CN117848315A - Method, device, equipment, medium and product for determining geographic position interest points - Google Patents

Abstract

The application provides a method, a device, equipment, a medium and a product for determining a geographic position interest point, which relate to the technical field of electronic maps and comprise the following steps: extracting POI data from the target webpage information; determining urban area information to which the POI data belong, and determining address information to which the POI data belong; acquiring a target address corresponding to the POI data based on urban area information and address information to which the POI data belong; and converting the target address into longitude and latitude coordinates so as to determine the geographic position of the POI data displayed on the electronic map based on the longitude and latitude coordinates. Through the method, the POI data are extracted and the position of the POI data in the map is determined by using the webpage information, manual in-situ collection is not needed, the labor cost is effectively reduced, and the coverage area of the newly added POI is larger and the instantaneity is stronger.

Description

Method, device, equipment, medium and product for determining geographic position interest points

Technical Field

The present disclosure relates to the field of electronic map technologies, and in particular, to a method, an apparatus, a device, a medium, and a product for determining a geographic location interest point.

Background

In electronic maps, in order to facilitate a user to quickly locate a target location, the target location is typically marked in the form of a point of interest (Point Of Information, POI).

In the related art, the new points of interest (Point of Information, POI) in the electronic map are found out mainly in a manual collection mode, and a professional takes photos from the scene or takes photos through a collection vehicle, makes the POI through image recognition and manual recognition, and performs new display in the electronic map.

In the new POI adding mode, due to high labor cost, only partial key POI (such as a large-scale mall and a large-scale scenic spot) can be generally collected, and the POI is difficult to be covered in a high-frequency and large-area manner; the manual acquisition is usually carried out in a time-sharing period, so that the real-time performance of POI data can not be ensured, and newly added POIs can not be found in time; in addition, because it is difficult to collect POIs inside a building, there is caused a problem that POIs inside the building are lost.

Disclosure of Invention

The application provides a method, a device, equipment, a medium and a product for determining a geographic position interest point, so as to at least solve one of the technical problems.

According to an aspect of the present application, there is provided a method for determining a geographic location interest point, including:

Extracting POI data from the target webpage information;

determining urban area information to which the POI data belong, and determining address information to which the POI data belong;

acquiring a target address corresponding to the POI data based on urban area information and address information to which the POI data belong;

and converting the target address into longitude and latitude coordinates so as to determine the geographic position of the POI data displayed on the electronic map based on the longitude and latitude coordinates.

In one embodiment, the point of interest POI data includes a point of interest name, initial urban area information, and initial address information; the extracting the POI data from the target webpage information comprises the following steps:

extracting the interest point name, the initial urban area division information and the initial address information from the target webpage information based on a pre-trained data extraction model so as to obtain interest point POI data;

the data extraction models comprise a name extraction model, a city division extraction model and an address extraction model, and each data extraction model is obtained based on the corresponding existing interest point data training.

In one embodiment, the determining the urban area information to which the POI data belongs includes:

Based on the characteristic information of each urban area corresponding to the initial urban area information in the POI data, the characteristic information at least comprises one of the following characteristics: the number of times of word appearance, the word appearance position of the urban area, and a first word distance between the urban area and the name of the interest point in the POI data;

and respectively obtaining the score of each urban area, and determining the urban area with the highest score as urban area information to which the POI data belong.

In one embodiment, the obtaining the score of each urban area based on the characteristic information of each urban area in the initial urban area information includes:

respectively calculating and determining a first product between the first text distance and the distance weight of each urban area, a second product between the text occurrence number and the number weight of each urban area, and a third product between the text occurrence position and the position weight of each urban area;

a score for each of the urban areas is determined based on a sum of the first product, the second product, and the third product.

In one embodiment, the determining the address information to which the POI data belongs includes:

And acquiring second text distances between each address corresponding to the initial address information in the POI data and the name of the interest point in the POI data, and determining the address with the shortest second text distance as the address information of the POI data.

In one embodiment, the converting the target address into latitude and longitude coordinates includes:

disassembling the target address to obtain sub-address information of the target address;

and determining longitude and latitude coordinates corresponding to the sub-address information of the target address based on a pre-established mapping relation between the sub-address information and the longitude and latitude coordinates, so as to convert the target address into the longitude and latitude coordinates.

In one embodiment, before determining the latitude and longitude coordinates corresponding to the sub-address information of the target address based on the pre-established mapping relationship between the sub-address information and the latitude and longitude coordinates, the method further includes:

for each urban area, all the existing interest point addresses in the urban area are disassembled to extract sub-address information corresponding to each interest point address, wherein the sub-address information at least comprises one of the following sub-addresses: road address, reference point of interest information, or parent point of interest information;

And mapping the sub-address information with longitude and latitude coordinates of the corresponding interest point address to obtain a mapping relation between the sub-address information and the longitude and latitude coordinates.

In one embodiment, before extracting the POI data from the target webpage information, the method further includes:

screening out target web pages containing preset keywords from the obtained current web pages, and performing duplication removal processing on the target web pages to obtain duplication-removed target web page information;

the preset keywords are determined based on POI types of interest points, and the POI types at least comprise one of the following types: scenic spots, stores, and houses.

In one embodiment, after converting the target address into latitude and longitude coordinates and before determining the geographic position of the POI data to be displayed on the electronic map based on the latitude and longitude coordinates, the method further comprises:

acquiring the existing interest points of the longitude and latitude coordinates within a preset range based on the longitude and latitude coordinates;

and judging whether the existing interest points and the interest points corresponding to the POI data are the same interest points, if not, determining the geographic position of the POI data displayed on the electronic map based on the longitude and latitude coordinates.

