CN111949834B

CN111949834B - Site selection method and site selection platform system

Info

Publication number: CN111949834B
Application number: CN201910413579.7A
Authority: CN
Inventors: 王一鸣; 杨柳桦樱; 马晓甦; 刘威良; 朱祎; 王志永
Original assignee: Jiaxing Shurong Data Technology Co ltd
Current assignee: Jiaxing Shurong Data Technology Co ltd
Priority date: 2019-05-17
Filing date: 2019-05-17
Publication date: 2024-04-05
Anticipated expiration: 2039-05-17
Also published as: CN111949834A

Abstract

The application discloses a site selection method and a site selection platform system, which are characterized in that an ontology-based city data model and a database are formed by carrying out data processing on acquired city multi-source data, then a multi-target site selection evaluation system is established based on the industry characteristics of target objects, related indexes are calculated, a site selection field knowledge graph based on space is associated, and site selection strategies and site selection operations of the target objects are provided in an interactive visual mode. Compared with the prior art, the method can improve the site selection efficiency, avoid the site selection risk, provide more valuable site selection decision schemes and improve the site selection success rate.

Description

Site selection method and site selection platform system

Technical Field

The present application relates to the field of big data technologies, and in particular, to an address selection method, an address selection platform system, a computer system, and a computer readable storage medium.

Background

In business, layout addressing of a business is an important decision-making matter for the business. Optimizing the site will generally attract more customers than random site selection, resulting in greater economic benefits. In the decision making process, a large amount of relevant information needs to be acquired, such as the geographical location of the area to be selected, the surrounding environment, the level and habit of residential consumption, the location and experience status of other shops of the same type, etc.

Traditionally, shop site selection is performed manually. For example: determining site selection conditions according to commercial types of merchants; roughing part of the target area according to the site selection condition; collecting data by a large amount of manpower, including geographic location of a target area, surrounding facility information, traffic information, people stream information and the like; and analyzing the collected data to make a decision of selecting addresses, and when the range of the target area to be selected is large, roughly framing the target area to be selected into a plurality of candidate areas with relatively small ranges, and then analyzing the candidate areas by utilizing a large amount of manpower to collect the data.

According to the method, the data are manually collected and analyzed to select the address, so that the labor cost and the time cost are greatly increased, the risk of error address selection is increased due to inaccurate data, and the high-efficiency decision requirement of the modern society cannot be met.

Disclosure of Invention

In view of the above-mentioned drawbacks of the related art, an object of the present application is to provide an address selection method, an address selection platform system, a computer system, and a computer readable storage medium, for solving the problems of time and effort consuming and poor address selection success rate in the related address selection decision.

To achieve the above and other objects, a first aspect of the present application discloses an address selection method, including the steps of: acquiring multi-source data, performing data processing on the multi-source data, and perfecting an ontology-based city data model to form a basic database; establishing a multi-target site selection evaluation system based on the industry characteristics of the target object and the basic database; based on the basic database and the multi-target site selection evaluation system, a site selection knowledge graph based on space is constructed, and the site selection strategy and site selection operation of the target object are provided in an interactive visual mode.

In certain embodiments of the first aspect of the present application, the step of performing data processing on the multi-source data to refine the ontology-based city data model includes: establishing an ontology-based city data model related to site selection decision behaviors; extracting characteristic parameters related to site selection decision from the multi-source data, and grabbing data related to the characteristic parameters from the multi-source data; and generating basic attributes and labels based on the data model of the target object and the grabbed data related to the characteristic parameters.

In certain embodiments of the first aspect of the present application, the method for locating further comprises the step of data cleansing and data fusion of the captured data related to the feature type.

In certain embodiments of the first aspect of the present application, the data sources of the multi-source data include external data sources and self-contained data sources.

In certain embodiments of the first aspect of the present application, the data in the external data source comprises one or more of land data describing an urban as-built environment, map road network data, traffic infrastructure data and its traffic flow data, map point of interest data, operator data describing individual behavior, and property mediation data.

In certain embodiments of the first aspect of the present application, the external data source is acquired by at least one of: collecting from network resources through a data collection program; obtained from at least one database, the database including a public database and a private database.

In certain embodiments of the first aspect of the present application, the data in the self-contained data source includes one or more of sales data, passenger flow data, and in-sales data.

In certain embodiments of the first aspect of the present application, the step of establishing a multi-objective site selection evaluation system based on the industry characteristics of the objective object and the base database includes: determining an impact factor associated with the addressing decision from the base database based on the industry characteristics of the target object; determining the attribute and the label of the influence factor; and carrying out numerical processing on the attribute of the influence factor and the label.

In certain embodiments of the first aspect of the present application, the impact factor comprises at least one of: demographic data, block data, commercial point of interest distribution data, traffic facility and service level and traffic flow data, passenger flow data, and bid data.

In certain embodiments of the first aspect of the present application, the method for addressing further includes a step of acquiring space-based tile information based on the multi-objective addressing evaluation system.

In certain embodiments of the first aspect of the present application, the step of obtaining the block information based on the multi-target addressing evaluation system includes: fusing the space data, and redefining the area space to form a plurality of blocks; assigning attributes and labels to the plurality of defined blocks based on the multi-target addressing evaluation system; and carrying out numerical processing on the attributes and the labels of each block.

In certain embodiments of the first aspect of the present application, the method further includes a step of performing data interpolation on the block with the missing data support.

In certain embodiments of the first aspect of the present application, the location method further comprises a step of performing operation index prediction before constructing the space-based location knowledge graph.

In certain embodiments of the first aspect of the present application, the step of performing operation index prediction includes: and predicting the prediction result of the target object in each block according to the self operation data of the target object, the operation data of the bid and/or the operation index of the industry to which the target object belongs and combining the attribute and the label of each block.

A second aspect of the present application discloses an addressing platform system comprising: the database creation unit is used for carrying out data processing on the acquired multi-source data and perfecting the city data model based on the ontology so as to form a basic database; an evaluation system establishing unit for establishing a multi-target site selection evaluation system based on the industry characteristics of the target object and the basic database; the site selection knowledge graph construction unit is used for constructing a site selection knowledge graph based on the basic database and the multi-target site selection evaluation system; and the visual processing unit is used for displaying the space-based addressing knowledge graph in an interactive visual mode so as to provide an addressing strategy and addressing operation of the target object.

In certain embodiments of the second aspect of the present application, the database creation unit performs data processing on the multi-source data, and the manner of perfecting the ontology-based city data model includes: establishing an ontology-based city data model related to site selection decision behaviors; in the city data model, the relation of related systems such as city building environment, individual behaviors and the like is described; extracting characteristic parameters related to site selection decision from the multi-source data, and grabbing data related to the characteristic parameters from the multi-source data; and generating basic attributes and labels based on the data model of the target object and the grabbed data related to the characteristic parameters.

In certain embodiments of the second aspect of the present application, the database creation unit is further configured to perform data cleansing and data fusion on the captured data related to the feature type.

In certain embodiments of the second aspect of the present application, the data sources of the multi-source data include external data sources and self-contained data sources.

In certain embodiments of the second aspect of the present application, the data in the external data source comprises one or more of land data describing an urban as-built environment, map road network data, traffic infrastructure data and its traffic flow data, map point of interest data, operator data describing individual behavior, and property mediation data.

In certain embodiments of the second aspect of the present application, the external data source is obtained by at least one of: collecting from network resources through a data collection program; obtained from at least one database, the database including a public database and a private database.

