CN112711645B

CN112711645B - Method and device for expanding position point information, storage medium and electronic equipment

Info

Publication number: CN112711645B
Application number: CN202110029268.8A
Authority: CN
Inventors: 季成晖; 张哲旸; 卢俊之; 黄海涛
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2021-01-11
Filing date: 2021-01-11
Publication date: 2022-05-10
Anticipated expiration: 2041-01-11
Also published as: CN112711645A

Abstract

The application provides a method and a device for expanding position point information, a storage medium and electronic equipment, belongs to the technical field of Internet, and relates to artificial intelligence and natural language processing technology. The method and the device adopt the position point information relational database to store the corresponding relation between the identification of the object and the identification of the position point in the map. After the first identifier of the target object and the extended information to be added are obtained, the second identifier of the target position point associated with the target object can be searched in the position point information relation base according to the first identifier, then the basic information of the target position point identified in the map is obtained according to the searched second identifier, and the extended information and the basic information are stored in an associated mode aiming at the target position point, so that corresponding target information is obtained. By the method, the marked information is expanded for the position points in the map, so that the information of the position points is more comprehensive and accurate, and a more comprehensive and accurate travel reference is provided for a user.

Description

Method and device for expanding position point information, storage medium and electronic equipment

Technical Field

The present application relates to the field of internet technologies, and in particular, to a method and an apparatus for extending location point information, a storage medium, and an electronic device.

Background

With the progress of technology and the increasing development of mobile internet, the usage amount of map products by users is increasing year by year. When a user uses a map product, such as an electronic map, the user usually pays attention to map data such as a position point marked in the map.

Currently, the number of location points marked in a map is very large, for example: and the positions of landmarks, scenic spots, merchants, traffic facilities and the like. Meanwhile, the relevant information sources of the position points are many, such as: user add or merchant add, etc.

Therefore, in the related art, the maintenance workload of the related information of the location point is large, the data accuracy is insufficient, and a more comprehensive and more accurate travel reference cannot be provided for the user.

Disclosure of Invention

In order to solve technical problems in the related art, embodiments of the present application provide a method and an apparatus for extending location point information, a storage medium, and an electronic device, which can label location points in a map with more comprehensive and accurate information.

In order to achieve the above purpose, the technical solution of the embodiment of the present application is implemented as follows:

in a first aspect, an embodiment of the present application provides a method for extending location point information, where the method includes:

acquiring a first identifier of a target object and extended information to be added;

searching a second identifier of the target position point associated with the target object in a position point information relational database according to the first identifier; the position point information relation library is used for storing the corresponding relation between the mark of the object and the mark of the position point in the map;

acquiring the identified basic information of the target position point in the map according to the second identification;

and for the target position point, performing associated storage on the extended information and the basic information to obtain corresponding target information.

In a second aspect, an embodiment of the present application provides a location point information extension apparatus, where the apparatus includes:

the first data acquisition unit is used for acquiring a first identifier of a target object and extended information to be added;

the data query unit is used for searching a second identifier of the target position point associated with the target object in a position point information relational database according to the first identifier; the position point information relation library is used for storing the corresponding relation between the mark of the object and the mark of the position point in the map;

the second data acquisition unit is used for acquiring the basic information of the target position point identified in the map according to the second identification;

and the information extension unit is used for associating and storing the extension information and the basic information aiming at the target position point to obtain corresponding target information.

In an optional embodiment, the information extension unit is further configured to:

and sending the target information to the first terminal based on an information acquisition request sent by the first terminal aiming at the target position point, so that the first terminal displays the target information aiming at the target position point in a map.

In an optional embodiment, the data query unit is further configured to:

for each position point with feedback information, the feedback information is information fed back by the second terminal for the position point; the following operations are respectively performed:

acquiring the identifier of the position point in the map;

acquiring an identifier of an object corresponding to the position point based on the feedback information of the position point;

and storing the corresponding relation between the identification of the object and the identification of the position point into the position point information relational database.

In an optional embodiment, the feedback information of the one location point includes a license image of the object corresponding to the one location point; the data query unit is specifically configured to:

performing character recognition on the license image to obtain license character information of the object corresponding to the one position point;

and acquiring the identification of the object corresponding to the one position point from the license text information of the object.

In an optional embodiment, the first data obtaining unit is specifically configured to:

acquiring a transaction data set of the target object; each transaction data in the transaction data set comprises transaction time information and a first identification of the target object;

determining business information of the target object according to the transaction time information corresponding to each transaction data in the transaction data set;

and generating the extended information to be added according to the business information of the target object.

In an optional embodiment, the transaction data further includes transaction location information; the second data obtaining unit is further configured to:

if the second identifier of the target position point associated with the target object is not found in the position point information relational database, clustering the transaction data of the target object according to the transaction position information corresponding to each transaction data in the transaction data set to obtain the transaction center position corresponding to the target object;

searching candidate position points in a preset range around the position of the transaction center in the map, and acquiring the identifier of each candidate position point;

and selecting a candidate position point with the identifier matched with the first identifier from the candidate position points as the target position point.

In an optional embodiment, the identifier of the candidate position point and the first identifier are both text identifiers; the second data obtaining unit is specifically configured to:

for each candidate position point, if the identifier of the candidate position point and the first identifier contain at least one same character, taking the candidate position point as a reference target position point of the target object;

determining text similarity between the identifier of each reference target position point and the first identifier;

and selecting the target position points from the reference target position points according to the text similarity corresponding to the reference target position points.

In an optional embodiment, the second data obtaining unit is specifically configured to:

for each reference target position point, the following operations are respectively performed:

performing text feature extraction on the first identification to obtain a first text feature vector;

extracting text features of the marks of the reference target position points to obtain text feature vectors of the reference target position points;

determining a difference vector between the first text feature vector and the text feature vector of the reference target position point;

splicing the first text characteristic vector, the text characteristic vector of the reference target position point and the difference vector to obtain a spliced vector;

and determining the text similarity between the identifier of the reference target position point and the first identifier according to the splicing vector.

taking the reference target position point with the maximum similarity in all the reference target position points as the target position point; alternatively, the first and second electrodes may be,

taking the reference target position points with the similarity greater than or equal to a set similarity threshold value in all the reference target position points as the target position points; alternatively, the first and second electrodes may be,

and taking the reference target position point with the maximum similarity and the similarity larger than or equal to a set similarity threshold value in all the reference target position points as the target position point.

In an alternative embodiment, the business information includes daily business hours; the first data obtaining unit is specifically configured to:

determining the earliest business time and the latest business time of the target object according to the transaction time information in each transaction data;

and generating the daily business hours of the target object according to the earliest business time and the latest business time of the target object.

In an alternative embodiment, the business information includes business status; the first data obtaining unit is specifically configured to:

acquiring a corresponding transaction date in the transaction time information of each transaction data;

and if the fact that the transaction data exist every day within a preset time threshold before the current moment is determined according to the transaction date corresponding to each transaction data, determining that the business state of the target object is normal business.

In an optional embodiment, the data query unit is specifically configured to:

if the identifiers of a plurality of candidate target position points corresponding to the target object are found in the position point information relational database, acquiring the geographical position of each candidate target position point according to the identifier of each candidate target position point;

determining the distance between the geographic position of each candidate target position point and the transaction center position corresponding to the target object;

and taking the candidate target position point with the closest distance as a target position point, and taking the mark of the target position point as the second mark.

In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method for extending location point information in the first aspect is implemented.

In a fourth aspect, an embodiment of the present application further provides an electronic device, including a memory and a processor, where the memory stores a computer program operable on the processor, and when the computer program is executed by the processor, the processor is caused to implement the location point information extension method of the first aspect.