In a second aspect, the present application provides a device for determining a geographic location point of interest, including:

an extraction module configured to extract point of interest POI data from the target web page information;

a determining module configured to determine urban area information to which the POI data belongs, and determine address information to which the POI data belongs;

the acquisition module is used for acquiring a target address corresponding to the POI data based on urban area information and address information to which the POI data belong;

the determining module is further configured to convert the target address into latitude and longitude coordinates, so as to determine a geographic position of the POI data displayed on the electronic map based on the latitude and longitude coordinates.

In one embodiment, the point of interest POI data includes a point of interest name, initial urban area information, and initial address information; the extraction module is specifically configured to:

extracting the interest point name, the initial urban area division information and the initial address information from the target webpage information based on a pre-trained data extraction model so as to obtain interest point POI data;

the data extraction models comprise a name extraction model, a city division extraction model and an address extraction model, and each data extraction model is obtained based on the corresponding existing interest point data training.

In one embodiment, the determining module includes:

a first determining unit configured to determine, based on feature information of each urban area corresponding to the initial urban area information in the POI data, the feature information including at least one of the following features: and the number of times and the position of the word appearance of the urban area and the first word distance between the urban area and the name of the interest point in the POI data are respectively obtained, the score of each urban area is respectively obtained, and the urban area with the highest score is determined as the urban area information of the POI data.

In one embodiment, the first determining unit is specifically configured to: respectively calculating and determining a first product between the first text distance and the distance weight of each urban area, a second product between the text occurrence number and the number weight of each urban area, and a third product between the text occurrence position and the position weight of each urban area; a score for each of the urban areas is determined based on a sum of the first product, the second product, and the third product.

In one embodiment, the determining module includes:

And a second determining unit configured to acquire second text distances between respective addresses corresponding to the initial address information in the POI data and the names of the points of interest in the POI data, and determine an address having a shortest second text distance as address information to which the POI data belongs.

In one embodiment, the determining module includes:

the disassembly unit is used for disassembling the target address to obtain sub-address information of the target address;

and the third determining unit is used for determining longitude and latitude coordinates corresponding to the sub-address information of the target address based on the pre-established mapping relation between the sub-address information and the longitude and latitude coordinates so as to convert the target address into the longitude and latitude coordinates.

In one embodiment, the method further includes a building module configured to pre-build a mapping relationship between sub-address information and longitude and latitude coordinates, including: for each urban area, all the existing interest point addresses in the urban area are disassembled to extract sub-address information corresponding to each interest point address, wherein the sub-address information at least comprises one of the following sub-addresses: road address, reference point of interest information, or parent point of interest information; and mapping the sub-address information with longitude and latitude coordinates of the corresponding interest point address to obtain a mapping relation between the sub-address information and the longitude and latitude coordinates.

In one embodiment, the apparatus further comprises:

the screening and de-duplication module is used for screening out target webpages containing preset keywords from the acquired current webpages, and performing de-duplication processing on the target webpages to obtain de-duplicated target webpage information;

the preset keywords are determined based on POI types of interest points, and the POI types at least comprise one of the following types: scenic spots, stores, and houses.

In one embodiment, the apparatus further comprises:

the judging module is used for acquiring the existing interest points of the longitude and latitude coordinates within a preset range based on the longitude and latitude coordinates, and judging whether the interest points corresponding to the existing interest points and the POI data are the same interest points or not;

the determining module is specifically configured to determine, when the judging module judges no, a geographic position of the POI data displayed on the electronic map based on the longitude and latitude coordinates.

In a third aspect, the present application provides a computer device comprising: a processor, and a memory communicatively coupled to the processor;

the memory stores computer-executable instructions or programs;

the processor executes the computer-executable instructions or programs stored in the memory to implement the method of determining the geographic location points of interest,

In a fourth aspect, the present application provides a computer-readable storage medium having stored therein computer-executable instructions or programs which, when executed by a processor, are adapted to implement a method for determining a geographic location point of interest.

In a fifth aspect, the present application provides a computer program product having stored therein computer-executable instructions or programs for performing a method for determining a point of interest in a geographic location when the computer-executable instructions or programs are executed by a processor.

According to the method, the device, the equipment, the medium and the product for determining the geographic position interest point, POI data are extracted from target webpage information, urban areas and address information of the POI data are determined, more accurate target addresses of the POI data are obtained according to the urban areas and the address information, and geographic positions of the POI data displayed on an electronic map are determined by converting the target addresses into longitude and latitude coordinates. According to the method, the webpage information disclosed in the Internet is utilized to rapidly extract POI data and determine the position in the map without manual on-site acquisition, so that not only can extraction and determination of key POIs be realized, but also high-frequency large-area coverage of other newly added POIs can be realized, meanwhile, the POIs in a building can be covered, and the problem of omission of the POIs is effectively solved; in addition, according to the latest time of webpage information publication, real-time extraction and determination of POI data can be realized, the generation efficiency of POIs in an electronic map is greatly improved, and meanwhile, the labor cost is reduced.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.

FIG. 1 is a diagram of one possible system architecture provided in an embodiment of the present application;

FIG. 2 is a flowchart of a method for determining a geographic location interest point according to an embodiment of the present application;

FIG. 3 is an exemplary diagram of extracting a point of interest name in an embodiment of the present application;

FIG. 4 is a second flowchart of a method for determining a geographic location interest point according to an embodiment of the present disclosure;

FIG. 5 is one of the flow charts of step S202 in FIG. 2 or FIG. 4;

FIG. 6 is a second flowchart of step S202 in FIG. 2 or FIG. 4;

FIG. 7 is a flowchart illustrating another method for determining a geographic location interest point according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a device for determining a geographic location interest point according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a computer device according to an embodiment of the present application;

fig. 10 is a block diagram of a terminal device according to an exemplary embodiment of the present application.

Specific embodiments thereof have been shown by way of example in the drawings and will herein be described in more detail. These drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.