In certain embodiments of the second aspect of the present application, the data in the self data source includes one or more of sales data, passenger flow data, and in-sales data.

In certain embodiments of the second aspect of the present application, the manner in which the evaluation system establishment unit establishes the multi-objective site selection evaluation system based on the industry characteristics of the objective object and the base database includes: determining an impact factor associated with the addressing decision from the base database based on the industry characteristics of the target object; determining the attribute and the label of the influence factor; and carrying out numerical processing on the attribute of the influence factor and the label.

In certain embodiments of the second aspect of the present application, the influencing factor comprises at least one of: demographic data, block data, commercial point of interest distribution data, traffic facility and service level and traffic flow data, passenger flow data, and bid data.

In some embodiments of the second aspect of the present application, the location platform system further includes a spatial fusion unit, configured to obtain space-based block information based on the multi-target location evaluation system.

In some embodiments of the second aspect of the present application, the spatial fusion unit obtains the block information based on the multi-objective addressing evaluation system by: fusing the space data, and redefining the area space to form a plurality of blocks; assigning attributes and labels to the plurality of defined blocks based on the multi-target addressing evaluation system; and carrying out numerical processing on the attributes and the labels of each block.

In some embodiments of the second aspect of the present application, the spatial fusion unit is further configured to perform data interpolation on a block that lacks data support.

In certain embodiments of the second aspect of the present application, the location platform system further includes a prediction unit, configured to perform operation index prediction.

In certain embodiments of the second aspect of the present application, the manner in which the prediction unit performs operation index prediction includes: and predicting the prediction result of the target object in each block according to the self operation data of the target object, the operation data of the bid and/or the operation index of the industry to which the target object belongs and combining the attribute and the label of each block.

A third aspect of the present application discloses a computer system comprising:

a storage device for storing at least one program;

an interface device;

and the processing device is connected with the storage device and the interface device, wherein the processing device is integrated with a trusted processing environment, and the processing environment executes the addressing method according to the stored at least one program.

A fourth aspect of the present application discloses a computer readable storage medium storing computer instructions that when invoked participate in performing an addressing method as previously described.

According to the site selection method, the site selection platform system, the computer system and the computer readable storage medium, the acquired multi-source data are subjected to data processing, a basic database is formed based on an ontology city data model, a multi-target site selection evaluation system is built based on the industry characteristics of a target object and the basic database, so that a site selection knowledge graph based on space is built, and the site selection strategy and site selection operation of the target object are provided in an interactive visual mode. Compared with the prior art, the method can improve the site selection efficiency, avoid the site selection risk, provide more valuable site selection decision schemes and improve the site selection success rate.

Drawings

FIG. 1 is a flow chart of an embodiment of the addressing method of the present application.

Fig. 2 shows a schematic diagram of the refinement procedure of step S101.

Fig. 3 shows a schematic diagram of the refinement procedure of step S103.

FIG. 4 is a flow chart of the addressing method according to another embodiment of the present application.

Fig. 5 shows a schematic diagram of the refinement procedure of step S104.

Fig. 6 is a schematic flow chart of an address selecting method according to another embodiment of the present application.

Fig. 7 is a schematic diagram showing space-based addressing information based on the addressing method of the present application.

FIG. 8 is a schematic diagram of an embodiment of the addressing platform of the present application.

Fig. 9 is a schematic structural diagram of an address selecting platform according to another embodiment of the present application.

Detailed Description

Further advantages and effects of the present application will be readily apparent to those skilled in the art from the present disclosure, by describing the embodiments of the present application with specific examples.

In the following description, reference is made to the accompanying drawings, which describe several embodiments of the present application. It is to be understood that other embodiments may be utilized and that compositional and operational changes may be made without departing from the spirit and scope of the present disclosure. The following detailed description is not to be taken in a limiting sense, and the scope of embodiments of the present application is defined only by the claims of the patent of the present application. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

Furthermore, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise. For example, in the present application, the term "at least one client" includes a case of one client and a plurality of clients, or the term "at least one content presentation device" includes a case of one content presentation device and a plurality of content presentation devices. It will be further understood that the terms "comprises," "comprising," "includes," and/or "including" specify the presence of stated features, steps, operations, elements, components, items, categories, and/or groups, but do not preclude the presence, presence or addition of one or more other features, steps, operations, elements, components, items, categories, and/or groups. The terms "or" and/or "as used herein are to be construed as inclusive, or meaning any one or any combination.

In business, the location of a business is one of the most important factors affecting the business's operating conditions. Therefore, layout and addressing of the shops is an important decision. Traditionally, most of site selection work is to manually realize market research, data arrangement, stepping point investigation and subjective decision, the whole decision process is low in efficiency, and site selection is likely to be low due to factors such as insufficient information acquisition or knowledge level of a decision maker.

In view of this, the application discloses a method and platform system for selecting addresses, which processes acquired multi-source data, forms a basic database based on an urban data model of an ontology, and establishes a multi-target evaluation system for selecting addresses based on industry characteristics of target objects and the basic database, thereby constructing a space-based knowledge graph for selecting addresses, providing a method and strategy for selecting addresses of target objects, and visually displaying the method and strategy for providing various quantized decision schemes for selecting addresses, and solving the problems of time and effort waste, poor success rate of selecting addresses and the like in the existing related decision for selecting addresses.

Referring to fig. 1, a flow chart of an address selecting method according to an embodiment of the present application is shown. The addressing method shown in fig. 1 is used for effectively integrating the acquired multi-source data according to the addressing request of the corresponding target object, and thus constructing a space-based addressing knowledge graph, and providing various quantized addressing decision schemes for users.

Embodiments of the method for locating disclosed in the embodiments of the present application may be performed in a computer system including a storage device, a processing device, an interface device, etc., where the computer system may be a single computer device, a computer cluster, or a service system based on a cloud architecture, etc. The single computer device may be an autonomously configured terminal device capable of executing the methods of the present application, and may be located in a private machine room or a rented machine location in a public machine room, for example, a client may be used on a user side, or may be a remote server, or may be a data service provided by a special or third party. The terminal device may include various types of devices, such as a smart phone, a tablet computer, an intelligent wearable device, a vehicle-mounted device, a self-service device, and the like, where corresponding APP (application) implementing the method/apparatus of the embodiments of the present specification may be installed on these devices. The computer clusters may be a group of mutually independent computer devices interconnected through a high-speed network, which form a group and are managed in a single system mode. The Cloud architecture Service system comprises a Public Cloud (Public Cloud) Service end and a Private Cloud (Private Cloud) Service end, wherein the Public Cloud Service end or the Private Cloud Service end comprises Software-as-a-Service (Software as a Service for short, saaS), platform-as-a-Service (Platform as a Service for short, paaS), infrastructure-as-a-Service (Infrastructure as a Service for short, iaaS) and the like. The public cloud service platform is, for example, an ali cloud computing service platform, a microsoft Azure cloud computing service platform, an amazon AWS (Amazon Web Service) cloud computing service platform, a hundred-degree cloud computing platform, a communication cloud computing platform and the like.

According to the hardware device for actually executing the methods, each device constituting the computer system may be located on a single server or located in a plurality of servers and completed cooperatively through data communication between the servers.

For this purpose, the interface device is connected to the processing device in a data manner, which can be connected via a bus or can be data-transferred via a communication network. To this end, the interface means include, but are not limited to, a network card, a mobile network access module, a bus interface connected to the processing means via a bus, etc. For example, the interface device of the corresponding second computer system is communicatively connected to the interface device of the first computer system, the interface device of the user equipment, and the like. The interface devices communicate data through the Internet, a mobile network and a local area network.