The location point information expansion method, device, storage medium and electronic equipment provided by the embodiment of the application are provided with a location point information relation library for storing the corresponding relation between the identification of the object and the identification of the location point in the map. After the first identifier of the target object and the extended information to be added are obtained, the second identifier of the target position point associated with the target object can be searched in the position point information relation base according to the first identifier, then the identified basic information of the target position point in the map is obtained according to the searched second identifier, and the extended information and the basic information are stored in an associated mode aiming at the target position point, so that corresponding target information is obtained. By the method, the identified information is expanded for the position points in the map, so that the information of the position points is more comprehensive and accurate, and more comprehensive and accurate travel references are provided for users.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

Fig. 1 is a schematic view of an application scenario of a location point information expansion method according to an embodiment of the present application;

fig. 2 is a schematic flowchart of a method for extending location point information according to an embodiment of the present disclosure;

fig. 3 is a schematic diagram illustrating uploading feedback data of a location point information expansion method according to an embodiment of the present application;

fig. 4 is a schematic diagram of a shortcut menu selection box for feeding back information with respect to a location point according to an embodiment of the present disclosure;

fig. 5 is a schematic diagram of an interest point feedback information page provided in an embodiment of the present application;

fig. 6 is a schematic diagram of a data format for location point feedback information according to an embodiment of the present application;

fig. 7 is a schematic diagram illustrating location point expansion information displayed when a location point is clicked according to an embodiment of the present application;

fig. 8 is a schematic flowchart illustrating a process of establishing a location point information relationship library according to an embodiment of the present application;

fig. 9 is a schematic flowchart of a method for extending location point information according to an embodiment of the present application to obtain extended information;

fig. 10 is a schematic flowchart of another location point information expansion method according to an embodiment of the present application;

fig. 11 is a schematic flowchart of determining text similarity according to a method for expanding location point information provided in an embodiment of the present application;

fig. 12 is a schematic diagram of a frame of text similarity calculation in a location point information expansion method according to an embodiment of the present application;

fig. 13 is a schematic flowchart of another location point information expansion method according to an embodiment of the present application;

FIG. 14 is a diagram illustrating location point information displayed when a location point is clicked;

fig. 15 is a schematic diagram illustrating location point expansion information displayed when a location point is clicked according to another embodiment of the present application;

fig. 16 is a block diagram illustrating a structure of a location point information extension apparatus according to an embodiment of the present application;

fig. 17 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that references in the specification of the present application to the terms "comprises" and "comprising," and variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Some terms in the embodiments of the present application are explained below to facilitate understanding by those skilled in the art.

(1) Geographic Information System (GIS): the system is a computer system for collecting, storing, managing, processing, retrieving, analyzing and expressing geospatial data, and is a system for analyzing and processing massive geographic data.

(2) Point of Interest (POI): the location point is also referred to as a landmark or a scenic spot in the geographic information system in the embodiment of the present application, and is used for marking places such as government departments represented by the place, commercial institutions of various industries (gas stations, department stores, supermarkets, restaurants, hotels, convenience stores, hospitals, etc.), tourist attractions (parks, public toilets), historic sites, transportation facilities (various stations, parking lots, speeding cameras, speed limit signs), and the like.

(3) Knowledge map (KGs): the knowledge domain visualization or knowledge domain mapping map is a series of different graphs for displaying the relationship between the knowledge development process and the structure, describes knowledge resources and carriers thereof by using visualization technology, and mines, analyzes, constructs, draws and displays knowledge and the mutual relation between the knowledge resources and the carriers. The POI knowledge graph in the embodiment of the application is a database for storing the corresponding relationship among basic POI information, merchant names and corporate information of points of interest (POI), wherein the basic POI information includes: POI serial number, POI name, POI coordinates, POI address and POI classification. The POI name may be a signboard name of the geographical information to which the POI refers, for example, the POI name may be "bridge spareribs (store)' as shown in fig. 5; the merchant name may be a license name of the geographic information to which the POI refers, for example, the merchant name may be "# # school # trade company"; the corporate information may be the name of a legal representative in a license of the geographic information designated by the POI, for example, the corporate information may be "lie somewhere" as shown in fig. 5.

(4) Lightweight Bert model (a Lite Bert, ALBert): the lightweight BERT model is a lightweight BERT model for Chinese preprocessing, and is also called ALBert model. The number of parameters is much less than the conventional BERT model. The ALBert overcomes the main obstacles faced by the extended pre-training model through the following two parameter reduction technologies:

first, the embedding parameters are factorized. The large vocabulary embedding matrix is decomposed into two small matrices, separating the size of the hidden layer from the size of the vocabulary embedding. This separation makes the addition of the hidden layer easier, while not significantly increasing the number of parameters of the lexical embedding.

And secondly, cross-layer parameter sharing can avoid the increase of the number of network parameters along with the increase of the network depth.

Both techniques can significantly reduce the number of parameters of BERT without significantly affecting the performance of the model. To further improve performance, the ALBert also introduces an auto-supervised loss function for sentence-level prediction (SOP). SOP focuses mainly on inter-sentence coherence for solving the problem of low efficiency of next-sentence prediction (NSP) loss in the conventional BERT model. In some embodiments of the present application, the ALBert is used to extract text feature vectors of merchant names and POI names.

The word "exemplary" is used hereinafter to mean "serving as an example, embodiment, or illustration. Any embodiment described as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The terms "first" and "second" are used herein for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of embodiments of the application, unless stated otherwise, "plurality" means two or more.

The embodiment of the present application relates to Artificial Intelligence (AI) and Machine Learning technologies, and is designed based on Natural Language Processing (NLP) and Machine Learning (ML) technologies in the AI.

Artificial intelligence is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making. The artificial intelligence techniques mainly include computer vision techniques, natural language processing techniques, Speech processing techniques (Speech Technology), and machine learning/deep learning.

With the research and progress of artificial intelligence technology, artificial intelligence is researched and applied in a plurality of fields, such as common smart homes, smart customer service, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, robots, smart medical treatment and the like.

Machine learning is a multi-field cross discipline, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and the like. The method and the device for extracting the text feature vectors of the merchant names and the POI names adopt a lightweight Bert model based on machine learning and deep learning to carry out operations such as extracting the text feature vectors of the merchant names and the POI names.

Natural language processing technology is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that enable efficient communication between humans and computers using natural language. Natural language processing is a science integrating linguistics, computer science and mathematics. Therefore, the research in this field will involve natural language, i.e. the language that people use everyday, so it is closely related to the research of linguistics. Natural language processing techniques typically include text processing, semantic understanding, machine translation, robotic question and answer, knowledge mapping, and the like. The embodiment of the application adopts a natural language processing technology to process the character information in the business license of the target merchant and identify the name of the merchant.

In order to better understand the technical solution provided by the embodiment of the present application, some brief descriptions are provided below for application scenarios to which the technical solution provided by the embodiment of the present application is applicable, and it should be noted that the application scenarios described below are only used for illustrating the embodiment of the present application and are not limited. In specific implementation, the technical scheme provided by the embodiment of the application can be flexibly applied according to actual needs.

Fig. 1 shows an application scenario of the location point information extension method provided in the embodiment of the present application, and referring to fig. 1, the application scenario includes a first terminal device 100, a second terminal device 200, a third terminal device 300, and a server 400. Each terminal device and the server 400 may be communicatively connected and transmit data through the communication network 500. The communication network may be a wired network or a wireless network, such as a cellular data network or a WiFi wireless network.

The first terminal device 100 may be a mobile terminal such as a mobile phone, a Personal Digital Assistant (PDA), a tablet computer, and an intelligent wearable device (e.g., an intelligent watch and an intelligent helmet). The server 400 may be a server or a server cluster or a cloud computing center composed of a plurality of servers, or a virtualization platform, and may also be a personal computer, a large and medium-sized computer, or a computer cluster, etc.

In the application scenario provided in the embodiment of the present application, the first terminal device 100 is installed with application software of a geographic information system GIS, such as a client of an XX map. The server 400 may be a server providing background support for the GIS, and the number of the terminal devices connected to the server 400 may be one or more. The second terminal device 200 is also installed with application software of the geographic information system GIS. The third terminal device 300 is installed with a back-stage management client of the geographic information system GIS, and a back-stage manager of the geographic information system GIS can manage and maintain the geographic information system GIS through the back-stage management client installed on the third terminal device 300, for example, triggering the location point information extension of the geographic information system GIS according to needs, or performing or periodically triggering the parameter setting related to the location point information extension of the geographic information system GIS, and the like.