It will be appreciated that when the electronic map is displayed on a terminal device (e.g., a vehicle-mounted terminal), the POI may be displayed on the map. In a geographic information system, the POI may be a house, a shop, a post, a bus stop, or the like.

In the related art, the manual acquisition and the POI determination are adopted, and because of higher labor cost, the field acquisition is needed, and most of the acquired POIs are key POIs taking a large mall and tourist attractions as examples, so that the high-frequency and large-area POI coverage is difficult to realize; the manual acquisition is usually carried out in a time-sharing period, so that the real-time performance of POI data can not be ensured, and newly added POIs can not be found in time; in addition, the problem of missing POIs inside a building is caused by the difficulty in acquiring POIs inside the building.

In order to solve the above-mentioned problems, embodiments of the present application provide a method, an apparatus, a device, a medium, and a product for determining a geographic location interest point, by extracting POI data from target web page information, determining a city region and address information to which the POI data belongs, acquiring a more accurate target address of the POI data according to the city region and address information, and converting the target address into longitude and latitude coordinates, so as to determine a geographic location where the POI data is displayed on an electronic map. According to the method, the webpage information disclosed in the Internet is utilized to rapidly extract POI data and determine the position in the map without manual on-site acquisition, so that not only can extraction and determination of key POIs be realized, but also high-frequency large-area coverage of other newly added POIs can be realized, meanwhile, the POIs in a building can be covered, and the problem of omission of the POIs is effectively solved; in addition, according to the latest time of webpage information publication, real-time extraction and determination of POI data can be realized, the generation efficiency of POIs in an electronic map is greatly improved, and meanwhile, the labor cost is reduced.

With the continuous development of internet technology, users can issue promotion messages or employment messages in internet web pages, whether they are newly opened shops, newly established parks or residential communities, newly established scenic spots, companies, hospitals, schools, and the like, so as to provide convenience. In the webpage information, since a large amount of information is included, for example, urban areas and addresses may include a plurality of POIs, if the geographical positions of POIs on an electronic map are determined directly by using the information disclosed in the webpage information, the same POI data may be finally marked in a plurality of geographical positions in the electronic map, which may result in inaccurate generated POIs. According to the method for determining the geographical position interest point, after the POI data are extracted, the urban area and the address information of the POI data are determined to obtain the more accurate target address of the POI data, the target address is converted into the longitude and latitude coordinates, the geographical position of the POI data displayed on the electronic map is determined, and the problem that the POI generation accuracy is low due to the common practice under the condition that the webpage information contains a plurality of urban areas, addresses and the like is solved.

Alternatively, fig. 1 is a schematic diagram of one possible system architecture according to an embodiment of the present application. In fig. 1, the system architecture includes at least one of a data acquisition device 110, a processing device 120, and a display device 130. It can be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the system architecture corresponding to the method for determining the geographic location interest point. In other possible embodiments of the present application, the architecture may include more or fewer components than those illustrated, or some components may be combined, some components may be separated, or different component arrangements may be specifically determined according to the actual application scenario, and the present application is not limited herein. The components shown in fig. 1 may be hardware, software, or a combination of software and hardware implementation.

In a specific implementation, the data acquisition device 110 may include an input/output interface, or may include a communication interface, where the data acquisition device 110 may be connected to the processing device through the input/output interface or the communication interface. The data acquisition device 110 may acquire the target webpage information through an input/output interface, and output the target webpage information to the processing device 120 through the input/output interface; the processing device 120 may determine the urban area and address information to which the POI data belongs by extracting the POI data in the target webpage information, obtain a more accurate target address of the POI data according to the urban area and address information to which the POI data belongs, and determine the geographic location of the POI data displayed on the electronic map by converting the target address into latitude and longitude coordinates; the display device 130 may also be a touch display screen or a screen of a terminal device, and is configured to display an electronic map carrying newly added POI data, and may also receive a user instruction to implement interaction with a user. It should be appreciated that the processing device 120 described above may be implemented by a processor reading instructions in a memory and executing the instructions, or may be implemented by a chip circuit.

In addition, the system architecture described in the embodiments of the present application is for more clearly describing the technical solution of the embodiments of the present application, and does not constitute a limitation on the technical solution provided in the embodiments of the present application, and as a person of ordinary skill in the art can know, with evolution of the network architecture and occurrence of a new service scenario, the technical solution provided in the embodiments of the present application is equally applicable to similar technical problems.

The following describes the technical solution of the present application and how the technical solution of the present application solves the above technical problems with reference to the drawings and specific embodiments. It should be noted that these specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with related laws and regulations and standards, and are provided with corresponding operation entries for the user to select authorization or rejection.

Referring to fig. 2, fig. 2 is a flowchart of a method for determining a geographic location interest point according to an embodiment of the present application, taking an execution subject of the method as an example of the processing device 120 in the system architecture, the method includes steps S201 to S205.

Step S201, POI data of interest points are extracted from the target webpage information.

In this embodiment, the POI data may include a point of interest name, initial urban area information, initial address information. Wherein, the initial urban area information, namely all urban area information appearing in the target webpage information, can comprise one or more urban area information; the initial address information, i.e. all address information present in the target web page information, may comprise one or more address information.

In this embodiment, the target webpage information is published webpage information published on a website, and in order to improve the real-time performance of POI data, the target webpage information of the latest publication (the publication time in a specified time range based on the current time, for example, the current time is 6 months, 5 days, 12:00, and the specified time can be determined to be 6 months, 1 days, 12:00 to 6 months, 5 days, 12:00) can be obtained.

In this embodiment, mainly consider the case that the target web page information includes one point of interest name, in some embodiments, the target web page information may also include a plurality of point of interest names, and for the plurality of point of interest names, the association between the point of interest name and its corresponding urban area and address is also related, where the association rule may be determined by the text distance between the point of interest name and the urban area and address, and the nearest determination of the distance is the urban area and address associated with the corresponding point of interest name.