The storage device is used for storing at least one program capable of executing any one or more of the methods. The storage means corresponding to the same computer system may be located on the same physical server as the processing means or in different physical servers and the program is transferred to the processing means running the program via the interface means of each server. The storage may include high-speed random access memory, and may also include non-volatile memory, such as one or more disk storage devices, flash memory devices, or other non-volatile solid-state storage devices. In some embodiments, the memory may also include memory remote from the one or more processors, such as network-attached memory accessed via RF circuitry or external ports and a communication network (not shown), which may be the internet, one or more intranets, a Local Area Network (LAN), a wide area network (WLAN), a Storage Area Network (SAN), etc., or suitable combinations thereof. The storage also includes a memory controller that can control access to memory by other components of the device, such as the CPU and peripheral interfaces. Among other software components stored in the storage device include an operating system, a communication module (or instruction set), a text input module (or instruction set), and an application (or instruction set).

The processing device is operatively coupled with the storage device. More specifically, the processing apparatus may execute programs stored in the memory and/or the nonvolatile storage device to perform operations in the task platform. As such, the processing device may include one or more general purpose microprocessors, one or more application specific processors (ASICs), one or more field programmable logic arrays (FPGAs), or any combinations thereof. Wherein, the plurality of CPUs contained in the processing device can be positioned in the same entity server or distributed in a plurality of entity servers, and realize data communication by means of the interface device so as to cooperatively execute the steps of each method.

The following describes embodiments of the present specification taking a specific application scenario of store site selection as an example. Although the description provides methods and apparatus structures as shown in the examples or figures described below, more or fewer steps or modular units may be included in the methods or apparatus, whether conventionally or without inventive effort. In the steps or the structures where there is no necessary causal relationship logically, the execution order of the steps or the module structure of the apparatus is not limited to the execution order or the module structure shown in the embodiments or the drawings of the present specification. The described methods or module structures may be implemented in a device, server or end product in practice, in a sequential or parallel fashion (e.g., parallel processor or multi-threaded processing environments, or even distributed processing, server cluster implementations) as shown in the embodiments or figures.

Of course, the following description of the embodiments does not limit other extensible technical solutions based on the present specification. For example, one or more embodiments of the present description may be applicable to the locating of physical stores in the general retail industry, where target location refers to store location, which typically refers to a location where commercial activities are conducted, typically a fixed building location. In other implementation scenarios, the embodiments provided in this disclosure may be applied to implementation scenarios of other commercial target object site selection, such as temporary mobile booth sales promotion venues, billboard placement sites, self-service vending machine/ATM/car charging posts or the like, or non-commercial target object site selection, such as signage building site selection, artistic statue placement addresses, mobile blood collection site docking sites, and the like. In the addressing application scenario including the above examples, it should be understood that the changes of the object acting on the addressing in the "target object addressing" in the embodiments of the present specification still fall within the scope of the implementations claimed in the present specification.

As shown in fig. 1, the addressing method of the present application may include the following steps:

Step S101, multi-source data are acquired, data processing is carried out on the multi-source data, and an ontology-based city data model is perfected to form a basic database.

For data sources, the multi-source data source is not limited and may be derived from one or more data sources. In practical applications, the data sources of the multi-source data may include, for example, external data sources and self-contained data sources.

For data content, in some examples, the data in the external data sources is related to a city, which may include one or more of land data describing the city build environment, map road network data, traffic infrastructure data and its traffic flow data, map point of interest data, operator data describing individual behavior, and property intermediation data. The data in the self data source may include one or more of sales data, passenger flow data, and in-sales data.

In certain exemplary embodiments, the data in the external data source may be collected from the network resource by a data collection program.

For example, data collection is performed on network resources using a written data collection program. Generally, a data acquisition program is a program or script that automatically captures network information according to certain rules. The data collection program may reside on the server, read the corresponding document by means of standard protocols such as HTTP (Hyper Text Transfer Protocol ) through given URLs (Uniform Resource Locator, uniform resource locators), and then continue roaming with all unvisited URLs included in the document as new starting points until no new URL is met.

When a written data collection program is used to perform a data collection application on a network resource, for example, data related to a target object may be collected from a web portal (e.g., newness, networkbook), brand officer network, e-commerce web site, life service web site (e.g., public commentary, beauty team, 58 city, me love me home network, chain home network, etc.), social web site (e.g., newfashioned microblog), forum (e.g., hundred degree bar, fence network), blog, etc.

In some examples, the real estate residential data and/or real estate agent data for a city may be crawled from real estate agent company websites, such as chain house (https:// www.lianjia.com), me love my house (https:// www.5i5j.com), 58 co-city (https:// www.58.com), or real estate developer websites, or real estate registration websites hosted by the urban homeowner, or the like. The property intermediation data may include, but is not limited to, property source information (e.g., number of property sources, location, area, floor, price, etc.), recent property transaction information, price trends, etc. that may be rented/sold.

In some examples, each brand-related data (brand name, industry domain to which the brand belongs, label of the brand, geographic coordinate information of an off-line store of the brand, affiliated store name and location within the store, business hours, feature recommendations, preference information, customer reviews, etc.) and corresponding consumption level data (e.g., people average consumption, etc.) may be crawled from, for example, a mass review network (http:// www.dianping.com).

In some examples, the point of interest data for a city may be collected from a geographic data service provider website such as a hundred degree map (https:// map. Baidu. Com /), a Tencentrated map, a Goldmap, and the like. A POI (Point Of Interest ) is a landmark in a geographic information system, and is used to mark a landmark scenic spot represented by the landmark (e.g., a protected building, a plaza statue), various business operations (e.g., a gas station, a mall, a supermarket, a convenience store, a restaurant, a hotel, a bank, a post office, a hospital, etc.), a transportation facility (e.g., a bus stop, a subway station, a parking lot, an overpass, etc.), and the like. The point of interest data may include a total number of points of interest, a name of each point of interest, industry classifications, and coordinate locations.

In some examples, business status information of an enterprise or a direct competitor of the industry to which the target object belongs may be obtained directly or indirectly through calculation from, for example, enterprise searches (https:// www.qichacha.com) or sky eye searches (https:// www.tianyancha.com).

In some examples, all road network data within a selected city or designated area of a city may be obtained from a geographic data facilitator website or other specialized software such as a hundred degree map (https:// map. Baidu. Com /), a Tencentration map, a Goldmap, and the like.

In certain exemplary embodiments, the data in the external data source may be obtained from at least one database.

The database may be a public database, such as government functional departments (e.g., municipal, civil, house-hold, public security, business, fire, traffic, weather, etc.), government public databases, map databases, brand databases, etc., of universities, scientific institutions, or commercial organizations, etc. Taking a government public database as an example, the government public database can be, for example, land data of an urban building environment disclosed by municipal departments, or map road network data, traffic infrastructure data, traffic flow data thereof and the like disclosed by traffic departments. Taking a map database as an example, for example, point of interest data of a certain city or a certain area of a city, or geographic coordinate information of an off-line store to which a brand belongs may be collected through an API (Application Programming Interface ) of a map application.

The database may also be a private database, which is a database of a partner, a contract database, or the like. For example, the database of the partner may be a database provided by some mall, a database provided by other third party (e.g., cell phone signaling data provided by a telecom operator), etc.

In certain exemplary embodiments, the data in the external data source may be self-built data.

For example, the self-built data can be formed by sorting a plurality of data sources, or can be collected, recorded and sorted by field investigation, collection of feedback tables and the like.