In practical applications, users often use the information of POI points in a map as an important basis for travel planning. However, the POI points of the map product in the related art can only give reference information to the user based on the identified basic information in the map, and at present, no scheme has been proposed for displaying the relevant customer information corresponding to the POI in the electronic map, so that the user cannot accurately know the customer information corresponding to each location point in the electronic map. How to provide a method for extending the location point information, so that the location point information can provide more comprehensive and more accurate travel references for the user, is a problem to be solved.

In order to solve technical problems in the related art, embodiments of the present application provide a method and an apparatus for extending location point information, a storage medium, and an electronic device. According to the method and the device for obtaining the target information, the first identification of the target object and the extended information to be added are obtained, the second identification of the target position point related to the target object is searched in the position point information relation base according to the first identification, then the basic information of the target position point, which is already identified in the map, is obtained according to the second identification, and the extended information and the basic information are stored in a related mode aiming at the target position point, so that the corresponding target information is obtained. The target information of the target position point is obtained by storing the acquired extended information to be added of the target object in association with the identified basic information in the map associated with the acquired target object, so that the position point information is more comprehensive and accurate, more comprehensive and accurate travel reference can be provided for a user, and the accuracy, timeliness and completeness of the position point information are improved.

For example, in the embodiment of the present application, the first terminal device 100 may be a mobile phone, the mobile phone is installed with application software of a geographic information system GIS01, and the server 400 is configured to provide a background support service for the application software of the geographic information system GIS 01. After the first user opens the geographic information system GIS01 using the first terminal device 100, the location point on the electronic map of the geographic information system GIS01 may be clicked to view information of the location point. The location point on the map may also be referred to as a point of interest, or a POI point, and the target object may be geographic information represented by an optional point of interest, in this embodiment, the classification of the geographic information represented by the optional point of interest is taken as an example of the business. The second user may open the geographic information system GIS01 through the second terminal device 200, click a location point on the electronic map of the geographic information system GIS01, and upload information for the clicked location point.

A background manager of the geographic information system GIS01 may open the background management client of the geographic information system GIS01 through the third terminal device 300, and input a command to trigger the location point information extension of the geographic information system GIS01, or perform parameter setting related to periodically triggering the location point information extension of the geographic information system GIS01, or the like. The server 400 may perform location point information expansion according to the location point information expansion method provided in the embodiment of the present application in response to a triggering operation of a back-end manager of the geographic information system GIS01, or may perform location point information expansion according to the location point information expansion method provided in the embodiment of the present application periodically according to a parameter setting of the back-end manager.

Specifically, the server 400 may obtain a first identifier of the target object and extension information to be added; searching a second identifier of a target position point associated with the target object in the position point information relational database according to the first identifier; the position point information relation library is used for storing the corresponding relation between the mark of the object and the mark of the position point in the map; acquiring the identified basic information of the target position point in the map according to the second identification; and for the target position point, performing associated storage on the extended information and the basic information to obtain corresponding target information so as to complete position point information extension. The above process of obtaining the target information of the target location point by storing the obtained extended information to be added of the target object in association with the identified basic information in the map associated with the obtained target object will be described in detail below.

In the embodiment described below, the first terminal device and the second terminal device are each installed with application software of the geographic information system GIS01, and the user can click a location point on an electronic map of the geographic information system GIS01 through the application software of the GIS01 to view location point information corresponding to the clicked location point, or upload information for the clicked location point. In the embodiments of the present application, the category of the geographic information represented by the clicked location point that is desired to be viewed is taken as an example of the merchant.

Fig. 2 illustrates a method for extending location point information provided by an embodiment of the present application, which may be applied to a server, such as the server 400 in fig. 1. As shown in fig. 2, the method may include the steps of:

step S201, a first identifier of the target object and the extension information to be added are acquired.

In some embodiments, the first identification of the target object may include a geographic information name of the target geographic information, for example, the target object is a target merchant, and the first identification of the target object may be a merchant name of the target merchant. In other embodiments, the first identification of the target object may include a geographic information name and geographic location coordinates of the target geographic information, for example, the target object is a target merchant, and the first identification of the target object may include a merchant name and merchant coordinates of the target merchant. In the following embodiments, a target object is taken as a target merchant, and a first identifier of the target object is a merchant name of the target merchant.

In some embodiments of the present application, the server may obtain transaction data of the target object from a third party transaction platform, where the transaction data of the target object includes a first identifier of the target object. For example, the transaction data of the target merchant may include a merchant ID, a merchant name, transaction coordinates, transaction time, and the like, where the merchant name may be used as the first identifier of the target object, and the transaction coordinates are coordinates of a transaction position determined by the user according to the longitude value and the latitude value when the user conducts a transaction with the third-party transaction platform. According to the transaction data of the target object, the extended information to be added by the target object can be obtained, for example, according to the transaction time and other information in the transaction data, the extended information of the business hours and business states of the target merchant can be determined.

It should be noted that the target object may be other mechanisms or attractions besides the business, and correspondingly, the extended information to be added to the target object may also be other information, such as entertainment items of the attractions.

Step S202, according to the first identification, a second identification of the target position point associated with the target object is searched in the position point information relational database.

The position point information relation library is used for storing the corresponding relation between the mark of the object and the mark of the position point in the map.

Illustratively, the first identifier of the target object is a business name, and the location point information relation library may be a POI knowledge map, wherein the POI knowledge map is used for storing the corresponding relation between the business name and the POI name of the POI point in the map. And the server searches a POI name of a target position point associated with the target object in the POI knowledge graph according to the merchant name, wherein the POI name is the second identifier.

In some embodiments, the POI knowledge graph may further store a corresponding relationship between a merchant name, corporate information, and POI basic information; the POI knowledge graph is updated regularly by the server according to information fed back by a map user aiming at the POI of the map interest point and POI basic information of the POI of the map interest point.

In other embodiments, the first identifier may be a business name and business coordinates, and the basic information of the POI in the POI knowledge map includes the POI coordinates. The server can also search the POI name of the target position point associated with the target object in the POI knowledge map according to the merchant name and the merchant coordinates.

Step S203, acquiring the identified basic information of the target position point in the map according to the second identification.

Illustratively, the second identification may be a POI name of a target location point associated with the target object. Optionally, the basic POI information in the POI knowledge graph may include basic information that the POI point has identified in the map. The server can query the POI knowledge graph according to the POI name of the target position point associated with the target object, and acquire the basic information of the target position point identified in the map. Alternatively, the map database may store the identified basic information of each POI point on the map. The server can query the map database according to the POI name of the target position point associated with the target object to acquire the basic information of the target position point identified in the map.

And S204, performing associated storage on the extended information and the basic information aiming at the target position point to obtain corresponding target information.

The server may store the extended information obtained in step S201 and the basic information obtained in step S203 for the target location point in a correlated manner, for example, store the obtained extended information and the basic information in a map database in a corresponding manner to obtain the target information of the target location point, thereby completing the extension of the information of the target location point in the map, and when the information of the target location point is displayed later, more information may be displayed.

Specifically, the server may send the target information to the first terminal device based on an information acquisition request sent by the first terminal device for the target location point, so that the first terminal device displays the target information for the target location point in the map. The first terminal device may also be referred to as the first terminal.

For example, the user may click on a target location point in a map on the first terminal on which the geographic information system is installed, and view information of the target location point. And the first terminal responds to the click operation of the user and sends an information acquisition request to the server aiming at the target position point, wherein the information acquisition request comprises the identification of the target position point. And the server receives an information acquisition request sent by the first terminal, and acquires the target information of the target position point from the map database according to the identifier of the target position point in the information acquisition request. And sending the target information to the first terminal. The first terminal displays the target information in the map for the target interest point.

In the location point information expansion process, the embodiment stores the acquired expansion information to be added of the target object in association with the identified basic information in the map associated with the acquired target object to obtain the target information of the target location point, so that the location point information is more comprehensive and accurate. The target information can be sent to the first terminal based on an information acquisition request sent by the first terminal aiming at the target position point, so that the first terminal can display the target information aiming at the target position point in the map, a user can conveniently and quickly master more comprehensive and more accurate position point information, more comprehensive, more accurate and more convenient trip reference can be provided for the user, and the accuracy, timeliness and completeness of the position point information are improved.

