CN112269925A

CN112269925A - Method and device for acquiring geographical location point information

Info

Publication number: CN112269925A
Application number: CN202011117316.0A
Authority: CN
Inventors: 黄际洲; 张昊
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2020-10-19
Filing date: 2020-10-19
Publication date: 2021-01-26
Anticipated expiration: 2040-10-19
Also published as: CN112269925B

Abstract

The application discloses a method and a device for acquiring geographical location point information, and relates to the technical field of big data. The specific implementation scheme is as follows: acquiring a newly generated spatial relationship list, wherein the spatial relationship list comprises more than one spatial relationship data, and the spatial relationship data comprises spatial relationship information between two adjacent geographical position points; serially connecting the spatial relationship data in the spatial relationship list to obtain at least one serial set; if at least one spatial relationship data in the serial set exists in the existing knowledge base, writing the spatial relationship data in the serial set into the knowledge base; and analyzing the geographical position points contained in the spatial relationship data newly written into the knowledge base to obtain the geographical position point information contained in the spatial relationship data newly written into the knowledge base. The method and the device can realize automatic discovery of the changed geographical location point information.

Description

Method and device for acquiring geographical location point information

Technical Field

The present application relates to the field of computer application technologies, and in particular, to a method and an apparatus for acquiring geographical location point information in the field of big data technologies.

Background

The main aim of map products is to depict the real world, so that users can be helped to inquire the information of geographical position points and various travel demands can be further met. However, the information of the geographical location point in reality is changed for various reasons. If the information of the geographical position points collected by the map product is inaccurate, the user cannot find the destination according to the requirement.

The current method for acquiring the geographical location point information commonly used in the industry adopts crowd-sourced acquisition and manual verification. The method relies on the information of geographical location points reported by various channels, such as shop reports, user uploads, internet information and the like, and then the information is manually checked and brought online based on various information by internal staff familiar with the service. However, this method relies heavily on manpower, which causes problems of low efficiency, untimely information update, and low coverage.

Disclosure of Invention

In view of this, the present application provides a method and an apparatus for obtaining geographical location point information, so as to implement automatic discovery of the geographical location point information.

In a first aspect, the present application provides a method for obtaining geographic location point information, including:

acquiring a newly generated spatial relationship list, wherein the spatial relationship list comprises more than one spatial relationship data, and the spatial relationship data comprises spatial relationship information between two geographical position points;

serially connecting the spatial relationship data in the spatial relationship list to obtain at least one serial set;

if at least one spatial relationship data in the serial set exists in the existing knowledge base, writing the spatial relationship data in the serial set into the knowledge base;

and analyzing the geographical position points contained in the spatial relationship data newly written into the knowledge base to obtain the geographical position point information contained in the spatial relationship data newly written into the knowledge base.

In a second aspect, the present application provides an apparatus for acquiring geographic location point information, including:

the system comprises a spatial relationship acquisition unit, a spatial relationship processing unit and a spatial relationship processing unit, wherein the spatial relationship acquisition unit is used for acquiring a newly generated spatial relationship list, the spatial relationship list comprises more than one spatial relationship data, and the spatial relationship data comprises spatial relationship information between two geographical position points;

the spatial relationship concatenation unit is used for concatenating the spatial relationship data in the spatial relationship list to obtain at least one concatenation set;

the knowledge base processing unit is used for writing the spatial relationship data in the serial set into the knowledge base if at least one spatial relationship data in the serial set exists in the existing knowledge base;

and the information generation unit is used for analyzing the geographical position points contained in the spatial relationship data newly written into the knowledge base to obtain the geographical position point information contained in the spatial relationship data newly written into the knowledge base.

In a third aspect, the present application provides an electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method described above.

In a fourth aspect, the present application provides a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method described above.

Through the technical scheme provided by the application, the automatic discovery of the geographical position point information can be realized, the dependence on manpower is greatly reduced, the efficiency is improved, and the labor cost is reduced.

Other effects of the above-described alternative will be described below with reference to specific embodiments.

Drawings

The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:

FIG. 1 illustrates an exemplary system architecture to which the methods or apparatus of embodiments of the present application may be applied;

FIG. 2 is a flow chart of a main method provided by an embodiment of the present application;

FIG. 3 is a flowchart of a detailed method provided by an embodiment of the present application;

FIG. 4 is a flowchart of a method for generating a spatial relationship list according to an embodiment of the present application;

fig. 5 is a schematic diagram illustrating a calculation of coordinates of a geographic location point by using shooting parameters according to an embodiment of the present application;

FIG. 6 is a flowchart of another method for generating a spatial relationship list according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of a geographic location point spatial relationship extraction model provided in the embodiment of the present application;

FIG. 8 is a block diagram of an apparatus according to an embodiment of the present disclosure;

FIG. 9 is a block diagram of an electronic device used to implement embodiments of the present application.