The obtained multi-source data related to brands can be stored, for example, the multi-source data can be stored in a storage medium (such as a hard disk, an optical disk, a magnetic disk, etc.), a cloud, a distributed server, etc.

In some embodiments, the method may further include associating the acquired data with a data source where the acquired data is located, establishing a trace information chain associated with the data, where the trace information chain includes creation time of the data in the data source where the data is located, implementing trace back of each piece of data, and knowing a variation trend of the data.

Because a large amount of invalid or abnormal data may exist in the multi-source data, the invalid or abnormal data may be repeated data, incomplete data, erroneous data, etc., and the invalid data may not only cause a large amount of subsequent processing, but also cause interference or pollution to subsequent data processing, and affect the reliability and effectiveness of the data processing result. Therefore, it is necessary to delete the invalid data or correct some or all of the invalid data, which involves cleaning the data.

At present, for lightweight data, a manual cleaning mode is adopted conventionally, a unified and standard cleaning flow is lacked, and the manual cleaning mode mainly has the following problems: the time consumption for data cleaning is long, the manual cleaning mode depends on the data judgment of operators, and cleaning is needed to be completed step by step after the judgment, so that a great amount of time is needed; data cleaning is easy to miss; the data cleaning result is unstable, and the problem of inconsistent cleaning result can occur due to different operators; the data cleaning process can not be traced back, and when cleaning errors occur, the data cannot be traced back and corrected; and (3) checking the data cleaning result, which is time-consuming and labor-consuming, and carrying out statistics on the data again after cleaning is completed, so as to check the data cleaning result. Thus, it is apparent that conventional manual cleansing is not an effective way to consume transaction data in large data volumes in this application.

The site selection method can also carry out data cleaning on the acquired multi-source data according to the data cleaning rule.

Generally, data cleansing (Data cleansing) refers to a process of re-checking and checking Data, and aims to delete repeated Data, delete redundant Data, delete or correct incomplete Data and erroneous Data, thereby obtaining Data with high consistency.

In an embodiment, the method includes performing data cleansing on part or all of the acquired consumption transaction data, deleting duplicate data, deleting redundant data, deleting or correcting incomplete data and erroneous data, and retaining qualified data and corrected data, where the data may be stored in a storage medium (e.g., hard disk, optical disk, magnetic disk, etc.), cloud, or distributed server, etc.

The cleaning of the consumer transaction data may be performed according to preset data cleaning rules. In some embodiments, the data cleansing rule file may include one or more data cleansing rules, where the data cleansing rules may be set according to a type, a format, a source, and/or an industry of data, that is, different types of data may set different data cleansing rules, different formats of data may set different data cleansing rules, different sources of data may set different data cleansing rules, and different industries of data may set different data cleansing rules.

In one example, the data cleansing rules may be validated and adjusted according to the validation results. For example, by performing an auto-and cross-correlation data validation analysis on the consumer transaction data, it is determined whether the current data cleansing rules for a certain data source, data type, and/or data format need to be modified based on the validation analysis results. If the correction is needed, the original data cleaning rule is corrected and updated, and the consumption transaction data is cleaned according to the updated data cleaning rule.

In one example, a machine learning method may be employed to train the data cleansing rules, for example, by employing a machine learning method to train the data cleansing rules on existing data, which may then be utilized to conduct data cleansing on multi-source data.

In some embodiments, in the acquired multi-source data, the data for describing an object often come from multiple data sources, so the addressing method of the application can also be used for performing optimized synthesis on the multi-source data for describing the same object.

For example, in some examples, data in different data sources may take different data standards or no corresponding data standards, resulting in different descriptive information for data in the multi-source data that relates to the same brand name. Thus, data relating to the same brand name in multi-source data may be fused.

In some examples, different descriptive information may exist in different data sources relating to the name of the same bus stop, and thus, the data relating to the name of the same bus stop in the multi-source data may be fused.

Taking the brand name as an example, the fusing of the content of the brand name includes, but is not limited to, the following steps:

And extracting the content containing the suspected brand name.

And judging whether the content of the suspected brand name has the same brand name as a pre-stored brand library.

And when judging that the content of the suspected brand name is the same as the brand name in the pre-stored brand library, pointing the suspected brand name in the content to the same brand name, and adding the description information of the suspected brand name into the corresponding brand name data in the brand library.

Still taking McDonald's as an example, suspected brand names such as "McDonald", "madonna", "major", "M-jiu", "M-store", "McDonald's", "McDonald", "Jin Gongmen" may be extracted from the identified text, while a pre-stored brand library stores various standard brand names referring to "McDonald's": mcDonald's, may occur, "McDonald", "mactita", "malt", "malted", "M", "McDonald's", when data fusion is performed, the data to be fused is fused by having the suspected brand names "McDonald" corresponding to the standard brand names, mcDonald's, and the like.

Notably, to facilitate the accuracy of data fusion to avoid missing or misjudging data, manual analysis may be added as necessary. In some embodiments, for some data that is disputed or highly suspected but not matched, a manual analysis is used to determine if the suspected brand name matches the standard brand name. For example, by manual analysis, "McDonald" is directed to the standard brand name "McDonald's", or "McDonald's".

Additionally, in some embodiments, standard brand names may be updated or augmented according to the development of brand names. For example, "Jin Gongmen" is updated to the standard brand name "McDonald's", and thus, when data fusion is performed, the suspected brand name "Jin Gongmen" may be directed to the standard brand name "McDonald's".

Therefore, the brand names in the multi-source data are fused, and the data corresponding to the standard brand names are integrated, so that single and scattered brand data in different data sources in the multi-source data are integrated into unified brand data.

Taking the name of the bus station as an example, the fusing the content of the name of the station includes, but is not limited to, the following steps:

and extracting the content containing the suspected site name and the associated geographic position information thereof.

And judging whether the content of the suspected site name has the same site name as a pre-stored site information base.

When the content of the suspected site name is judged to be the same as the site name in a pre-stored site information base, the suspected site name in the content is pointed to be the same site name, and description information of the suspected site name is added into corresponding site data in the site information base.

When judging that the content of the suspected site name corresponds to a plurality of site names in a pre-stored site information base, comparing geographic position information associated with the suspected site name with geographic position information associated with the corresponding plurality of site names, determining the site name matched with the geographic position information, and pointing the suspected site name in the content to be under the determined site name and adding description information of the suspected site name into corresponding site data in the site information base.

When judging that the content of the suspected site name does not have the corresponding site name in a pre-stored site information base, searching whether the site name of the geographic position information exists or not from the site information base according to the geographic position information associated with the suspected site name, if so, pointing the suspected site name in the content to the found site name, and adding the description information of the suspected site name to the corresponding site data in the site information base.

Therefore, the site names in the multi-source data are fused, and the data corresponding to the standard site names are integrated, so that single and scattered site data in different data sources in the multi-source data are integrated into unified site data.

In some embodiments, in the acquired multi-source data, the description that often involves a certain object is multi-dimensional data. Thus, multidimensional data relating to an object can be fused.

Taking a point of interest as a convenience store as an example, the fusing the multidimensional data of the convenience store includes: the multi-dimensional data such as names of convenience stores, average consumption of people, evaluation information, address information, property rights of stores, store areas, rentals of stores, surrounding traffic foundation configuration and traffic flow of surrounding residential areas or commercial area structures can be integrated in the multi-source data. In this way, multidimensional data associated with the convenience store can be fused.