In one embodiment, considering that the sources of the internet information are different, the information publisher may publish articles about the points of interest using different vocabularies and languages, and in order to reduce the problems of missing extraction of the point of interest data, the step S201 of this embodiment may include the following steps of:

extracting the interest point name, the initial urban area division information and the initial address information from the target webpage information based on a pre-trained data extraction model so as to obtain interest point POI data; the data extraction models comprise a name extraction model, a city division extraction model and an address extraction model, and each data extraction model is obtained based on the corresponding existing interest point data training.

In this embodiment, the data extraction model may employ a global pointer (Bidirectional Encoder Representation from Transformers Global Pointer, bert Global Pointer) model based on bi-directional coded representation of the transducer. It can be appreciated that the Global Pointer model utilizes a Global normalized idea to perform Named Entity Recognition (NER), can indiscriminately recognize nested entities and non-nested entities, can accurately predict entities (such as names, urban areas, addresses, etc.), and simultaneously combines the Bert model, adopts the Bert as an encoder so as to provide a bi-directional characterization function by using the coding mode of the Bert, and better understand the relational converter architecture between language structures and contexts to recognize more accurate entity results. The principle of the model is that on the NER task, the length of an input sequence is n, the number of candidate entities is n (n+1)/2, and the number of real entities is k in n (n+1)/2. Locally for different entity types: if m entity types are provided, the multi-label classification problem of'm ' selecting k correct entities ' "from n (n+1)/2 candidate entities is solved, and the specific classification process can refer to the prior art and will not be repeated herein.

In this embodiment, the name extraction model, the urban area extraction model and the address extraction model are used to extract the point of interest name, the initial urban area information and the initial address information, respectively, and each model is obtained based on the corresponding existing point of interest name, the point of interest urban area and the point of interest address training (Bert Global Pointer model).

In one implementation, the extraction process of the interest point data takes a target webpage as an example, an article is published in the target webpage, the article is firstly segmented into individual words, each word is then converted into a 768-latitude vector, all word vectors of the article are respectively input into a name extraction model, a city region extraction model and an address extraction model for processing, and classification results are output, namely results which are identified as the interest point name, the initial city region information and the initial address information. Illustratively, taking the example of extracting the point of interest name, the extraction result is shown in fig. 3, where 1 and 0 respectively represent the classification result.

In practical application, if the interest point name is not identified, the corresponding webpage information can be filtered out or sent to the user terminal, the user terminal further determines whether the interest point name exists or not, and the initial urban area information and the initial address information identified by the model are combined for further processing.

In some embodiments, the data extraction model may also employ other neural network models, which are not specifically limited in this embodiment.

As a further example, the target web page information may contain one or more web pages, where the user typically publishes content about a point of interest (e.g., a new store business) in an article, and may publish in one or more web pages at the same time. When the processing device searches newly issued webpage information by using the search engine, the processing device also comprises a lot of other invalid webpage information (such as examination published webpages and the like) besides webpages about interest point articles issued by a user, and considering the limited computing resources of the processing device, firstly filtering out the invalid webpages and performing deduplication processing on a plurality of webpages containing the same interest point data. Specifically, as shown in fig. 4, before extracting the POI data from the target webpage information in step S201, the present embodiment may further include the following steps:

step S401, screening out target webpage containing preset keywords from the obtained current webpage, and performing duplication removal processing on the target webpage to obtain duplication-removed target webpage information; the preset keywords are determined based on POI types of interest points, and the POI types at least comprise one of the following types: scenic spots, stores, and houses.

In this embodiment, the preset keyword may be a vocabulary associated with the newly added POI, such as industry, business, completion, etc. For example, a user will typically carry a business/business vocabulary, while for a home will typically carry a completion/acceptance vocabulary. It should be noted that, for different POI types, the same preset keywords may be used, or different preset keywords may be used, for example, in the above example, the scenic spot and store types may be screened by using the industry as the preset keywords, and the residence and store may be screened by using different preset keywords. Further, other POI types, such as industrial parks, etc., may be included in addition to the POI types described above. In practical application, the method can select as many preset keywords as possible by adopting a paraphrasing mode for screening so as to improve the extraction accuracy of POI data.

In this embodiment, after the target web page is screened, the target web page is deduplicated, and the deduplication method may be performed on multiple target web pages issued by the same IP at the same time (or within a period of time), or may be performed by using the point of interest name, where the deduplication method of the target web page is not particularly limited.

With continued reference to fig. 2, step S202 determines urban area information to which the POI data belongs, and determines address information to which the POI data belongs.

In this embodiment, in consideration of that, in the webpage information, besides the urban area information and the address information corresponding to the interest point, other urban area information and address information which are not related to the interest point are generally carried, but the system cannot automatically identify the urban area information and the address information to which the POI data belongs, and the POI data is calibrated by combining all the urban area information and the address information, which results in poor POI generation accuracy. According to the embodiment, the final destination address is determined by determining the urban area information and the address information to which the POI data belong, so that the accuracy of the POI is improved, and redundant POI information is reduced.

In one embodiment, as shown in fig. 5, the determining the urban area information to which the POI data belongs in the step S202 may include the following steps:

step S202a, based on the feature information of each urban area corresponding to the initial urban area information in the POI data, the feature information at least includes one of the following features: the number of times of word appearance, the word appearance position of the urban area, and a first word distance between the urban area and the name of the interest point in the POI data; and respectively obtaining the score of each urban area, and determining the urban area with the highest score as urban area information to which the POI data belong.

In this embodiment, the text distance, i.e. the distance between the text, is for example, A, B in "a and B" 1 word "and" A, B, where the first text distance and the second text distance are used only to represent similar objects, and the two may be the same distance or different distances.