Detailed Description

The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1 illustrates an exemplary system architecture to which the methods or apparatus of embodiments of the present application may be applied. As shown in fig. 1, the system architecture may include

terminal devices

101 and 102, a network 103, and a server 104. The network 103 serves as a medium for providing communication links between the

terminal devices

101, 102 and the server 104. Network 103 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

A user may interact with server 104 through network 103 using

terminal devices

101 and 102. Various applications, such as a map-like application, a web browser application, a communication-like application, and the like, may be installed on the

terminal apparatuses

101 and 102.

The

terminal devices

101 and 102 may be various types of user devices capable of running a map-like application. Including but not limited to smart phones, tablets, PCs, smart televisions, etc. The apparatus for acquiring the geographical location point information provided by the present application may be configured and operated in the server 104, or may be operated in a device independent from the server 104. It may be implemented as a plurality of software or software modules (for example, for providing distributed services), or as a single software or software module, which is not specifically limited herein. The server 104 may interact with the map database 105, and specifically, the server 104 may obtain data from the map database 105 or store data in the map database 105. The map database 105 stores therein relevant data including geographical location points, such as status, coordinate information, and the like.

For example, the device for acquiring the geographical location point information is configured and operated in the server 104, and the server 104 acquires the geographical location point information by using the method provided in the embodiment of the present application, and then updates the map database 105 by using the acquired geographical location point information. The server 104 is capable of querying the map database 105 in response to a query request of the

terminal device

101, 102 and returning relevant information of the queried geographical location point, including a state of the geographical location point, coordinate information, route query information based on the geographical location point information, navigation information, and the like, to the

terminal device

101, 102.

The server 104 may be a single server or a server group including a plurality of servers. In addition 104 may be other computer systems or processors with higher computing capabilities than in the form of servers. It should be understood that the number of terminal devices, networks, servers, and databases in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, servers, and databases, as desired for implementation.

The geographic position point referred to in the application refers to a geographic position point in map application, and the geographic position point can be inquired and browsed by a user, displayed to the user and the like. These geo-location points have basic attributes such as coordinates (e.g., latitude and longitude), name, administrative address, type, status, etc. Wherein the geo-location Point may include, but is not limited to, a POI (Point Of Interest), an AOI (Area Of Interest), a ROI (region Of Interest), etc. In the following examples, POI is described as an example. A POI is a term in a geographic information system, which broadly refers to all geographic objects that can be abstracted as points, a POI can be a house, a shop, a mailbox, a bus station, a school, a hospital, etc. The main purpose of the POI is to describe the position of a thing or an event, thereby enhancing the description capability and the query capability of the position of the thing or the event.

Fig. 2 is a flowchart of a main method provided in an embodiment of the present application, and as shown in fig. 2, the method may include the following steps:

in 201, a newly generated spatial relationship list is obtained.

The newly generated spatial relationship list in the application is obtained by extracting spatial relationship information between geographic position points from at least one of professionally collected live-action images, crowd-sourced collected live-action images and internet texts.

The acquired spatial relationship list comprises more than one spatial relationship data, and the spatial relationship data comprises spatial relationship information between two geographical position points. As a preferred embodiment, the spatial relationship data may include spatial relationship information between two adjacent geographical location points.

For example, the spatial relationship data may be represented in the form of a quadruple, where S and O are information of the geographic location point, and for example, a unique ID of the geographic location point may be used, P is a spatial relationship type, and a is a spatial relationship value.

The type of spatial relationship mainly includes the types of spatial relationships in some directions, such as east, south, west, north, southeast, northeast, southwest, northwest, left, right, upstairs, downstairs, and so on. Values may include values for distances, values for floors, and the like. For example, the quadruplet < qinghua science and technology garden, qinghua university southeast door, south, 100 meters > means "qinghua science and technology garden 100 meters south at qinghua university southeast door".

At 202, the spatial relationship data in the newly generated spatial relationship list is concatenated to obtain at least one concatenated set.

In this step, when the spatial relationship data are concatenated, if two spatial relationship data include a same geographic location point, the two spatial relationship data may be concatenated, and so on, the spatial relationship data may be concatenated to form a concatenated set. If one spatial relationship data and other spatial relationship data in a newly generated spatial relationship list cannot be connected in series, the spatial relationship data forms a series set by itself.