As shown in fig. 2, a detailed flowchart of step S101 is shown. As shown in fig. 2, the method for performing data processing on the multi-source data to perfect the ontology-based city data model may further include:

in step S101a, an ontology-based city data model related to the site selection decision behavior is built. In the city data model, the relation of related systems such as city building environment, individual behaviors and the like is described.

The city built environment refers to an artificial environment provided for human activities including large city environments. In this embodiment, elements of the city build environment may include: land use, space morphology, road traffic, etc.

The individual behavior may be, for example, a behavior of an individual or a target object.

Step S101b, extracting the characteristic parameters related to the address selection decision from the multi-source data, and capturing the data related to the characteristic parameters from the multi-source data.

Step S101c, generating basic attributes and labels based on the data model of the target object and the captured data related to the feature parameters.

Step S103, based on the industry characteristics of the target object and the basic database, a multi-target site selection evaluation system is established.

In some embodiments, please refer to fig. 3, which shows a detailed flowchart of step S103. As shown in fig. 3, the step of establishing a multi-objective site selection evaluation system based on the industry characteristics of the objective object and the basic database may further include:

step S103a, determining an influence factor related to the site selection decision from a basic database based on the industry characteristics of the target object.

In this embodiment, the impact factors associated with the addressing decision may include, but are not limited to, population, environment, traffic, and bidding among others.

Step S103b, determining the attribute and the label of the influence factor;

taking population as an example, extracting the impact factors related to the addressing decision from the multi-source data includes extracting the population impact factors related to the addressing decision from the multi-source data, and capturing the data related to the population impact factors from the multi-source data.

Taking the population as an example: basic population attributes are determined, for example: age, sex, job site, residence, etc. Based on the business morphology of the target object, relevant population labels are determined.

Taking the environment as an example, extracting the impact factors related to the site selection decision from the multi-source data comprises extracting the environment impact factors related to the site selection decision from the multi-source data, and grabbing the data related to the environment impact factors from the multi-source data.

Taking the environment as an example: determining block attributes, such as: planning land attributes, number of surrounding commercial points of interest, etc. The tile labels are marked based on the business morphology of the target object.

Taking traffic as an example, extracting the impact factors related to the addressing decision from the multi-source data comprises extracting the traffic impact factors related to the addressing decision from the multi-source data, and capturing the data related to the traffic impact factors from the multi-source data.

Taking traffic as an example: determining traffic attributes and traffic labels, for example: traffic hub, number of stops at peripheral bus stops, etc.

Taking a bid as an example, extracting the influence factors related to the address selection decision from the multi-source data comprises extracting the bid influence factors related to the address selection decision from the multi-source data, and capturing data related to the bid influence factors from the multi-source data.

Taking a bid as an example: the business attributes and tags of the business of the industry to which the bid or target object belongs are determined for the city or a specific area of the city.

And step S103c, performing numerical processing on the attribute of the influence factor and the label.

The attribute and the label of the influence factor are subjected to numerical treatment, the numerical attribute and the numerical value of the label can be quantitatively classified, a class score standard is formulated, then the total sum of the scores of all indexes is used for comprehensively evaluating the site selection decision of the target object, and a multi-target site selection evaluation system is established.

Step 105, constructing a space-based site selection knowledge graph based on the basic database and the multi-target site selection evaluation system, and realizing the method in an interactive visual mode.

The established multi-objective addressing evaluation system is a state which can be used initially, but the description objects of the data in space are not consistent.

For example: the operator's user signaling data is stored and calculated by map rasterization, which is typically a square or rectangular pattern. The land planning information and the land attributes are described in terms of city blocks. Housing information and house renting data are stored through city blocks divided by a house intermediation company. And the resident population information is also located to the city street. Therefore, various types of data need to be fused spatially.

Thus, referring to FIG. 4, a flow chart of the method for addressing according to another embodiment of the present application is shown. As shown in fig. 4, the method for addressing of the present application may further include step S104, before executing step S105, of obtaining space-based block information based on the multi-target addressing evaluation system.

In practical application, urban space can be cut again through map road network data and other base map information, then other various data (such as user signaling data of operators, house property intermediate data and the like) are fitted into blocks and buildings in the city, and index calculation and label marking are carried out on the data on the fused space.

Referring to fig. 5, a detailed flowchart of step S104 is shown. As shown in fig. 5, the step of obtaining the block information based on the space based on the multi-target site selection evaluation system may further include:

in step S104a, the spatial data are fused, and the region space is redefined to form a plurality of blocks.

In some embodiments, city blocks are cut by open source road network data and special roads such as intersections, tunnels, broken roads, etc. are processed by algorithms to enclose all areas into a regular polygon.

Step S104b, assigning attributes and labels to the delimited blocks based on the multi-target addressing evaluation system.

In some embodiments, the assigned attributes and labels may be, for example, demographic attributes and demographic labels, traffic attributes and traffic labels, and the like.

In step S104c, the attribute and the label of each block are digitized.

In addition, step S104 further includes a step of interpolating data for the blocks that lack data support, so as to complement the attributes and tags in all the blocks.

And then, classifying and storing the index after the attribute and the label of each block are subjected to the numerical treatment.

Returning to step S105, constructing a space-based site selection knowledge graph based on the basic database and the multi-target site selection evaluation system, which is implemented in an interactive visual manner.

Through the previous steps, all the data in the multi-source data are extracted based on the addressing decision of the target object and are subjected to numerical processing to form indexes of all the blocks of the city, and the information is combined with the block information to be displayed in an interactive visual mode so as to provide the addressing strategy and the addressing operation of the target object. The user can intuitively obtain the evaluation index related to the address of the target object according to the interactive visual display page and can make a quick and reliable decision according to the evaluation index.

Referring to fig. 6, a flow chart of the address selecting method according to another embodiment of the present application is shown. As shown in fig. 6, the location method of the present application further includes a step S12 of performing operation index prediction.

In step S12, the step of performing operation index prediction further includes: and predicting the prediction result of the target object in each block according to the self operation data of the target object, the operation data of the bid and/or the operation index of the industry to which the target object belongs and combining the attribute and the label of each block.

In a certain example, according to the self operation data of the target object, the prediction result of the target object in each block is predicted by combining the attribute and the label of each block.

In a certain example, according to the operation data of the bid, the prediction result of the target object in each block is predicted by combining the attribute and the label of each block.

In a certain example, according to the operation index of the industry to which the target object belongs, the prediction result of the target object in each block is predicted by combining the attribute and the label of each block.

Thus, in step S105, the data has been extracted based on the addressing decision of the target object and is numerically processed to form the index of each block of the city and the prediction result in step S12, and these pieces of information are visually displayed in combination with the block information.

Referring to fig. 7, a schematic diagram of displaying space-based addressing information based on the addressing method of the present application is shown. As shown in fig. 7, block information of a city is displayed. Various indexes of the block formed by the numerical processing based on the address decision of the target object can be displayed in a visual mode such as thermodynamic diagram, pointer icon and the like. The thermodynamic diagram can display indexes with arbitrary dimensions, such as population, traffic and the like, in all areas of the city. The pointer may identify all points of interest, including the bunk to be selected, surrounding business points, traffic sites, and the like.

The "index list" section functions in that the selection of an index item, the user can point out the index category that he wants to view. After clicking, the corresponding index heating power is correspondingly displayed in the index display area, and a specific calculation basis and corresponding model parameters of the popup window display index are also provided.

The "block list" and "block information" sections are used to select and present basic information and corresponding strategic index prediction results for the recommended block.