The location point information relation library used in the above-described embodiment stores the correspondence between the identifier of the object and the identifier of the location point in the map. Fig. 8 shows a flowchart for establishing a correspondence between the identifier of a location point and the identifier of an object according to the feedback information of the location point. The feedback information is information fed back by the second terminal for the location point, and the second terminal may be any terminal device that sends the feedback information to the server. Referring to fig. 8, for each location point having feedback information, the following operations may be performed:

step S801, an identifier of a location point in a map is acquired.

Step S802, based on the feedback information of the position point, the identification of the object corresponding to the position point is obtained.

In some embodiments, the server may obtain the feedback information of the user to any position point on the map through a user feedback platform of the map information system. The server may be configured to establish, for each location point that receives the feedback information, a correspondence between an identifier of the location point and an identifier of the object at regular intervals; or receiving feedback information of a user for a certain position point each time, and establishing a corresponding relationship between the identifier of the position point and the identifier of the object according to the feedback information.

For example, the user may open the geographic information system GIS01 on a second terminal that presents an electronic map to the user. When a user clicks a certain position point on the electronic map, feedback information can be edited for the position point. And the second terminal sends the feedback information of the user aiming at the position point to the server. The server receives the feedback information sent by the second terminal, and obtains the identifier of the position point in the map, such as the POI name of the position point.

In some embodiments, the feedback information uploaded by the user for the location point includes a license image of the object corresponding to the location point, that is, an image of a business license of the merchant corresponding to the location point. The following description will take the interest point as the location point as an example.

Illustratively, the user may feed back information through the second terminal in a manner of uploading feedback data through an electronic map for a point of interest with a POI name of "bridge x spareribs (five-mouth shop)". As shown in fig. 3, the user may press the selected interest point "bridge row rib" (store) in the electronic map displayed on the second terminal, and feed back information for the interest point. The second terminal receives the operation of pressing the interest point for a long time by the user, and pops up a shortcut menu selection box for the interest point, as shown in fig. 4. The user selects "feedback interest point information" in the shortcut menu selection box, and the second terminal receives the operation of the user's selection and displays the interest point feedback information page as shown in fig. 5. The user can edit the text through the text description area and select the picture of the license to upload through the license uploading area. In the electronic map, each point of interest has a POI number, which may also be referred to as a POI ID, and the POI number of each point of interest is unique and can be distinguished from other points of interest, for example, the POI number of the point of interest "bridge row rib (store by one mouth)" is 18195221478405701691. After the photos of the license are uploaded, the electronic map automatically names the uploaded photos according to the POI numbers of the selected points of interest.

After editing the content of the feedback information on the interest point feedback information page as shown in fig. 5, the user clicks the "submit" button, the second terminal receives the operation of the user feedback information, and sends the feedback information of the user for the interest point to the server. The data format of the feedback information received by the server may be, as shown in fig. 6, a business license including a point of interest with a POI name "bridge spareribs" (store), and the file name of the business license is "poiid: 18195221478405701691 business license ". The information fed back by the user also comprises specific feedback contents input by the user, such as 'the map display position is deviated, and is opposite to the road', and the information can be used for assisting background personnel of the electronic map A to refer when map information maintenance is carried out.

The feedback information sent by the second terminal also carries the POI number of the point of interest. The server can obtain the POI name of the point of interest according to the POI number in the feedback information: "bridge spareribs" (store), which are classified as merchants in the electronic map of the geographic information system GIS 01. And using the POI name of the interest point as the identification of the position point in the map.

Since the feedback information of the location point includes an image of a license of the object corresponding to the location point (hereinafter referred to as a license image), the identifier of the object may be obtained based on the license of the object in the feedback information.

In an optional embodiment, obtaining the identifier of the object corresponding to the location point based on the feedback information of the location point may be implemented by the following processes, including:

step A1, character recognition is carried out on the license image, and license character information of the object corresponding to the position point is obtained.

Illustratively, the server first updates the file by assigning a file name "poiid: 18195221478405701691 license "is subjected to OCR (Optical Character Recognition) Recognition to obtain the text information in the license.

Step a2, obtaining the identifier of the object corresponding to the location point from the license text information of the object.

Illustratively, the server may obtain corresponding merchant license information through keyword-based structured extraction. For example, structured extraction can be performed according to the keyword "legal representative", and the legal information is "lie somewhere"; and performing structured extraction according to the keyword 'name', and obtaining a merchant name '# # schuber # from commerce finite responsibility company' in the merchant license information. Optionally, the name of the merchant in the business license may be used as the identifier of the object corresponding to the location point; alternatively, the name of the legal representative in the business license and the name of the business can be used together as the identification of the object corresponding to the location point.

Step S803, storing the correspondence between the object identifier and the location point identifier in the location point information relationship library.

Illustratively, the server correspondingly stores the business name in the business license and the POI name of the location point into a location point information relational database to obtain the POI knowledge map.

Optionally, the storing the correspondence between the identifier of the object and the identifier of the location point into the location point information relationship library may further include: storing the corresponding relation between the identification association information of the object and the identification association information of the position point into a position point information relation library; when the identification associated information of the position point is the identification of the position point in the acquired map, the acquired position point information which comprises the identification of the position point and is related to the identification of the position point; and when the identification related information of the object is the identification of the object corresponding to the acquisition position point, the acquired object information including the identification of the object and related to the identification of the object.

For example, the server may store the corresponding relationship between the identification association information of the object and the identification association information of the location point in the location point information relationship library to obtain the POI knowledge map. The identification associated information of the object comprises a merchant name and legal person information; the identification association information of the location point includes basic POI information of a POI name.

In some optional embodiments, the POI basic information includes: POI number, POI name, POI coordinates, POI address, POI category, POI alias, etc.

Exemplarily, it is assumed that the POI name of a location point may be "bridge spareribs" (store)' shown in fig. 3, and the POI number of the location point is 18195221478405701691. In the basic information of the POI of the location point, the POI number is 18195221478405701691, the POI name is "bridge spareribs (× store)", the POI coordinate is the coordinate determined by the longitude value and the latitude value of the central point of the location point whose name is "bridge spareribs (× store)", the POI address is "× city region one route 29", and the POI classification is the default classification of the merchant name corresponding to the location point in the electronic map, which may be "snack", for example.

The server has obtained identification related information of the object of the location point, and the identification related information of the object includes legal information of "lie somewhere" and a merchant name of "# # schlumbergen # coming to trade limited responsibility company". And the server stores the identification association information of the object of the position point with the name of the ' bridge spareribs ' (store-by-store) ' and the POI basic information of the position point in an association manner, and stores the identification association information into the POI knowledge graph to obtain new recording information of the POI knowledge graph.

In the embodiment, in the process of expanding the position point information, the corresponding relationship between the identifier of the position point and the identifier of the object is established according to the feedback information of the position point, so that the position point information is more comprehensive and more accurate. When the identification of the object corresponding to the location point is obtained based on the feedback information of the location point, a method of combining OCR recognition and keyword-based structured extraction may be adopted to obtain a merchant name from a photo of a business license of a merchant, and associate the merchant name with a POI name of the location point in a map, for example, an association relationship is established between a merchant name "# # scholarly # in the business license and a merchant limited responsibility company" and a POI name "bridge" (-bar house) "of the location point in the map, so that a problem that the merchant name on the business license and the POI name displayed in the map in the related art are different can be solved.

In an optional embodiment of the present application, in step S201, a process of acquiring, by the server, the first identifier of the target object and the extension information to be added may be as shown in fig. 9, and includes the following steps:

step S901, a transaction data set of the target object is acquired.

And each transaction data in the transaction data set comprises transaction time information and a first identification of the target object.

For example, the transaction time information may be an hour-level transaction time, the target object may be a target merchant, and the first identification of the target object may be a merchant name of the target merchant. In some embodiments, the server may obtain the transaction data set of the target merchant from the transaction data of the target merchant within the preset time period acquired from the database of the third-party transaction platform. In some other embodiments, the server may further obtain transaction data of all merchants within a preset time period from a database of the third-party transaction platform, and because each transaction data includes a merchant name, the server may divide the obtained transaction data into different transaction data sets according to the merchant name to obtain transaction data sets of multiple merchants, each transaction data set includes transaction data with the same merchant name, and the merchant names of the transaction data included in the different transaction data sets are different. The server may obtain a transaction data set of the target merchant from the plurality of transaction data sets according to the merchant name of the target merchant.