In this embodiment, the text appearance position may be included at the appearance position of the article author, or at the appearance position of the keyword position, the appearance position of the title, or the like, and the weights thereof may be different for these different types of appearance positions. It should be noted that, in addition to the above features, those skilled in the art may determine other features in combination with practical applications to determine a more accurate urban area.

Further, the step S202a obtains the score of each urban area based on the characteristic information of each urban area in the initial urban area information, specifically:

respectively calculating and determining a first product between the first text distance and the distance weight of each urban area, a second product between the text occurrence number and the number weight of each urban area, and a third product between the text occurrence position and the position weight of each urban area; a score for each of the urban areas is determined based on a sum of the first product, the second product, and the third product.

In this embodiment, the cities with the highest comprehensive scores are taken according to the characteristics of each city, so as to improve the accuracy of the POI urban division. The characteristic information is as follows:

first text distance: distance f1 (normalized) of urban section (hereinafter, simply referred to as city) from POI name: as in XXX wine home in city A, the distance between city A and XXX wine home is 0; whereas the century old "XXX winery" comes from B province, leaving C city travel "at a distance of 7 from the XXX winery.

Number of text occurrences: the number of occurrences of a city in an article is the proportion f2 of the number of occurrences of all cities in the article.

Text appearance position 1: whether the city appears in the article title f3 (which may be represented by 0 or 1).

Text appearance position 2: whether the city appears f4 (0 or 1) in the article author.

Word appearance position 3: whether the city appears around some keywords, such as keywords f5 (0 or 1) of the industry, door opening, store detection, etc.

And (3) scoring cities in the initial city information by integrating the characteristic information, and selecting the highest scoring people, wherein each appearing city is scored as follows: score=w1×f1+w2×f2+w3×f3+w4×f4+w5×f5, where f1, f2, f3, f4, and f5 respectively represent the above 4 pieces of characteristic information, w1, w2, w3, w4, and w5 respectively represent the weights corresponding thereto, w1 and w2 are respectively a first weight and a second weight, and w3, w4, and w5 are third weights (which may be the same or different). Alternatively, the sum of the weights of w1, w2, w3, w4, w5 may be 1, and the person skilled in the art may determine the maximum weight proportion of the weights in combination with a large amount of a priori data.

Furthermore, an urban area selection model can be trained by using the artificial neural network model and the prior data, and the urban area information in the POI data is automatically identified by using the urban area selection model, so that the determination efficiency of the urban area is improved. Wherein w1-w5 can be used as a parameter to be learned, and the score of each city is back-propagated through softmax to update the w1-w5 weight parameter.

In one embodiment, as shown in fig. 6, the determining the address information to which the POI data belongs in the step S202 may include the following steps:

s202b, obtaining second text distances between each address corresponding to the initial address information in the POI data and the name of the interest point in the POI data, and determining the address with the shortest second text distance as the address information of the POI data.

Taking the target webpage information as a' A first home XX square field la, an address (180 meters in northwest at the XXX intersection of the Daokou in the B region and the North Daokou in the Daokou), and stopping: 7 months 21 just in the industry, also in the peak period, the parking is difficult, and although the garage exists, the roadside can stop. For the local area of the market A, the market is regular, whether brands, catering and entertainment are carried out, and is quite common, so that the inventor feels that the market A has special skating to be a special bar, and people have the market, eat or drink the market A, bake fish in the way that the market A is a hot pot, bake fish in the way that the market A is a special bar! However, for people living in the eastern region of rice basically, the people who work are simply the heaven, six-layer shopping mall, brand parents, all the people who eat and drink, and the oversized gymnasium, KTV and movie theatre, which drive the consumption level of the whole eastern region of rice to be o, ha-! For the mom loving the walking baby, the recreation ground can punch cards for a period of days, the recreation ground is recently operated, the activities are more than one, the recreation ground is purchased for one, the recreation ground is folded for six times, the recreation ground is fully reduced, the child can be stroked for a while, the child can travel for a while without urgent time, in the target webpage, the northwest 180 meters at the intersection of the middle road of Daway of Daand the North road XXX of Daway B, the distance between the child and the characters of the POI name XX square is nearest, and the child is only 1, and the child is determined as address information of the XX square.

In some embodiments, the determination of the address information of the POI may also be performed by determining the urban area in the manner described above, where the feature information of the determined address and the feature information of the urban area may be the same or different, and in practical applications, the address information of the POI is longer than the text contained in the urban area, and includes area, street, road number, etc., and generally does not appear at the title, author, etc., so that the location of the address may not be considered. Through a large amount of priori data, the closer the distance between the POI address and the POI name is, the more likely the POI address is, and the weight corresponding to the second text distance can be set as the maximum weight.

With continued reference to fig. 2, step S203 obtains a target address corresponding to the POI data based on the urban area information and the address information to which the POI data belongs.

It can be understood that the same address information may exist for different urban areas, and the final target address of POI data, that is, the target address corresponding to the POI name, can be determined by combining the determined urban areas and the determined address information.

Step S204, converting the target address into longitude and latitude coordinates, and step S205, determining the geographic position of the POI data displayed on the electronic map based on the longitude and latitude coordinates.

In the electronic map, each interest point has corresponding longitude and latitude coordinates. According to the embodiment, the target address is converted into the corresponding longitude and latitude coordinates, so that the interest points are conveniently displayed in the corresponding geographic positions of the electronic map. After determining the longitude and latitude coordinates of the POI data, the difference value between the longitude and latitude coordinates of other interest points in the electronic map can be used for determining the geographic position of the POI data displayed on the map.

In one embodiment, the target address may be translated by disassembling the target address and according to a mapping relationship between longitude and latitude coordinates and the disassembled address. Specifically, the step S204 of converting the target address into latitude and longitude coordinates may include the following steps:

disassembling the target address to obtain sub-address information of the target address; and determining longitude and latitude coordinates corresponding to the sub-address information of the target address based on a pre-established mapping relation between the sub-address information and the longitude and latitude coordinates, so as to convert the target address into the longitude and latitude coordinates.