For example, assume that the newly generated spatial relationship list contains the following four-tuples:

<S,O,P,A>、<S1,S,P1,A1>、<O,O1,P2,A2>、<S2,O2,P3,A3>

then < S, O, P, a >, < S1, S, P1, a1>, < O, O1, P2, a2> constitute a concatenated set; < S2, O2, P3, A3> form a concatenated set.

At 203, if at least one spatial relationship data in the concatenated set exists in the existing knowledge base, the spatial relationship data in the concatenated set is written into the knowledge base.

In the embodiment of the present application, the knowledge base stores spatial relationship data, and the trusted spatial relationship data determined each time is stored as the spatial relationship data. For the concatenated set obtained by the newly generated spatial relationship list, if at least one spatial relationship data exists in the existing knowledge base, the at least one spatial relationship is credible. And each spatial relationship in the concatenated set is concatenated with the trusted spatial relationship, so that the spatial relationship data in the concatenated set can be considered to be trusted and written into the knowledge base.

In 204, the geographical location points included in the spatial relationship data newly written into the knowledge base are analyzed to obtain geographical location point information included in the spatial relationship data newly written into the knowledge base.

The geographical location point information obtained in this step may include coordinate information of the geographical location point and/or state information of the geographical location point. The state information is mainly embodied in the change of the geographic location point, such as addition, closing, change and the like.

In a preferred embodiment, the coordinate information of the other geographic position points in the spatial relationship data newly written in the knowledge base is obtained by using the known coordinate information of at least one geographic position point included in the spatial relationship data newly written in the knowledge base. The known coordinate information can be obtained from the geographic database, or can be obtained from a specially acquired live-action image.

As a preferred embodiment, the spatial relationship data newly written into the knowledge base may be compared with the spatial relationship data of the existing knowledge base to obtain the geographical position point state information of the area corresponding to the spatial relationship data newly written into the knowledge base.

In the embodiment of the present application, the map database may store related information of the geographic location points, and therefore, information of each geographic location point determined in this step is also stored in the geographic database.

Therefore, the method and the device can realize automatic discovery of the geographical location point information by processing the newly generated spatial relationship data, greatly reduce dependence on manpower, improve efficiency and reduce labor cost.

According to the traditional mode of manually reporting and manually checking the geographical position point information, timeliness and information coverage rate completely depend on manually collected contents, and the mode provided by the application determines the geographical position information based on spatial relationship data, so that timeliness and information coverage rate are remarkably improved.

The traditional mode of manually reporting and auditing the geographical location point information is relied on, which may cause inaccuracy of the geographical location point information due to errors of user behaviors, errors of user equipment and the like, and the mode provided by the application reduces dependence on the user behaviors and the user equipment and improves accuracy of the geographical location point information.

Fig. 3 is a flowchart of a detailed method provided by an embodiment of the present application, and as shown in fig. 3, the method may include the following steps:

in 301, spatial relationship information between adjacent geographic location points is extracted from at least one of professionally collected live-action images, crowd-sourced collected live-action images, and internet texts, to obtain a newly generated spatial relationship list.

The preferred implementation of extracting the spatial relationship information between adjacent geographical location points involved in this step will be described in detail in the following examples.

At 302, the spatial relationship data in the newly generated spatial relationship list is concatenated to obtain at least one concatenated set.

This step is the same as step 202 in the second embodiment, and is not described herein again.

Then the following steps are respectively executed for each series set:

in 303, judging whether at least one spatial relationship data exists in the existing knowledge base in the current serial connection set, if so, executing 304; otherwise, 306 is performed.

As a preferred embodiment, before this step is performed, the geographical location area may be divided into cells in advance, and there is an overlapping area between adjacent cells. The spatial relationship data in the knowledge base is corresponding to at least one cell in advance according to the geographic position of the contained geographic position point.

Since the positioning accuracy may reach an error of more than a hundred meters, the geographical location area may be divided into cells, such as 1km × 1km, with some overlap between adjacent cells, for example 0.5 km. Therefore, the problem that adjacent geographical position points can not fall in the same cell when the geographical position points are positioned at the edge of the cell can be effectively solved when the coordinates of any geographical position point fall in the range of the cell.