Step S902, according to the transaction time information corresponding to each transaction data in the transaction data set, determining the business information of the target object.

In some alternative embodiments, the business information of the target object may include the business status of the target object. According to the transaction time information corresponding to each transaction data in the transaction data set, the corresponding transaction date in the transaction time information of each transaction data can be obtained, and according to the transaction date corresponding to each transaction data, whether the transaction data exist in a preset time threshold before the current moment every day or not is determined. And if the transaction data exist every day, determining that the business state of the target object is normal business.

Illustratively, the business states include normal business and business intermissions. The server may determine whether the business status of the target merchant is normal business based on whether there is business data every day for a period of time that satisfies a set threshold number of days from the current time, e.g., whether there is business data every day for 7 days.

In some optional embodiments, the business information of the target object includes a daily business time of the target object; the business hours of the target object can be determined according to the transaction time information in each transaction data, and then the daily business hours of the target object can be generated according to the business hours of the target object.

For example, the server may determine the earliest business time and the latest business time of the target merchant according to the hour-level transaction time included in the transaction data set of the target merchant. For example, ignoring the transaction date in each transaction data, only paying attention to the transaction time, if the transaction time in the transaction data is at the earliest of 07:05, it may be determined that the earliest business time of the target merchant is 07: 00; if the transaction time in the transaction data is 21:50 at the latest, the earliest business time of the target merchant may be determined to be 22: 00. And the obtained daily business time information of the target object is 07: 00-22: 00.

For example, for a target merchant with a business government company' with a name of "# # schoolwork #, the business information of the target merchant can be determined by the method, wherein the business information comprises business time of 07: 00-22: 00 per day and normal business state.

And step S903, generating expanded information to be added according to the business information of the target object.

Illustratively, the server may generate the extension information to be added according to the business information of the target object. For example, the business information of the target object is "normal business", and the extended information to be added of the target object may be "normal business".

After the extended information of the target object is obtained, and the second identifier of the target location point corresponding to the target object is found in the location point information relation base obtained in fig. 8, the identified basic information of the target location point in the map can be obtained according to the second identifier, and the extended information and the basic information of the target location point are stored in an associated manner, so that the basic information of the target location point is extended. After the basic information of the target position point is expanded, when the information of the target position point is displayed on the terminal, more information can be displayed.

For example, for a target merchant with a name of "# # scholar # business llc", the second identifier of the target location point corresponding to the target merchant is found to be "bridge spareribs (store)", the business information of the target merchant is stored in association with the basic information of the target location point "bridge spareribs (store)", and the basic information of the target location point is expanded. After the above expansion is completed, as shown in fig. 7, when the terminal displays the information of the target location point "bridge row rib (store), the name of the merchant corresponding to the target location point, the information of the normal business of the merchant, and the business time of each day can be displayed.

In the embodiment, in the process of expanding the position point information, the server determines the business information according to the transaction data and generates the expanded information, and the business information of the method can be updated according to the set period, so that more comprehensive and more accurate travel reference can be provided for the user, and the accuracy, timeliness and completeness of the position point information are improved.

The corresponding relation between the identification of the object in the position point information relation base and the identification of the position point in the map is established based on the feedback information aiming at the position point. For many location points, there may be no information feedback from the user for the location point, so the location point information relation library does not include the identifier of the object corresponding to the location point, that is, does not include the correspondence between the identifier of the location point and the identifier of the object associated therewith. Therefore, in some embodiments, for the obtained first identifier of the target object, a situation that the second identifier of the target location point corresponding to the first identifier of the target object is not found in the location point information relationship library may occur, that is, the target location point associated with the target object is not found in the location point information relationship library.

In the above situation, the method shown in fig. 10 may be used to determine the target location point associated with the target object, and specifically includes the following steps:

step S1001, according to the transaction position information corresponding to each transaction data in the transaction data set, clustering the transaction data of the target object to obtain the transaction center position corresponding to the target object.

Each transaction data in the set of transaction data for the target object includes transaction location information. If the second identifier of the target position point associated with the target object, such as the POI name, is not found in the position point information relation base, the transaction data of the target object may be clustered according to the transaction position information corresponding to each transaction data in the transaction data set, so as to obtain the transaction center position corresponding to the target object.

For example, the transaction location information may be longitude and latitude coordinates of the transaction location, and still taking the target object as the target merchant as an example, if the target merchant uses the scanning terminal to scan the two-dimensional code displayed on the mobile phone of the user for performing the transaction, the transaction location information in the transaction data of the transaction is the longitude and latitude coordinates of the location where the scanning terminal is located or the longitude and latitude coordinates of the location where the mobile phone of the user is located. When the POI name of the target interest point associated with the target merchant is not found in the POI knowledge graph, the transaction data of the target merchant can be clustered according to the transaction position in each transaction data in the transaction data set, so as to obtain the transaction center position corresponding to the target object.

Specifically, in an embodiment, the DBSCAN spatial clustering algorithm may be used to cluster the transaction data of the target merchant, and specifically includes the following steps:

step a, taking the transaction position corresponding to each piece of transaction data of the transaction data set of the target object as a transaction point. In the transaction data set of the target object, one piece of transaction data is arbitrarily selected, and the number of the transaction points included in the vicinity of the transaction point p corresponding to the selected transaction data is determined according to the transaction position information, i.e., the longitude and latitude coordinates, of each piece of transaction data, and the number can be represented as NBHD (p, epsilon). The area adjacent to the transaction point p is a circular area with the transaction point p corresponding to the transaction data as a center of a circle and the set value epsilon as a radius. If the number of transaction points included in the vicinity of the transaction point p is greater than or equal to a set number threshold value minPts, i.e., NBHD (p, epsilon) > minPts, the transaction point is taken as a center point around which a class is established. Otherwise, marking the transaction point corresponding to the transaction data as a peripheral point.

And b, after determining a transaction point corresponding to one transaction data as a central point, traversing the transaction points corresponding to other transaction data in the transaction data set of the target object, adding the transaction points directly reachable by the central point in the class corresponding to the central point, and then adding the transaction points reachable by the central point in the density into the class corresponding to the central point. If the transaction points marked as the peripheral points are added into the classes corresponding to the central points, the state of the transaction points marked as the peripheral points is modified into edge points.

The direct density is reachable, that is, for any two transaction data in the transaction data set of the target object, if the transaction point corresponding to the transaction data a is located in a region adjacent to the transaction point corresponding to the transaction data B, and the transaction point corresponding to the transaction data B is a central point, the transaction point of the transaction data a is directly reachable from the transaction point of the transaction data B.

The density is reachable, that is, for a plurality of transaction data in the transaction data set of the target object, it is assumed that the transaction points corresponding to the transaction data are p respectively₁,p₂....p_n. If there is a point of transaction p_iFrom p_i-1If the direct density is reachable, the transaction point p is reached₁By the point of transaction p_nThe density can be reached.

Step c, taking the transaction points which do not meet the direct density reachable state with the central point and also do not meet the density reachable state as unprocessed transaction points; and (3) randomly selecting one trading point from the unprocessed trading points to judge the trading points: if the transaction point meets the condition of being the central point, taking the transaction point as a new central point, and returning to execute the step b; if the trade point does not meet the condition as the central point, the trade point is marked as a peripheral point, and a next trade point is randomly selected from the unprocessed trade points to carry out the trade point judgment in the step c.

And c, repeatedly executing the step c and the step b until the unprocessed transaction point is empty. And finally, taking the determined central point as the position of the transaction center corresponding to the target object. The transaction center location represents the geographic location of a targeted merchant, which may be a store in a chain.

According to the method, the server can cluster the transaction data of the target merchant to obtain the transaction center position corresponding to the target merchant, the center point determined by clustering is used as the transaction center position corresponding to the target merchant, and noise data represented by peripheral points are filtered out, so that non-store payment data of a user remotely paid by scanning codes are filtered out, only the store payment data are reserved, and the obtained transaction center position can accurately reflect the geographic position of the target merchant.