In this embodiment, after determining the final target address of the POI through the above steps, address segmentation tools may be used to extract sub-address information in the target address, where the sub-address information may include information such as a road sign, a parent POI or a reference POI, and it may be understood that the parent POI, i.e. the POI belongs to another POI, for example, the XXX building may be the parent POI of the XXX wine family, and typically carries the storey; the reference POI is carried in the address, and usually no floors are carried, for example, XXX building A, XXX building B and the like are reference POIs of XXX building A. And then combining the urban area division and the extracted information, and acquiring longitude and latitude coordinates through an address-coordinate mapping system. Illustratively:

The mapping relation in the address mapping system is that: * Stone road, house number: no. 10 < - > x1, y1, new store (newly added POI) name is: small-x-packet address: * Stone road number 10. The mapping can be: fushilu 10 # x1, y1 as the coordinates of small steamed stuffed bun; alternatively, the mapping relationship in the address mapping system is that: fushilu, (already) POI: key < - > x2, y2, new store (newly added POI) name: small-x-packet address: fu Dan Lukai market 2-layer small steamed stuffed bun can be combined with city, and the coordinates can be searched by using road and father POI as the coordinates of the small steamed stuffed bun.

In this embodiment, before the above step is based on the pre-established mapping relationship between the sub-address information and the longitude and latitude coordinates, the processing device may further pre-establish the mapping relationship between the sub-address information and the longitude and latitude coordinates, including: for each urban area, all the existing interest point addresses in the urban area are disassembled to extract sub-address information corresponding to each interest point address, wherein the sub-address information at least comprises one of the following sub-addresses: road address, reference point of interest information, or parent point of interest information; and mapping the sub-address information with longitude and latitude coordinates of the corresponding interest point address to obtain a mapping relation between the sub-address information and the longitude and latitude coordinates.

Optionally, the road address includes a road (name), a house number, and the like.

In one implementation, the POI address of each city in the existing POI database is segmented according to the city, and the road house number, father POI information or reference POI information contained in the POI address is extracted. Examples are as follows:

eg1, address: the XX area is the 10 th Fu of road, and the extracted information is: fu x way, house number: number 10; the longitude and latitude coordinates are < - > x1, y1;

eg2, address: the information extracted from the layer 18 of the building a of XX area Fu is that the father POI: the method is free; and (3) road: fu x way; reference POI: XXX building; the longitude and latitude coordinates are < - > x3, y3;

eg3 address: the XX area monster is extracted from 200 meters in SOHO a seater: and (3) road: fushilu reference POI: XXX building; orientation: east; distance: 200 meters. The longitude and latitude coordinates are < - > x4, y4;

further, the mapping between the road sign or the POI and the coordinates is obtained according to the extracted road sign or the POI and the existing POI database coordinates (in practical application, the reference POI can also be calculated by means of azimuth and distance, for example, 200 meters in the east of the building a of XXX, and the coordinates of the POI can be calculated according to the current coordinates and azimuth distance of the building a of XXX).

Referring to fig. 7, fig. 7 is a flowchart of another method for determining a geographic location interest point according to the embodiment of the present application, where, based on the above embodiment, a certain hysteresis may exist in internet information or the same related POI is repeatedly issued at intervals, and in order to effectively avoid newly adding redundant POI in an electronic map, the embodiment determines whether POI data is available when the POI is newly added. Specifically, after the target address is converted into the latitude and longitude coordinates in step S204 and before the geographic position of the POI data displayed on the electronic map is determined based on the latitude and longitude coordinates in step S205, the following steps S701 and S702 may be further included.

Step S701, acquiring an existing interest point of the latitude and longitude coordinate within a preset range based on the latitude and longitude coordinate.

It should be noted that, a person skilled in the art may adapt the preset range, for example, 0 to 0.1 ° in combination with the actual application and the prior art.

Step S702, determining whether the existing interest point and the interest point corresponding to the POI data are the same interest point, if not, executing step S205 to determine the geographic position of the POI data displayed on the electronic map based on the longitude and latitude coordinates, if so, ending the flow.

Optionally, whether the newly added point of interest (i.e., the point of interest corresponding to the POI data) and the existing point of interest are the same point of interest or not is determined, and the difference between the newly added point of interest (i.e., the point of interest corresponding to the POI data) and the POI in the existing POI database can be made according to the name address or the coordinate information, and if the newly added point of interest does not exist or is inconsistent in the POI database, the newly added point of interest can be used as the newly added point of interest. By way of example, the latitude and longitude coordinates of the newly added POI are subjected to difference operation, if the difference is smaller than a specified threshold (for example, 0.0005 °), the latitude and longitude coordinates can be considered to be the same latitude and longitude coordinates, whether the existing POI is revoked (for example, if the situation of a store closing down or the like is that the existing POI data is still stored in a library), the judging process can further judge the similarity of names between the POI by manual or other determining modes, if the corresponding POI is not revoked, if the similarity reaches the specified threshold (for example, 80%), the POI is considered to be the same POI, and if the similarity reaches the specified threshold, the corresponding POI is considered to exist, for example, the newly added POI can cause redundancy of the POI data, if the existing POI is revoked, the newly added POI and the existing POI can be directly considered to be non-identical POI, and the geographical position of the newly added POI displayed on the electronic map can be further determined, and the new POI is added.

Therefore, through the technical scheme, the POI determining efficiency and accuracy in the electronic map are effectively improved, and meanwhile the POI generating cost in the electronic map is reduced.