The histogram in the figure is used to express the distribution of the individual strategic indicators of the block throughout the city.

And the specific operation index prediction result can be checked by clicking the corresponding block to enter the block details.

The visual presentation may be, for example, using SVG. SVG (Scaleable Vector Graphics, scalable vector graphics) is a language that uses XML (ExtensibleMarkup Language ) to describe two-dimensional graphics and drawing programs. The SVG graph has small storage capacity, small input load to the network, small network transmission delay, support of interaction and animation, and the image is not distorted by the image amplifying and shrinking operation. The SVG has the advantages of being very suitable for being used as a carrier of a Web two-dimensional map for lightweight application.

The application discloses an address selecting method, which is characterized in that an acquired multi-source data is subjected to data processing, a basic database is formed based on an ontology urban data model, and a multi-target address selecting evaluation system is established based on the industry characteristics of a target object and the basic database, so that a space-based address selecting knowledge graph is constructed, an address selecting method and strategy of the target object are provided, and visual display is performed, so that various quantized address selecting decision schemes are provided, and the problems of time and labor waste, poor address selecting success rate and the like in the existing related address selecting decisions are solved.

Based on the addressing method, the application also discloses an addressing platform system aiming at the target object. Because the implementation scheme of the address selection platform system is similar to the address selection method, the implementation of the specific processing unit in the embodiment of the present disclosure may refer to the implementation of the address selection method, and the repetition is omitted.

The following description will be given with the application of the above-described addressing method to a specific example.

In the specific example, the target object is a chain of coffee shops that wish to open a number of new shops in a city (e.g., shanghai).

Firstly, related multi-source data are acquired, and data processing is carried out on the multi-source data.

In this particular example, the target object is a chain of coffee shops, and thus, the available multi-source data includes, but is not limited to: open source network data in Shanghai, operator mobile phone signaling data, shanghai enterprise directory, traffic infrastructure data and traffic flow data thereof, map interest point data in Shanghai, shop intermediary data, operation data of the chain coffee shop (and operation data of bidding products if necessary) and the like.

Then, data processing such as data cleaning and data fusion can be carried out on the multi-source data, and an urban data model based on the ontology is perfected, so that a basic database is formed;

an impact factor associated with the addressing decision is determined from the base database based on the industry characteristics of the coffee shop.

Including but not limited to population, environment, traffic, bidding, and the like.

For population, a base population attribute is determined and related population tags are determined based on the business shape of the coffee shop. The basic population attributes may include, among others: age, gender, workplace, residence, etc., the population label may include: white collar (job site confirmation), abroad (records of country departure), dining attention (catering or takeaway APP), and the like.

For an environment, block attributes are determined and block tags are labeled based on the business shape of the coffee shop. The block attributes comprise planning land attributes, catering quantity within 1 km and business interest point quantity within 1 km, and the block labels comprise a main business area, a central business area, university cities of universities and the like.

For traffic, the locations of block perimeter traffic sites and average daily traffic are determined.

For the bid, the business attributes and tags of all coffee shops in Shanghai are determined. Such as number of stores, store area, unit price per cup, providing light snack foods, etc.

And carrying out numerical processing on the attribute and the label of the influence factor, classifying the attribute and the label into four categories of population, environment, traffic and bid products, and establishing a multi-target site selection evaluation system.

And then, based on the multi-target site selection evaluation system, fusing the space data to obtain the block information based on the space.

Urban blocks are cut through open source road network data of Shanghai, and special roads such as overpasses, tunnels, broken roads and the like are processed through an algorithm, so that all areas are surrounded into regular polygons.

And assigning attributes and labels to all blocks in the Shanghai based on the multi-target site selection evaluation system.

And fitting or calculating numerical indexes of the block, such as population number, working population number and commercial interest point number within 1 km through standardized data.

And interpolating the blocks which cannot be supported by the data source through an algorithm to complement all block indexes, such as the rent of a shop, and passing passenger flow every day.

And storing all the digitized indexes in a classified manner.

Then, operation index prediction is performed.

And determining three strategic indexes of daily business turnover, daily incoming passenger flow and 5-star good number of the month according to operation data provided by the chain coffee shops, and respectively taking the strategic indexes as Y values of model regression.

And extracting block indexes in the database, carrying out principal component analysis by combining free operation data provided by the chain coffee shops, denoising all indexes, and merging indexes with high correlation.

And regression is carried out to obtain the prediction results of all the blocks.

And merging indexes after denoising of all blocks according to parameters of a regression model, dividing the indexes into population, environment, traffic and bidding products, and carrying out standardization through algorithm distribution, wherein the standard is a distribution numerical value of 0-1, so as to form a standardized intermediate index.

Then, visual display is performed.

And calling spatial basic data of all the blocks, a model prediction result and a standardized intermediate index.

The basic data of the numerical value and all the intermediate indexes are stored in the svg files of all the blocks in a thermodynamic diagram mode, and all shops and interest points are located in the blocks through coordinates.

An interactive visual presentation is provided to provide an address decision for a new store of the chain of coffee shops.

In some embodiments, in the visual presentation, the 10 candidate blocks with the highest model scores may be invoked and highlighted in the page.

Referring to fig. 8, a schematic structural diagram of an address selection platform according to an embodiment of the present application is shown.

As shown in fig. 1, the addressing platform system of the present application may include: a database creation unit 12, an evaluation system establishment unit 14, an addressing knowledge graph construction unit 16 and a visualization processing unit 18.

The database creation unit 12 is used to create a basic database. In this embodiment, the database creation unit 12 is used to perform data processing on the acquired multi-source data, and perfect the ontology-based city data model to form a basic database.

In practical applications, the addressing platform system of the present application may further include a data obtaining unit 11, configured to obtain multi-source data.

For example, data collection is performed on network resources using a written data collection program. When a written data collection program is used to perform a data collection application on a network resource, for example, data related to a target object may be collected from a web portal (e.g., newness, networkbook), brand officer network, e-commerce web site, life service web site (e.g., public commentary, beauty team, 58 city, me love me home network, chain home network, etc.), social web site (e.g., newfashioned microblog), forum (e.g., hundred degree bar, fence network), blog, etc.

The multi-source data related to brands acquired by the data acquisition unit 11 may be stored, for example, in a storage medium (e.g., hard disk, optical disk, magnetic disk, etc.), cloud, or distributed server, etc.

In some embodiments, the data obtaining unit 11 may further include associating the obtained data with the data source where the obtained data is located, and establishing a trace information chain with the data, where the trace information chain includes the creation time of the data in the data source where the obtained data is located, so as to implement tracing of each piece of data, and understand the trend of the change of the data.

The system of the addressing platform of the present application may further comprise a data cleansing unit (not shown in the drawings) for cleansing the multi-source data acquired by the data acquisition unit 11 according to a data cleansing rule.

In an embodiment, the data cleansing unit cleans some or all of the consumption transaction data acquired by the data acquisition unit 11, deletes duplicate data, deletes redundant data, deletes incomplete data and erroneous data, and retains qualified data and corrected data, where the data may be stored in a storage medium (e.g., hard disk, optical disk, magnetic disk, etc.), cloud, or a distributed server.

The data cleansing unit may cleansing the consumption transaction data according to a preset data cleansing rule, and thus, the data cleansing unit may further include a cleansing rule setting unit for setting a cleansing rule of the data. In some embodiments, the data cleansing rule file may be configured by using the cleansing rule setting unit, where the data cleansing rule file may include one or more data cleansing rules, where the data cleansing rules may be set according to a type, a format, a source, and/or an industry of data, that is, different types of data may set different data cleansing rules, different formats of data may set different data cleansing rules, different sources of data may set different data cleansing rules, and different industries of data may set different data cleansing rules.