Step S1002, candidate position points in a preset range around the position of the transaction center are searched in a map, and the identification of each candidate position point is obtained.

Specifically, the server may query the POI index library of the map, obtain a position point in the map, which is located in a preset range around the geographic position of the target object, that is, the target merchant, as a candidate position point, and obtain an identifier of each candidate position point.

The POI index library is a database formed by POI basic information and POI aliases of all position points in an electronic map and comprises POI names, POI aliases and POI coordinates of all the position points. POI aliases are colloquial names of POIs or synonyms of POI names.

For example, the server may query the POI index library to obtain location points in the map within a preset range around the transaction center location corresponding to the target object, as candidate location points, and obtain POI names of the respective candidate location points.

In step S1003, a candidate position point whose mark matches the first mark is selected from the candidate position points as a target position point.

For example, the identification of the candidate location point may be a POI name of the candidate location point, and the first identification of the target object may be a merchant name of the target object. The server may select, as the target location point, a candidate location point whose POI name matches the merchant name from the respective candidate location points.

In an optional embodiment, the POI names of the candidate location points and the merchant names are both texts, and the server may directly compare the text similarity between the POI name of each candidate location point and the merchant name of the target object, and use the candidate location point with the highest text similarity as the target location point.

In another alternative embodiment, considering that the calculation amount of comparing the POI name with the merchant name is large, if comparing the POI name of each candidate location point with the merchant name of the target object one by one, it takes much time. In order to save the calculation time, in step S1003, selecting a candidate position point whose mark matches the first mark from the respective candidate position points as the target position point may include the following steps:

and step C1, under the premise that the mark of the candidate position point and the first mark are both text marks, for each candidate position point, if the mark of the candidate position point and the first mark contain at least one same character, the candidate position point is taken as a reference target position point of the target object.

For each candidate location point, if the POI name of the candidate location point and the merchant name of the target object contain at least one same character, the candidate location point is taken as a reference target location point of the target object.

And step C2, determining the text similarity between the mark of each reference target position point and the first mark.

In an alternative embodiment, the sequence-Bert model, whose structure may be as shown in fig. 12, may be used to determine the text similarity between the identifier of one reference target location point and the first identifier. Specifically, the process of determining the text similarity between the identifier of each reference target location point and the first identifier may be performed with reference to the steps shown in fig. 11. For each reference target position point, the following operations are respectively performed:

step S1101, performing text feature extraction on the first identifier to obtain a first text feature vector.

Wherein the first identification may be a merchant name of the target object. Exemplarily, as shown in fig. 12, an ALBert model may be adopted to perform text feature extraction on the first identifier of the target object, and the obtained text features are subjected to dimensionality reduction by the pooling layer to obtain a first text feature vector u.

Step S1102, performing text feature extraction on the identifier of the reference target location point to obtain a text feature vector of the reference target location point.

The identification of the reference target location point may be a POI name of the reference target interest point. Exemplarily, as shown in fig. 12, an ALBert model may be adopted to perform text feature extraction on an identifier of any one reference target location point, and the obtained text feature is subjected to dimensionality reduction by a pooling layer to obtain a text feature vector v of a reference target interest point.

Step S1103 determines a difference vector between the first text feature vector and the text feature vector of the reference target location point.

Specifically, a difference vector is obtained by the first text feature vector and the text feature vector of the reference target position point according to positions, and a difference vector of the first text feature vector and the text feature vector of the reference target position point is obtained.

For example, as shown in fig. 12, a difference vector is obtained for the first text feature vector u and the text feature vector v of the reference target position point by bit, and a difference vector | u-v | of the first text feature vector u and the text feature vector v of the reference target position point is obtained.

And step S1104, splicing the first text characteristic vector, the text characteristic vector of the reference target position point and the difference vector to obtain a spliced vector.

For example, as shown in fig. 12, a first text feature vector u, a text feature vector v of a reference target position point, and a difference vector | u-v | of the first text feature vector and the text feature vector of the reference target position point are spliced to obtain a spliced vector (u, v, | u-v |).

Step S1105, according to the splicing vector, determining the text similarity between the mark of the reference target position point and the first mark.

Specifically, after the splicing vector is multiplied by a trainable weight, the text similarity between the identifier of the reference target position point and the first identifier is obtained through a softmax classifier.

For example, as shown in FIG. 12, first, the stitching vector (u, v, | u-v |) is multiplied by a trainable weight W_t∈R³ⁿ ^*kTo obtain a spliced input vector W_t(u, v, | u-v |). Where n is the text feature vector dimension and k is the number of categories. Illustratively, n-312 and k-2.

Then, according to the splicing input vector W_t(u, v, | u-v |), obtaining the text similarity o between the identifier of the reference target position point and the first identifier through a softmax classifier:

o＝softmax(W_t(u,v,|u-v|))。

through the method, the text similarity between the identifier of each reference target position point and the first identifier is determined one by one, and for each reference target position point, the text similarity between the identifier of the reference target position point and the first identifier is used as the text similarity corresponding to the reference target position point.

And step C3, selecting the target position points from the reference target position points according to the text similarity corresponding to the reference target position points.

In an alternative embodiment, the reference target position point with the largest similarity and the similarity greater than or equal to the set similarity threshold value among the reference target position points may be used as the target position point.

In another alternative embodiment, the reference target position points whose similarity is greater than or equal to the set similarity threshold value among the respective reference target position points may be used as the target position points.

In another alternative embodiment, the reference target position point with the maximum similarity among the respective reference target position points may be used as the target position point.

In an alternative embodiment, in consideration that a same target merchant may have multiple stores, at this time, there may be multiple target location points associated with one target object in the location point information relationship library, and in order to accurately obtain a target location point, in the location point information relationship library, in addition to storing the POI names of the respective target location points, POI coordinates of the respective target location points may also be stored. In step S302, the process of searching for the second identifier of the target location point associated with the target object in the location point information relationship library according to the first identifier may include: searching a plurality of identifications of candidate target position points corresponding to the target object in the position point information relation base, acquiring the geographical position of each candidate target position point according to the identification of each candidate target position point, and determining the distance between the geographical position of each candidate target position point and the position of a transaction center corresponding to the target object; and taking the candidate target position point with the closest distance as a target position point, and taking the mark of the target position point as a second mark.

For example, if according to the merchant name of the target object, the POI names of a plurality of candidate target location points corresponding to the target object are found in the location point information relation base, and according to the POI names of the candidate target location points, the POI coordinates of the candidate target location points are obtained; taking the position of the transaction center corresponding to the target object as the merchant coordinate of the target object, and determining the distance between the POI coordinate of each candidate target position point and the merchant coordinate of the target object; and taking the candidate target position point with the closest distance as a target position point, and taking the POI name of the target position point as a second identifier. That is, the server may search the POI name of the target location point associated with the target object in the location point information relationship library according to the merchant name and the merchant coordinates of the target object.

In the process of expanding the location point information, if the identifiers of a plurality of candidate target location points corresponding to the target object are found in the location point information relation library in the embodiment; and acquiring the geographic position of each candidate target position point according to the identifier of each candidate target position point, determining the distance between the geographic position of each candidate target position point and the position of the transaction center corresponding to the target object, taking the candidate target position point with the closest distance as the target position point, and taking the identifier of the target position point as a second identifier. According to the method, when a target merchant has a plurality of shops, the POI name of the corresponding shop of the merchant can be accurately selected for the target merchant, and the obtained position point information is more accurate, so that more comprehensive and accurate travel reference can be provided for a user, and the accuracy, timeliness and completeness of the position point information are improved.

In order to more conveniently understand the location point information extension method of the embodiment of the present application, fig. 13 shows a specific implementation process of the embodiment of the present application. As shown in fig. 13, the process includes the steps of:

step S1301, obtaining a transaction data set of the target merchant from the obtained transaction data.

The server may obtain a large amount of transaction data from a third party transaction platform, including transaction data for a plurality of merchants. Each transaction data may include a merchant ID, a merchant name, transaction coordinates, and hour-level transaction time. The trading coordinate is the coordinate of the trading position determined by the longitude value and the latitude value when the user carries out trading through the third-party trading platform. The server may divide the acquired transaction data into different transaction data sets according to the merchant names to obtain transaction data sets of multiple merchants, where each transaction data set includes transaction data with the same merchant name, and the merchant names of the transaction data included in different transaction data sets are different. The server may optionally select one merchant as a target merchant, and use the transaction data set of the merchant as the transaction data set of the target merchant.

