plurality of the sample address information;

and a triple data generating unit 112, configured to generate triple data according to a relationship between the sample address information after the triple data generating unit identifies the sample address information by using the NER.

Wherein, the relationship searching module 13 includes: when the same data comprises a plurality of pieces of address information to be identified, judging whether the plurality of pieces of address information to be identified have inclusion relations or not through the knowledge graph; if the at least two pieces of address information to be recognized have an inclusion relationship, searching a complete path on the knowledge graph to obtain one piece of address information corresponding to the at least two pieces of address information to be recognized; if the inclusion relationship does not exist between at least two pieces of address information to be identified, searching a complete path on the knowledge graph to obtain one piece of address information corresponding to each piece of address information to be identified.

Example three:

referring to FIG. 10, this embodiment discloses an embodiment of a computer device. The computer device may comprise a processor 81 and a memory 82 in which computer program instructions are stored.

Specifically, the processor 81 may include a Central Processing Unit (CPU), or A Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.

Memory 82 may include, among other things, mass storage for data or instructions. By way of example, and not limitation, memory 82 may include a Hard Disk Drive (Hard Disk Drive, abbreviated to HDD), a floppy Disk Drive, a Solid State Drive (SSD), flash memory, an optical Disk, a magneto-optical Disk, tape, or a Universal Serial Bus (USB) Drive or a combination of two or more of these. Memory 82 may include removable or non-removable (or fixed) media, where appropriate. The memory 82 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 82 is a Non-Volatile (Non-Volatile) memory. In particular embodiments, Memory 82 includes Read-Only Memory (ROM) and Random Access Memory (RAM). The ROM may be mask-programmed ROM, Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), Electrically rewritable ROM (EAROM), or FLASH Memory (FLASH), or a combination of two or more of these, where appropriate. The RAM may be a Static Random-Access Memory (SRAM) or a Dynamic Random-Access Memory (DRAM), where the DRAM may be a Fast Page Mode Dynamic Random-Access Memory (FPMDRAM), an Extended data output Dynamic Random-Access Memory (EDODRAM), a Synchronous Dynamic Random-Access Memory (SDRAM), and the like.

The memory 82 may be used to store or cache various data files for processing and/or communication use, as well as possible computer program instructions executed by the processor 81.

The processor 81 implements any of the address recognition methods in the above embodiments by reading and executing computer program instructions stored in the memory 82.

In some of these embodiments, the computer device may also include a communication interface 83 and a bus 80. As shown in fig. 10, the processor 81, the memory 82, and the communication interface 83 are connected via the bus 80 to complete mutual communication.

The communication interface 83 is used for implementing communication between modules, devices, units and/or equipment in the embodiment of the present application. The communication port 83 may also be implemented with other components such as: the data communication is carried out among external equipment, image/data acquisition equipment, a database, external storage, an image/data processing workstation and the like.

Bus 80 includes hardware, software, or both to couple the components of the computer device to each other. Bus 80 includes, but is not limited to, at least one of the following: data Bus (Data Bus), Address Bus (Address Bus), Control Bus (Control Bus), Expansion Bus (Expansion Bus), and Local Bus (Local Bus). By way of example, and not limitation, Bus 80 may include an Accelerated Graphics Port (AGP) or other Graphics Bus, an Enhanced Industry Standard Architecture (EISA) Bus, a Front-Side Bus (FSB), a Hyper Transport (HT) Interconnect, an ISA (ISA) Bus, an InfiniBand (InfiniBand) Interconnect, a Low Pin Count (LPC) Bus, a memory Bus, a microchannel Architecture (MCA) Bus, a PCI (Peripheral Component Interconnect) Bus, a PCI-Express (PCI-X) Bus, a Serial Advanced Technology Attachment (SATA) Bus, a Video Electronics Bus (audio Electronics Association), abbreviated VLB) bus or other suitable bus or a combination of two or more of these. Bus 80 may include one or more buses, where appropriate. Although specific buses are described and shown in the embodiments of the application, any suitable buses or interconnects are contemplated by the application.

The computer device may be based on an address recognition method, thereby implementing the method described in connection with fig. 1-2.

In addition, in combination with the address identification method in the foregoing embodiments, the embodiments of the present application may provide a computer-readable storage medium to implement. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the address identification methods in the above embodiments.

The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

In summary, the beneficial effects of the invention are that the invention can use the knowledge graph reasoning method to judge the relation between the addresses, and use the knowledge graph to clearly and rapidly judge the relation between different addresses, thereby saving manpower and material resources.

The above-mentioned embodiments 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

1. An address identification method, comprising:

2. The address recognition method of claim 1, wherein the relational database comprises:

3. The address recognition method of claim 1, wherein the data preparation step comprises:

4. The address recognition method of claim 1, wherein the relationship lookup step comprises: when the same data comprises a plurality of pieces of address information to be identified, judging whether the plurality of pieces of address information to be identified have inclusion relations or not through the knowledge graph; if the at least two pieces of address information to be recognized have an inclusion relationship, searching a complete path on the knowledge graph to obtain one piece of address information corresponding to the at least two pieces of address information to be recognized; if the inclusion relationship does not exist between at least two pieces of address information to be identified, searching a complete path on the knowledge graph to obtain one piece of address information corresponding to each piece of address information to be identified.

5. An address recognition system, comprising:

6. The address recognition system of claim 5, wherein the relational database comprises:

7. The address recognition system of claim 5, wherein the data preparation module comprises:

8. The address recognition system of claim 5, wherein the relationship lookup module comprises: when the same data comprises a plurality of pieces of address information to be identified, judging whether the plurality of pieces of address information to be identified have inclusion relations or not through the knowledge graph; if the at least two pieces of address information to be recognized have an inclusion relationship, searching a complete path on the knowledge graph to obtain one piece of address information corresponding to the at least two pieces of address information to be recognized; if the inclusion relationship does not exist between at least two pieces of address information to be identified, searching a complete path on the knowledge graph to obtain one piece of address information corresponding to each piece of address information to be identified.

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the address recognition method according to any one of claims 1 to 4 when executing the computer program.

10. A storage medium on which a computer program is stored, which program, when being executed by a processor, carries out the address recognition method according to any one of claims 1 to 4.