In one example, the data cleansing rules may be validated and adjusted according to the validation results. For example, by performing an auto-and cross-correlation data validation analysis on the consumer transaction data, it is determined whether the current data cleansing rules for a certain data source, data type, and/or data format need to be modified based on the validation analysis results. If the correction is needed, the original data cleaning rule is corrected and updated, so that the data cleaning unit cleans the consumption transaction data according to the updated data cleaning rule.

In some embodiments, in the acquired multi-source data, the data for describing an object often comes from multiple data sources, so the addressing platform system of the present application may further include a data fusion unit (not shown in the drawings) that may be used to perform optimized synthesis on the multi-source data describing the same object.

For example, in some examples, data in different data sources may take different data standards or no corresponding data standards, resulting in different descriptive information for data in the multi-source data that relates to the same brand name. And fusing the data related to the same brand name in the multi-source data through a data fusion unit.

In some examples, different description information may exist in different data sources related to the name of the same bus stop, and the data related to the name of the same bus stop in the multi-source data are fused through the data fusion unit.

Therefore, the data fusion unit can fuse the site names in the multi-source data and integrate the data corresponding to the standard site names, so that the single and scattered site data in different data sources are integrated into unified site data in the multi-source data.

In some embodiments, in the acquired multi-source data, the description that often involves a certain object is multi-dimensional data. Thus, multidimensional data relating to a certain object can be fused by the data fusion unit.

Taking a point of interest as an example of a convenience store, the data fusion unit fusing multidimensional data of the convenience store includes: the multi-dimensional data such as names of convenience stores, average consumption of people, evaluation information, address information, property rights of stores, store areas, rentals of stores, surrounding traffic foundation configuration and traffic flow of surrounding residential areas or commercial area structures can be integrated in the multi-source data. Thus, the multidimensional data related to the convenience store can be fused through the data fusion unit.

Returning to the database creation unit 12, the database creation unit 12 performs data processing on the multi-source data, and the manner of perfecting the ontology-based city data model includes:

First, an ontology-based city data model is built that is relevant to the site selection decision behavior. In the city data model, the relation of related systems such as city building environment, individual behaviors and the like is described.

Then, extracting characteristic parameters related to site selection decision from the multi-source data, and grabbing data related to the characteristic parameters from the multi-source data;

next, based on the data model of the target object and the captured data related to the feature parameters, basic attributes and labels are generated.

The evaluation system establishment unit 14 is configured to establish a multi-objective site selection evaluation system based on the industry characteristics of the objective object and the base database.

In some embodiments, based on the industry characteristics of the target object and the base database, the manner in which the multi-target site selection rating system is established may include:

an impact factor associated with the addressing decision is determined from the base database based on the industry characteristics of the target object.

Determining the attribute and the label of the influence factor;

taking population as an example, extracting the impact factors related to the addressing decision from the multi-source data includes extracting the population impact factors related to the addressing decision from the multi-source data, and capturing the data related to the population impact factors from the multi-source data. Basic population attributes are determined, for example: age, sex, job site, residence, etc. Based on the business morphology of the target object, relevant population labels are determined.

Taking the environment as an example, extracting the impact factors related to the site selection decision from the multi-source data comprises extracting the environment impact factors related to the site selection decision from the multi-source data, and grabbing the data related to the environment impact factors from the multi-source data. Determining block attributes, such as: planning land attributes, number of surrounding commercial points of interest, etc. The tile labels are marked based on the business morphology of the target object.

Taking traffic as an example, extracting the impact factors related to the addressing decision from the multi-source data comprises extracting the traffic impact factors related to the addressing decision from the multi-source data, and capturing the data related to the traffic impact factors from the multi-source data. Determining traffic attributes and traffic labels, for example: traffic hub, number of stops at peripheral bus stops, etc.

Taking a bid as an example, extracting the influence factors related to the address selection decision from the multi-source data comprises extracting the bid influence factors related to the address selection decision from the multi-source data, and capturing data related to the bid influence factors from the multi-source data. The business attributes and tags of the business of the industry to which the bid or target object belongs are determined for the city or a specific area of the city.

And carrying out numerical processing on the attribute of the influence factor and the label.

Therefore, please refer to fig. 9, which is a schematic structural diagram of another embodiment of the address selection platform of the present application. As shown in fig. 9, the addressing platform system of the present application may further include a spatial fusion unit 15, configured to obtain space-based block information based on the multi-target addressing evaluation system.

In this embodiment, the spatial fusion unit 15 obtains the block information based on the space based on the multi-target site selection evaluation system by:

and fusing the space data, and redefining the area space to form a plurality of blocks.

And assigning attributes and labels to the delimited blocks based on the multi-target addressing evaluation system.

And carrying out numerical processing on the attributes and the labels of each block.

In addition, the spatial fusion unit 15 further includes performing data interpolation on the blocks that lack data support, so as to complement the attributes and tags in all the blocks.

The site selection knowledge graph construction unit 16 is configured to construct a site selection knowledge graph based on the basic database and the multi-objective site selection evaluation system.

All the data in the multi-source data are extracted based on the addressing decision of the target object and are subjected to numerical processing to form indexes of each block of the city, so that the addressing knowledge graph construction unit utilizes the indexes as knowledge items to construct the addressing knowledge graph based on the space.

The visualization processing unit 18 is configured to display the spatial-based addressing knowledge map in an interactive visual manner to provide an addressing strategy and an addressing operation of the target object.

In this embodiment, the visualization processing unit 18 is configured to display the spatial address selection knowledge graph in an interactive visual manner, so that a user can intuitively obtain an evaluation index related to the address selection of the target object according to the interactive visual display page and make a quick and reliable decision according to the evaluation index.

As an example of a visual presentation of a space-based site selection knowledge graph, reference may be made to fig. 7 and its corresponding illustration.

Furthermore, in some embodiments, the site selection platform system may further include a prediction unit for performing operation index prediction.

In this embodiment, the manner in which the prediction unit predicts the operation index includes: and predicting the prediction result of the target object in each block according to the self operation data of the target object, the operation data of the bid and/or the operation index of the industry to which the target object belongs and combining the attribute and the label of each block.

In this way, the site selection knowledge graph construction unit 16 may construct a space-based site selection knowledge graph based on the index of each block of the city and the prediction result of the target object in each block, and the site selection knowledge graph may be visually displayed by the visual processing unit 18.

The application discloses an addressing platform system, which is used for processing acquired multi-source data, forming a basic database based on an urban data model of an ontology, and establishing a multi-target addressing evaluation system based on the industrial characteristics of a target object and the basic database, so as to construct a space-based addressing knowledge graph, provide an addressing method and strategy of the target object, and visually display the addressing knowledge graph, and provide various quantized addressing decision schemes, thereby solving the problems of time and labor waste, poor addressing success rate and the like in the prior related addressing decisions.