Step S1302, clustering the transaction data in the transaction data set according to the transaction coordinates corresponding to each transaction data in the transaction data set of the target merchant, so as to obtain a transaction center position corresponding to the target merchant.

Step S1303, determining business information of the target merchant according to the transaction time information corresponding to each transaction data in the transaction data set of the target merchant.

In some embodiments, the business information of the target merchant may include the business state of the target merchant, such as whether the target merchant is normally open or not. In other embodiments, the business information of the target merchant may include the daily business hours of the target merchant. The process of determining the business information of the target merchant is described in detail above, and will not be described herein again.

Assuming that the merchant name of the target merchant is "@ Runzhong river city store", the target location point POI corresponding to the target merchant is labeled ". Runzhong river city store", the business state of the target merchant is "in business", and the daily business time is "07: 30-21: 30".

The order of step S1302 and step S1303 may be interchanged.

Step S1304, according to the merchant name of the target merchant, searching a POI identification of the target position point associated with the target merchant in the POI knowledge map.

The POI knowledge graph can be understood as a specific form of the above location point information relation library, and can be used for storing the corresponding relation among the merchant name, the corporate information and the basic POI information, and the basic POI information includes the POI identifier. The POI knowledge graph is updated regularly by the server according to information fed back by a map user aiming at the POI of the map interest point and POI basic information of the POI of the map interest point.

Let the merchant name of the target merchant be "@ moisten river city store", and the POI identifier of the target location point corresponding to the target merchant is "@ moisten milk industry (@ river city store)". Before the expansion of the embodiment of the present application is completed, as shown in fig. 14, when the terminal displays information of a target location point ". dot.a milk industry (. dot.river city store)", a POI identifier corresponding to the target location point may be displayed.

In an embodiment, in consideration that a plurality of stores are provided under the same merchant name and the geographic locations of the stores are different, the POI knowledge map may be queried according to the merchant name of the target merchant and the transaction center location of the target merchant, so as to determine a target location point associated with the target merchant, that is, which store the target merchant is specifically determined.

For example, the server may query the POI knowledge map based on the merchant name of the target merchant, determine a POI point closest to the transaction center location of the target merchant, and use the POI point closest to the transaction center location as a target location point associated with the target merchant.

Step S1305, if the POI identifier of the target location point associated with the target merchant is not found in the POI knowledge map, finding candidate location points located in a preset range around the transaction center location in the map, and using candidate location points where the POI identifier and the merchant name of the target merchant satisfy a preset condition among the candidate location points as reference target location points.

Specifically, a POI index library of the map may be queried, where POI identifiers and location information of each location point are stored in the POI index library, and a POI identifier of a candidate location point located in a preset range around a location of a transaction center may be searched according to the location of the transaction center of a target merchant, where the POI identifier may be a POI name or a POI alias. And segmenting the merchant name of the target merchant to obtain the key information of the merchant name.

In an embodiment, the preset conditions may include:

and the word or single word obtained by segmenting the POI identification of the candidate position point is at least one same as the key information of the business name of the target business.

In another embodiment, the preset conditions may include:

and the top N candidate position points which are closest to the transaction center position of the target merchant, wherein N is a preset recall quantity threshold value.

In another embodiment, the preset conditions may include:

the similarity of the business name key information of the target business is more than a preset recall threshold.

The similarity can be obtained by respectively performing word segmentation and word steering amount processing on the POI identification of the candidate position point and the merchant name key information of the target merchant, and then calculating the cosine similarity between word vectors contained in the POI identification and the merchant name key information of the target merchant.

The word Vector may also be referred to as a word Vector feature, is used to describe semantic features of words included in a natural language text, and generally refers to a Dense Vector (Dense Vector) or a matrix form that can be understood by a machine, which is obtained by Vector-converting words represented by a natural language, and the word Vector is a representation of words in the natural language text in a numeric manner in the machine. It is also understood that mathematical embedding from a one-dimensional space of each word, word or phrase to a continuous vector space with lower dimensions.

In step S1306, a candidate location point whose POI identifier matches with the merchant name of the target merchant is selected from the reference target location points as a target location point.

Specifically, with reference to the method shown in fig. 12, text similarity between the POI identifier of each reference target location point and the business name key information of the target business is determined, and the reference target location point with the highest similarity and the similarity greater than or equal to a set similarity threshold is used as the target location point. For example, assuming that the merchant name of the target merchant or the key information of the merchant name of the target merchant is "# moist × river city store", the reference target location point corresponding to the target merchant includes a location point identified as "# moist milk industry (# river city store)", and after comparing the "# moist milk industry (# river city store)" with the "# moist × river city store", it is determined that the text similarity of the two is 93%, which is greater than the set similarity threshold value of 80%, and is the reference target location point with the maximum similarity, and therefore, the location point identified as "# moist milk industry (# river city store)" may be used as the target location point associated with the target merchant. The method fully considers the multi-semantic relation among texts, and can relieve the problem of matching failure caused by adopting a text hard matching method with completely identical texts in the related technology.

Step S1307, acquiring the basic information of the target location point identified in the map, and storing the business information of the target merchant and the basic information of the target location point in an associated manner.

The basic information of the target position point, which is identified in the map, can be obtained according to the identification of the target position point, the business information of the target merchant is added into the basic information of the target position point, the business information and the basic information are stored in an associated manner, and the basic information of the target position point is expanded, so that when the identification information of the target position point is displayed by the terminal, the expanded information can be displayed.

Illustratively, assume that the POI is identified as POI number 19195221678405761621 for the location point of the "wet milk industry (river city shop)". In the basic POI information of the location point, the POI number is 19195221678405761621, the POI name may be "(" city of river store) ", the POI coordinate is the coordinate determined by the longitude value and the latitude value of the central point of the location point with the name" ("city of river store)", the POI address is "(" city of red star 30 ", and the POI classification is the default classification of the merchant name corresponding to the location point in the electronic map, and may be" food supermarket ", for example.

The server has already obtained the identification associated information of the merchant corresponding to the location point, for example, the identification associated information of the merchant includes the information of a legal person "something Zhao", and the name of the merchant is "the milk industry, commerce and trade, but liability company". After the extension described in the embodiment of the present application is completed, as shown in fig. 15, when the terminal displays information of a target location point ". the dairy industry (. the river city store)", a name of a merchant corresponding to the target location point, information of normal business of the merchant, and business time per day may be displayed. Thus, more comprehensive and accurate reference information can be provided for the user.

Although the embodiments of the present application provide the operational steps of the method as shown in the above embodiments or figures, more or less operational steps may be included in the method based on conventional or non-inventive efforts. In steps where no necessary causal relationship exists logically, the order of execution of these steps is not limited to the order of execution provided by the embodiments of the present application. The method may be executed in sequence or in parallel according to the method shown in the embodiment or the figures when the method is executed in an actual processing procedure or an apparatus.

Based on the same inventive concept, the embodiment of the application also provides a position point information expansion device, and the position point information expansion device can be arranged in a server. Because the device is a device corresponding to the location point information expansion method applied to the server in the embodiment of the present application, and the principle of the device for solving the problem is similar to that of the method, the implementation of the device may refer to the implementation process of the above method embodiment, and repeated details are not described again.

Fig. 16 is a schematic structural diagram illustrating a location point information extension apparatus according to an embodiment of the present application. The location point information extension apparatus, applied to the server 400, as shown in fig. 16, includes: a first data acquisition unit 1601, a data querying unit 1602, a second data acquisition unit 1603, and an information expansion unit 1604; wherein the content of the first and second substances,

a first data obtaining unit 1601, configured to obtain a first identifier of a target object and extension information to be added;

a data query unit 1602, configured to search, according to the first identifier, a second identifier of a target location point associated with the target object in the location point information relationship library; the position point information relation library is used for storing the corresponding relation between the mark of the object and the mark of the position point in the map;

a second data obtaining unit 1603, configured to obtain, according to the second identifier, basic information that the target location point has been identified in the map;

an information extension unit 1604, configured to associate and store the extension information and the basic information for the target location point, and obtain corresponding target information.