Referring to fig. 8, fig. 8 is a schematic structural diagram of a geographic location interest point determining device according to an embodiment of the present application, including an extracting module 81, a determining module 82 and an obtaining module 83, where,

an extraction module 81 configured to extract point of interest POI data from the target web page information;

a determining module 82 configured to determine urban area information to which the POI data belongs, and determine address information to which the POI data belongs;

an obtaining module 83 configured to obtain a target address corresponding to the POI data based on the urban area information and the address information to which the POI data belongs;

the determining module 83 is further configured to convert the target address into latitude and longitude coordinates, so as to determine a geographic position of the POI data displayed on the electronic map based on the latitude and longitude coordinates.

In one embodiment, the point of interest POI data includes a point of interest name, initial urban area information, and initial address information; the extraction module 81 is specifically configured to:

Extracting the interest point name, the initial urban area division information and the initial address information from the target webpage information based on a pre-trained data extraction model so as to obtain interest point POI data;

the data extraction models comprise a name extraction model, a city division extraction model and an address extraction model, and each data extraction model is obtained based on the corresponding existing interest point data training.

In one embodiment, the determining module 82 includes:

a first determining unit configured to determine, based on feature information of each urban area corresponding to the initial urban area information in the POI data, the feature information including at least one of the following features: and the number of times and the position of the word appearance of the urban area and the first word distance between the urban area and the name of the interest point in the POI data are respectively obtained, the score of each urban area is respectively obtained, and the urban area with the highest score is determined as the urban area information of the POI data.

In one embodiment, the first determining unit is specifically configured to: respectively calculating and determining a first product between the first text distance and the distance weight of each urban area, a second product between the text occurrence number and the number weight of each urban area, and a third product between the text occurrence position and the position weight of each urban area; a score for each of the urban areas is determined based on a sum of the first product, the second product, and the third product.

In one embodiment, the determining module 82 includes:

and a second determining unit configured to acquire second text distances between respective addresses corresponding to the initial address information in the POI data and the names of the points of interest in the POI data, and determine an address having a shortest second text distance as address information to which the POI data belongs.

In one embodiment, the determining module 82 includes:

the disassembly unit is used for disassembling the target address to obtain sub-address information of the target address;

and the third determining unit is used for determining longitude and latitude coordinates corresponding to the sub-address information of the target address based on the pre-established mapping relation between the sub-address information and the longitude and latitude coordinates so as to convert the target address into the longitude and latitude coordinates.

In one embodiment, the method further includes a building module configured to pre-build a mapping relationship between sub-address information and longitude and latitude coordinates, including: for each urban area, all the existing interest point addresses in the urban area are disassembled to extract sub-address information corresponding to each interest point address, wherein the sub-address information at least comprises one of the following sub-addresses: road address, reference point of interest information, or parent point of interest information; and mapping the sub-address information with longitude and latitude coordinates of the corresponding interest point address to obtain a mapping relation between the sub-address information and the longitude and latitude coordinates.

In one embodiment, the apparatus further comprises:

the screening and de-duplication module is used for screening out target webpages containing preset keywords from the acquired current webpages, and performing de-duplication processing on the target webpages to obtain de-duplicated target webpage information;

the preset keywords are determined based on POI types of interest points, and the POI types at least comprise one of the following types: scenic spots, stores, and houses.

In one embodiment, the apparatus further comprises:

the judging module is used for acquiring the existing interest points of the longitude and latitude coordinates within a preset range based on the longitude and latitude coordinates, and judging whether the interest points corresponding to the existing interest points and the POI data are the same interest points or not;

the determining module is specifically configured to determine, when the judging module judges no, a geographic position of the POI data displayed on the electronic map based on the longitude and latitude coordinates.

Correspondingly, the embodiment of the application also provides a computer device, as shown in fig. 9, which comprises: a processor 71, a memory 92 communicatively coupled to the processor 91;

the memory 91 stores computer-executable instructions;

The processor 92 executes the computer-executable instructions stored in the memory 91 to implement the method for determining the geographic location interest point according to the above embodiment, where the memory 92 and the processor 91 are connected through the bus 93.

The relevant descriptions and effects corresponding to the steps in the embodiments corresponding to fig. 2 to fig. 7 may be understood correspondingly, and are not described in detail herein.

The embodiment of the application correspondingly provides a computer readable storage medium, and the computer readable storage medium stores computer execution instructions or programs, and the computer execution instructions or programs are used for realizing the method for determining the geographic position interest points corresponding to the embodiment when being executed by a processor.

The computer readable storage medium may be, among other things, ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

The relevant descriptions and effects corresponding to the steps in the embodiments corresponding to fig. 2 to fig. 7 may be understood correspondingly, and are not described in detail herein.

The embodiment of the application correspondingly provides a computer program product, and the computer program product stores computer execution instructions or programs, and the computer execution instructions or programs are used for realizing the method for determining the geographic position interest points corresponding to the embodiment when being executed by a processor.

The relevant descriptions and effects corresponding to the steps in the embodiments corresponding to fig. 2 to fig. 7 may be understood correspondingly, and are not described in detail herein.

The embodiment of the application correspondingly further provides a chip, which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor is used for calling and running the computer program from the memory and executing the method for determining the geographic position interest point corresponding to the embodiment.

The relevant descriptions and effects corresponding to the steps in the embodiments corresponding to fig. 2 to fig. 7 may be understood correspondingly, and are not described in detail herein.

Fig. 10 is a block diagram of a terminal device 800, which may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, etc., as shown in an exemplary embodiment of the present application.

Terminal device 800 can include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.

The processing component 802 generally controls overall operation of the terminal device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interactions between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the terminal device 800. Examples of such data include instructions for any application or method operating on terminal device 800, contact data, phonebook data, messages, pictures, video, and the like. The memory 804 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply component 806 provides power to the various components of the terminal device 800. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the terminal device 800.