The present application also discloses a computer-readable storage medium storing at least one program that, when invoked, participates in performing a method of addressing a target object. The method for selecting the target object may refer to the related descriptions of fig. 1 to 6, and will not be described herein. It should be further noted that, from the description of the above embodiments, it is clear to those skilled in the art that some or all of the present application may be implemented by means of software in combination with a necessary general hardware platform. With such understanding, the storage medium stores at least one program that, when called, performs any of the methods described above. Based on such understanding, the technical solutions of the present application may be embodied essentially or in part in the form of a software product that may include one or more machine-readable media having stored thereon machine-executable instructions that, when executed by one or more machines such as a computer, computer network, or other electronic device, may cause the one or more machines to perform operations in accordance with embodiments of the present application. For example, each step in the positioning method of the robot is performed. The machine-readable medium may include, but is not limited to, floppy diskettes, optical disks, CD-ROMs (compact disk-read only memories), magneto-optical disks, ROMs (read only memories), RAMs (random access memories), EPROMs (erasable programmable read only memories), EEPROMs (electrically erasable programmable read only memories), magnetic or optical cards, flash memory, or other type of media/machine-readable medium suitable for storing machine-executable instructions. The storage medium may be located in a server or a third party server, for example, in an alicloud service system. The subject application is operational with numerous general purpose or special purpose computing system environments or configurations. For example: mainframe computers, distributed computing environments that include any of the above systems or devices, and so on. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

As can be seen from the above, the method and system for selecting addresses, the computer system and the computer readable storage medium disclosed in the present application perform data processing on the acquired multi-source data, form a basic database based on the body's city data model, and establish a multi-target site selection evaluation system based on the industry characteristics of the target object and the basic database, thereby constructing a site selection knowledge graph based on space, and provide the site selection strategy and site selection operation of the target object in an interactive visual manner. Compared with the prior art, the method can improve the site selection efficiency, avoid the site selection risk, provide more valuable site selection decision schemes and improve the site selection success rate.

The foregoing embodiments are merely illustrative of the principles of the present application and their effectiveness, and are not intended to limit the application. Modifications and variations may be made to the above-described embodiments by those of ordinary skill in the art without departing from the spirit and scope of the present application. Accordingly, it is intended that all equivalent modifications and variations which may be accomplished by persons skilled in the art without departing from the spirit and technical spirit of the disclosure be covered by the claims of this application.

Claims

1. An addressing method, characterized by comprising the following steps:

Acquiring multi-source data, performing data processing on the multi-source data, perfecting an ontology-based city data model to form a basic database, and comprising: establishing an ontology-based city data model related to site selection decision behaviors, wherein the relationship between a city building environment and an individual behavior related system is described in the city data model; extracting characteristic parameters related to site selection decision from the multi-source data, and grabbing data related to the characteristic parameters from the multi-source data;

generating basic attributes and labels based on a data model of the target object and the captured data related to the characteristic parameters;

based on the industry characteristics of the target object and the basic database, a multi-target site selection evaluation system is established, which comprises the following steps:

determining an impact factor associated with the addressing decision from the base database based on the industry characteristics of the target object;

determining the attribute and the label of the influence factor;

performing numerical processing on the attribute and the label of the influence factor to establish the multi-target site selection evaluation system; based on the multi-target site selection evaluation system, obtaining block information based on space comprises the following steps:

fusing the space data, and redefining the area space to form a plurality of blocks;

Assigning attributes and labels to the plurality of defined blocks based on the multi-target addressing evaluation system;

performing numeric processing on the attributes and the labels of each block to obtain space-based block information; based on the basic database and the multi-target site selection evaluation system, a site selection knowledge graph based on space is constructed, and the site selection strategy and site selection operation of the target object are provided in an interactive visual mode.

2. The method of claim 1, further comprising the steps of data cleansing and data fusion of the captured data associated with the feature type.

3. The method of claim 1, wherein the data sources of the multi-source data include external data sources and self-contained data sources.

4. The method of claim 3, wherein the data in the external data source comprises one or more of land data describing an urban as-built environment, map road network data, traffic infrastructure data and its traffic flow data, map point of interest data, operator data describing individual behavior, and property mediation data.

5. A method of addressing according to claim 3, wherein said external data source is obtained by at least one of:

Collecting from network resources through a data collection program;

obtained from at least one database, the database including a public database and a private database.

6. The method of claim 3, wherein the data in the self data source includes one or more of sales data, passenger flow data, and purchase and inventory data.

7. The method of claim 1, wherein the impact factor comprises at least one of: demographic data, block data, commercial point of interest distribution data, traffic facility and service level and traffic flow data, passenger flow data, and bid data.

8. The method of claim 1, further comprising the step of interpolating data for blocks that lack data support.

9. The site selection method of claim 1, further comprising the step of performing an operation index prediction prior to constructing the space-based site selection knowledge graph.

10. The method according to claim 9, wherein the step of performing operation index prediction includes:

and predicting the prediction result of the target object in each block according to the self operation data of the target object, the operation data of the bid and/or the operation index of the industry to which the target object belongs and combining the attribute and the label of each block.

11. An addressing platform system, comprising:

the database creation unit is used for carrying out data processing on the acquired multi-source data and perfecting the city data model based on the ontology so as to form a basic database; the database creation unit performs data processing on the multi-source data, and the way of perfecting the city data model based on the ontology comprises the following steps: establishing an ontology-based city data model related to site selection decision behaviors; in the city data model, the relation of the city building environment and the individual behavior related system is described; extracting characteristic parameters related to site selection decision from the multi-source data, and grabbing data related to the characteristic parameters from the multi-source data; generating basic attributes and labels based on a data model of the target object and the captured data related to the characteristic parameters;

an evaluation system establishment unit for establishing a multi-target site selection evaluation system based on the industry characteristics of the target object and the basic database, comprising:

determining the attribute and the label of the influence factor;

Performing numerical processing on the attribute and the label of the influence factor to establish a multi-target site selection evaluation system; the space fusion unit is used for acquiring block information based on the space based on the multi-target site selection evaluation system, and comprises the following steps:

performing numeric processing on the attributes and the labels of each block to obtain space-based block information;

the site selection knowledge graph construction unit is used for constructing a site selection knowledge graph based on the basic database and the multi-target site selection evaluation system;

and the visual processing unit is used for displaying the space-based addressing knowledge graph in an interactive visual mode so as to provide an addressing strategy and addressing operation of the target object.

12. The siting platform system according to claim 11, wherein said database creation unit is further adapted to perform data cleansing and data fusion of the captured data related to the feature type.

13. The siting platform system according to claim 11, wherein said data sources of multi-source data comprise external data sources and self-contained data sources.

14. The siting platform system according to claim 13, wherein said data in external data sources comprises one or more of land data describing an urban as built environment, map road network data, traffic infrastructure data and its traffic flow data, map point of interest data, operator data describing individual behavior, and house property intermediation data.

15. The siting platform system according to claim 13, wherein said external data source is obtained by at least one of:

collecting from network resources through a data collection program;

16. The siting platform system according to claim 13, wherein said data in said self data sources comprises one or more of sales data, passenger flow data, and purchase and sale data.

17. The siting platform system according to claim 11, wherein said influencing factors comprise at least one of: demographic data, block data, commercial point of interest distribution data, traffic facility and service level and traffic flow data, passenger flow data, and bid data.

18. The system of claim 11, wherein the spatial fusion unit is further configured to interpolate data for a block that lacks data support.

19. The siting platform system according to claim 11, further comprising a prediction unit for performing an operation index prediction.

20. The system according to claim 19, wherein the means for predicting the operation index comprises:

21. A computer system, comprising:

a storage device for storing at least one program;

an interface device;

processing means connected to said storage means and to said interface means, wherein said processing means is integrated with a trusted processing environment, said processing environment executing the addressing method according to any of the claims 1 to 10 in accordance with at least one stored program.

22. A computer readable storage medium storing computer instructions which, when invoked, participate in performing the addressing method of any one of claims 1 to 10.