In an alternative embodiment, the information extension unit 1604 is further configured to:

and sending the target information to the first terminal based on an information acquisition request sent by the first terminal aiming at the target position point, so that the first terminal displays the target information aiming at the target position point in the map.

In an alternative embodiment, the data query unit 1602 is further configured to:

acquiring an identifier of a position point in a map;

and storing the corresponding relation between the identification of the object and the identification of the position point into a position point information relation library.

In an alternative embodiment, the feedback information of a location point includes a license image of the object corresponding to the location point; the data query unit 1602 is specifically configured to:

character recognition is carried out on the license image to obtain license character information of an object corresponding to a position point;

and acquiring the identification of the object corresponding to one position point from the license text information of the object.

In an alternative embodiment, the first data obtaining unit 1601 is specifically configured to:

acquiring a transaction data set of a target object; each transaction data in the transaction data set comprises transaction time information and a first identification of a target object;

and generating expanded information to be added according to the business information of the target object.

In an alternative embodiment, each transaction data further includes transaction location information; second data obtaining unit 1603, further configured to:

if the second identification of the target position point associated with the target object is not found in the position point information relational database, clustering the transaction data of the target object according to the transaction position information corresponding to each transaction data in the transaction data set to obtain the transaction center position corresponding to the target object;

searching candidate position points in a preset range around the position of a transaction center in a map, and acquiring the identification of each candidate position point;

and selecting a candidate position point with the identifier matched with the first identifier from the candidate position points as a target position point.

In an optional embodiment, the identifier of the candidate position point and the first identifier are both text identifiers; the second data obtaining unit 1603 is specifically configured to:

and selecting a target position point from the reference target position points according to the text similarity corresponding to the reference target position points.

In an alternative embodiment, the second data obtaining unit 1603 is specifically configured to:

determining a difference vector between the first text feature vector and a text feature vector of a reference target position point;

taking the reference target position point with the maximum similarity in all the reference target position points as a target position point; alternatively, the first and second electrodes may be,

taking the reference target position points with the similarity greater than or equal to a set similarity threshold value in all the reference target position points as target position points; alternatively, the first and second electrodes may be,

and taking the reference target position point with the maximum similarity and the similarity larger than or equal to the set similarity threshold value in all the reference target position points as the target position point.

In an alternative embodiment, the business information includes daily business hours; the first data obtaining unit 1601 is specifically configured to:

determining the earliest operating time and the latest operating time of the target object according to the transaction time information in each transaction data;

In an alternative embodiment, the business information includes business status; the first data obtaining unit 1601 is specifically configured to:

and if the fact that the transaction data exist every day within the preset time threshold before the current moment is determined according to the transaction date corresponding to each transaction data, determining that the business state of the target object is normal business.

In an alternative embodiment, the data query unit 1602 is specifically configured to:

and taking the candidate target position point with the closest distance as a target position point, and taking the mark of the target position point as a second mark.

Based on the same inventive concept, the embodiment of the application also provides the electronic equipment. In one embodiment, the electronic device may be the server 400 of FIG. 1. In this embodiment, the electronic device may be configured as shown in FIG. 17, and may include a memory 1701, a communication module 1703, and one or more processors 1702.

The memory 1701 is used to store computer programs executed by the processor 1702. The memory 1701 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, a program required for running an instant messaging function, and the like; the storage data area can store various instant messaging information, operation instruction sets and the like.

The memory 1701 may be a volatile memory (volatile memory), such as a random-access memory (RAM); the memory 1701 may also be a non-volatile memory (non-volatile memory) such as, but not limited to, a read-only memory (rom), a flash memory (flash memory), a hard disk (HDD) or a solid-state drive (SSD), or the memory 1701 may be any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory 1701 may be a combination of the above memories.

The processor 1702, may include one or more Central Processing Units (CPUs), a digital processing unit, and so on. The processor 1702 is configured to implement the above-described location point information extension method when calling a computer program stored in the memory 1701.

The communication module 1703 is used for communicating with a terminal device or other servers.

The embodiment of the present application does not limit the specific connection medium among the memory 1701, the communication module 1703 and the processor 1702. In the embodiment of the present application, the memory 1701 and the processor 1702 are connected by the bus 1704 in fig. 17, the bus 1704 is shown by a thick line in fig. 17, and the connection manner between other components is merely illustrative and not limited. The bus 1704 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 17, but this does not mean only one bus or one type of bus.

The memory 1701 stores therein a computer storage medium having stored therein computer-executable instructions for implementing the location point information extension method of the embodiment of the present application. The processor 1702 is configured to perform the above-described location point information extension method.

The embodiment of the application also provides a computer storage medium, wherein computer-executable instructions are stored in the computer storage medium and used for realizing the location point information expansion method described in any embodiment of the application.

In some possible embodiments, various aspects of the location point information extension method provided by the present application may also be implemented in the form of a program product including program code for causing a computer device to perform the steps of the location point information extension method according to various exemplary embodiments of the present application described above in this specification when the program product is run on a computer device, for example, the computer device may perform the flow of the location point information extension method of steps S201 to S204 shown in fig. 2.

Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application.

Claims

1. A method for extending location point information, the method comprising:

acquiring a transaction data set of a target object; each transaction data in the transaction data set comprises transaction time information and a first identification of the target object;

generating expanded information to be added of the target object according to the business information of the target object;

2. The method according to claim 1, wherein the extended information and the basic information are stored in association with each other for the target location point, and after obtaining corresponding target information, the method further comprises:

3. The method according to claim 1, wherein the correspondence between the identifier of the object in the location point information relation library and the identifier of the location point in the map is established by the following method:

acquiring the identifier of the position point in the map;

4. The method according to claim 3, wherein the feedback information of the location points includes license images of the objects corresponding to the location points; based on the feedback information of the position point, acquiring an identifier of an object corresponding to the position point, including:

performing character recognition on the license image to obtain license character information of the object corresponding to the position point;

and acquiring the identification of the object corresponding to the position point from the license text information of the object.

5. The method of claim 1, wherein each transaction data further comprises transaction location information; before storing the extended information and the basic information in association with each other for the target location point, the method further includes:

6. The method of claim 5, wherein the identification of the candidate location point and the first identification are both textual identifications; selecting, as the target location point, a candidate location point whose identifier matches the first identifier from the respective candidate location points, including:

7. The method of claim 6, wherein determining the textual similarity between the identity of each of the reference target location points and the first identity comprises:

8. The method of claim 6, wherein selecting the target location point from each reference target location point according to the text similarity corresponding to the reference target location point comprises:

taking the reference target position point with the maximum text similarity in all the reference target position points as the target position point; alternatively, the first and second electrodes may be,

taking the reference target position points with the text similarity greater than or equal to a set similarity threshold value in all the reference target position points as the target position points; alternatively, the first and second electrodes may be,

and taking the reference target position point with the maximum text similarity and the text similarity larger than or equal to a set similarity threshold value in all the reference target position points as the target position point.

9. The method of claim 1, wherein the business information includes daily business hours; determining business information of the target object according to the transaction time information in each transaction data, wherein the business information comprises:

10. The method of claim 1, wherein the business information includes business status; determining business information of the target object according to the transaction time information in each transaction data, wherein the business information comprises:

11. The method of claim 5, wherein searching a location point information relationship base for a second identifier of a target location point associated with the target object according to the first identifier comprises:

12. A location point information extension apparatus, characterized in that the apparatus comprises:

the first data acquisition unit is used for acquiring a transaction data set of a target object; each transaction data in the transaction data set comprises transaction time information and a first identification of the target object; determining business information of the target object according to the transaction time information corresponding to each transaction data in the transaction data set; generating expanded information to be added of the target object according to the business information of the target object;

13. A computer-readable storage medium having a computer program stored therein, the computer program characterized by: the computer program, when executed by a processor, implements the method of any of claims 1-11.

14. An electronic device comprising a memory and a processor, the memory having stored thereon a computer program operable on the processor, the computer program, when executed by the processor, implementing the method of any of claims 1-11.