Each cell may be numbered and indexed with spatial relationship data corresponding to adjacent geographic location points whose coordinates fall within the cell. For example, some quad-data R_xBag ofThe coordinates of two geographical location points are in the cell S_iThen the quadruple data R is considered_xCorresponding region grid S_i。

For any spatial relationship data, namely a quadruple, fuzzy coordinate information of two adjacent geographical position points contained in the spatial relationship data can be acquired. Because the coordinate information of the geographic position point collected by other devices usually has more or less positioning accuracy problems except professional devices, in the embodiment of the present application, a positioning accuracy may be uniformly obtained for the coordinate information of the geographic position point collected by the terminal device, for example, only one bit after a decimal point is reserved, and the coordinate information is considered as fuzzy coordinate information. In the present application, when the positioning accuracy of the fuzzy coordinate information is obtained, the corresponding determination can be performed according to the size of the cell adopted in the division.

As a pre-selected embodiment, this step may be executed by respectively taking each spatial relationship data in the current concatenated set as the current spatial relationship data: determining the grids to which the geographic position points contained in the current spatial relationship data belong; inquiring current spatial relation data in the spatial relation data corresponding to the cell in the knowledge base, and if the current spatial relation data are inquired, determining that the current spatial relation data exist in the existing knowledge base; otherwise, determining that the current spatial relationship data does not exist in the existing knowledge base.

In the preferred embodiment provided by the present application, since the adjacent geographic location points included in the spatial relationship data are necessarily located in the same cell, the current spatial relationship data can be queried in the spatial relationship data corresponding to the cell in the knowledge base. When the region lattice to which the geographical position point belongs is determined, the region lattice to which the geographical position point belongs can be determined according to the fuzzy coordinate information of the geographical position point included in the current spatial relationship.

At 304, the spatial relationship data in the concatenated collection is written to a knowledge base.

At 305, a determination is made as to whether there are any more unprocessed concatenated sets, and if so, execution 303 continues on the next concatenated set, otherwise 308 is performed.

If a certain spatial relationship data in the concatenated set exists in the existing knowledge base, because the spatial relationship data stored in the knowledge base is the spatial relationship data which is considered to be correct, and the spatial relationship data in the concatenated set and the correct spatial relationship data have a reasonable concatenated relationship, the spatial relationship data contained in the concatenated set can be considered to be correct, and can be written into the knowledge base.

For example, in the newly generated spatial relationship data list, < S, O, P, a >, < S1, S, P1, a1>, < O, O1, P2, a2> form a concatenated set, and if there is < O, O1, P2, a2> in the existing knowledge base, < S, O, P, a >, < S1, S, P1, a1>, < O, O1, P2, a2> is written into the knowledge base.

In 306, judging whether the spatial relation data obtained by the specially collected live-action image exists in the current serial collection, if so, executing 304; otherwise, 307 is performed.

If certain spatial relationship data in the concatenated set does not exist in the existing knowledge base, whether the scene image acquired by the profession exists in the current concatenated set can be further judged. Therefore, if a certain spatial relationship data in the current serial set is obtained from the professional collected live-action image, the spatial relationship data can be considered to be correct, and the spatial relationship data in the serial set and the correct spatial relationship data have a reasonable serial relationship, so that the spatial relationship data contained in the serial set can be considered to be correct, and can be written into a knowledge base.

At 307, the spatial relationship data in the concatenated set is written to the list to be verified, which proceeds to execution 305.

If the spatial relationship data in the concatenated set does not exist in the existing knowledge base and the spatial relationship data obtained from the professionally collected live-action images does not exist, the spatial relationship data in the concatenated set can be written into the list to be verified. And moreover, a professional acquisition team can be further informed, and then the professional acquisition team acquires and verifies the information of each geographic position point of the corresponding area in the list to be verified.

After all the serial sets are processed, 308 is executed, that is, the coordinate information of other geographic position points in the spatial relationship data newly written into the knowledge base is obtained by using the known coordinate information of at least one geographic position point included in the spatial relationship data newly written into the knowledge base.

The known coordinate information refers to accurate coordinate information, and the positioning accuracy of the known coordinate information is higher than that of the fuzzy coordinate information.

As a preferred embodiment, if the spatial relationship data newly written in the knowledge base includes spatial relationship data obtained from a professional captured live-action image, the spatial relationship-based estimation is performed on another geographical position point included in the spatial relationship data newly written in the knowledge base using the coordinate information of the geographical position point carried by the professional captured live-action image, so as to obtain coordinate information of the other geographical position point, and the coordinate information is written in the map database.

Since the spatial relationship data includes the spatial relationship information between two adjacent geographical position points, if the coordinate information of one of the geographical position points is known, the coordinate of the other geographical position point can be estimated based on the spatial relationship. The spatial relationship data newly written into the knowledge base has a serial relationship, so that the coordinate information of the geographic position point contained in the spatial relationship data newly written into the knowledge base can be obtained by calculating based on a plurality of spatial relationship data.