The multimedia component 808 includes a screen between the terminal device 800 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or sliding action, but also the duration and pressure associated with the touch or sliding operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. The front camera and/or the rear camera may receive external multimedia data when the terminal device 800 is in an operation mode, such as a photographing mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the terminal device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 further includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of the terminal device 800. For example, the sensor assembly 814 may detect an on/off state of the terminal device 800, a relative positioning of the assemblies, such as a display and keypad of the terminal device 800, the sensor assembly 814 may also detect a change in position of the terminal device 800 or a component of the terminal device 800, the presence or absence of a user's contact with the terminal device 800, an orientation or acceleration/deceleration of the terminal device 800, and a change in temperature of the terminal device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate communication between the terminal device 800 and other devices, either wired or wireless. The terminal device 800 may access a wireless network based on a communication standard, such as WiFi,3G, 4G, 5G, or other standard communication networks, or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the terminal device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic elements for performing the method for determining a geographic location interest point provided in any one of the embodiments corresponding to fig. 2-7 of the present application.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 804 including instructions executable by processor 820 of terminal device 800 to perform the above-described method of determining a geographic location point of interest. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

The embodiments of the present application further provide a non-transitory computer readable storage medium, where the instructions in the storage medium, when executed by the processor of the terminal device, enable the terminal device 800 to perform the method for determining the geographic location interest point provided in any of the embodiments corresponding to fig. 2 to fig. 7 of the present application.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules is merely a logical function division, and there may be additional divisions of actual implementation, e.g., multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (11)

1. A method for determining a geographic location point of interest, comprising:

extracting POI data from the target webpage information;

determining urban area information to which the POI data belong, and determining address information to which the POI data belong;

acquiring a target address corresponding to the POI data based on urban area information and the address information to which the POI data belong;

And converting the target address into longitude and latitude coordinates so as to determine the geographic position of the POI data displayed on the electronic map based on the longitude and latitude coordinates.

2. The method of claim 1, wherein the point of interest POI data comprises a point of interest name, initial civic region information, and initial address information; the extracting the POI data from the target webpage information comprises the following steps:

extracting interest point names, initial urban area division information and initial address information from target webpage information based on a pre-trained data extraction model to obtain POI data;

the data extraction models comprise a name extraction model, a city division extraction model and an address extraction model, and each data extraction model is obtained based on the corresponding existing interest point data training.

3. The method according to claim 1 or 2, wherein the determining urban area information to which the POI data belongs includes:

based on the characteristic information of each urban area corresponding to the initial urban area information in the POI data, respectively obtaining the score of each urban area, and determining the urban area with the highest score as the urban area information to which the POI data belongs;

Wherein the characteristic information comprises at least one of the following characteristics: the number of occurrences of text in the urban area, the location of the occurrence of text, and a first text distance between the urban area and the name of the point of interest in the POI data.

4. The method of claim 3, wherein the obtaining the score of each urban area based on the characteristic information of each urban area in the initial urban area information comprises:

respectively calculating and determining a first product between the first text distance and the distance weight of each urban area, a second product between the text occurrence number and the number weight of each urban area, and a third product between the text occurrence position and the position weight of each urban area;

a score for each of the urban areas is determined based on a sum of the first product, the second product, and the third product.

5. The method according to claim 1 or 2, wherein the determining address information to which the POI data belongs includes:

and acquiring second text distances between each address corresponding to the initial address information in the POI data and the name of the interest point in the POI data, and determining the address with the shortest distance in the second text distances as the address information of the POI data.

6. The method of claim 1, wherein the converting the target address into latitude and longitude coordinates comprises:

disassembling the target address to obtain sub-address information of the target address;

and determining longitude and latitude coordinates corresponding to the sub-address information of the target address based on a pre-established mapping relation between the sub-address information and the longitude and latitude coordinates, so as to convert the target address into the longitude and latitude coordinates.

7. The method according to claim 6, wherein before determining the latitude and longitude coordinates corresponding to the sub-address information of the target address based on the pre-established mapping relationship between the sub-address information and the latitude and longitude coordinates, the method further comprises:

for each urban area, all the existing interest point addresses in the urban area are disassembled to extract sub-address information corresponding to each interest point address, wherein the sub-address information at least comprises one of the following sub-addresses: road address, reference point of interest information, or parent point of interest information;

and mapping the sub-address information with longitude and latitude coordinates of the corresponding interest point address to obtain the mapping relation between the sub-address information and the longitude and latitude coordinates.

8. The method of any one of claims 1-6, wherein prior to extracting the point of interest POI data from the target web page information, the method further comprises:

screening out target web pages containing preset keywords from the obtained current web pages, and performing duplication removal processing on the target web pages to obtain duplication-removed target web page information;

the preset keywords are determined based on POI types of interest points, and the POI types at least comprise one of the following types: scenic spots, stores, and houses.

9. The method of any of claims 1-6, further comprising, after converting the target address to latitude and longitude coordinates, and before determining a geographic location of the POI data for display on an electronic map based on the latitude and longitude coordinates:

acquiring the existing interest points of the longitude and latitude coordinates within a preset range based on the longitude and latitude coordinates;

and judging whether the existing interest points and the interest points corresponding to the POI data are the same interest points, if not, determining the geographic position of the POI data displayed on the electronic map based on the longitude and latitude coordinates.

10. A device for determining a geographic location point of interest, comprising:

An extraction module configured to extract point of interest POI data from the target web page information;

a determining module configured to determine urban area information to which the POI data belongs, and determine address information to which the POI data belongs;

the acquisition module is used for acquiring a target address corresponding to the POI data based on urban area information and address information to which the POI data belong;

the determining module is further configured to convert the target address into latitude and longitude coordinates, so as to determine a geographic position of the POI data displayed on the electronic map based on the latitude and longitude coordinates.

11. Computer device/readable storage medium/program product, characterized in that it has stored therein computer-executable instructions or programs which, when executed by a processor, are adapted to carry out the method of determining a geographical location point of interest according to any one of claims 1 to 9.