In another preferred embodiment, when the geographical position point included in the spatial relationship data newly written in the knowledge base has the accurate coordinate information in the existing map database, the geographical position point having the accurate coordinate information is used to calculate the other geographical position point included in the spatial relationship data newly written in the knowledge base based on the spatial relationship, so as to obtain the coordinate information of the other geographical position point, and the coordinate information is written in the map database.

In the embodiment of the application, the map database stores geographical position points with known accurate coordinate information, and the coordinate information in the map database is used when the map products are on line. If the spatial relationship data newly written into the knowledge base has accurate coordinate information of a certain geographical position point in the existing map database, and the spatial relationship data newly written into the knowledge base has a serial relationship, the coordinate information of other geographical position points can be obtained based on the calculation of the spatial relationship.

Based on the steps, coordinate information of a batch of geographic position points can be obtained. In some scenarios, in addition to the coordinate information of the geographic location point, it is also necessary to know the state change of the geographic location point in time. Then it may be further performed 309 that state change information for the geographical location point in the spatial relationship data newly written to the repository is determined.

As a preferred embodiment, if two adjacent geographical location points included in the spatial relationship data newly written in the knowledge base are not adjacent in the existing knowledge base, the state of the geographical location point between the two adjacent geographical location points in the existing knowledge base is determined to be closed, and the spatial relationship data of the geographical location point included in the knowledge base in the closed state is deleted.

For example, if the spatial relationship data newly written into the knowledge base includes < S, O, P, a >, and the geographic location points S and O in the existing knowledge base are not adjacent, but there are < S, S4, P4, a4> and < S4, O, P5, a5>, it indicates that the geographic location point S4 is not present, i.e., is in the off state. The knowledge base containing the spatial relationship data of S4 may be further deleted.

In a preferred embodiment, when the coordinate information of the geographical position point a included in the spatial relationship data newly written in the knowledge base overlaps with the coordinate information of another geographical position point B in the existing map database, the state of the geographical position point B is determined to be changed, the state of the geographical position point a is newly added, and the spatial relationship data of the geographical position point whose state is changed in the knowledge base is deleted.

In a preferred embodiment, if the geographical position point included in the spatial relationship data newly written in the knowledge base does not exist in the existing map database, the state of the geographical position point is determined to be newly added.

With respect to the specific manner of newly generating the spatial relationship list in

steps

201 and 301 in the above embodiments, two embodiments are listed for detailed description.

Fig. 4 is a flowchart of a method for generating a spatial relationship list according to an embodiment of the present application, and as shown in fig. 4, the method may include the following steps:

in 401, signboard recognition is performed on the live-action image collected by each terminal device, and a geographical location point pair included in the live-action image is determined.

In the application, the spatial relationship between the geographical position points is determined by using a live-action image obtained by shooting the geographical position points by the terminal equipment. The live-action image obtained by shooting the geographical position point by the terminal equipment can be a live-action image acquired from a professional source or a live-action image acquired from a public source.

After the live-action images collected by each terminal device are obtained, signboard recognition can be carried out on the live-action images, and the live-action images containing at least two signboards are screened out. And then, character recognition of the signboard is carried out on the live-action image containing at least two signboards, and the geographical location point pairs contained in the live-action image are determined. The pair of geographical location points referred to in this application consists of two different geographical location points.

The live-action image refers to an image obtained by shooting a geographical position point in the field by the terminal device. The live-action image used in the present application needs to include at least two signs, so that the shooting parameters of the live-action image are subsequently used to determine the spatial relationship between the geographic location points corresponding to the two signs. The signboard is a signboard hung in front of a building door corresponding to a geographical position point and used as a sign. Such as a shop name sign hanging out at the store doorway, a sign of a school name at the school doorway, and so forth.

When the signboard is discriminated from the live-action image, a signboard discrimination model obtained by training in advance may be used. The method comprises the steps of firstly carrying out region division on a live-action image, wherein a signboard in the live-action image is a closed region in general, so that the live-action image can be subjected to region identification and division, inputting a signboard judgment model for the determined closed region, and outputting a judgment result of whether the closed region is the signboard region or not by the signboard judgment model.

The signboard judging model is actually a classification model, some live-action images can be collected in advance, signboard areas and non-signboard areas are marked in the real-action images to serve as positive and negative samples respectively, and then the classification model is trained to obtain the signboard judging model.

When character recognition of signboards is performed on live-action images including at least two signboards, and geographic position point pairs included in the live-action images are determined, clustering can be performed on the screened live-action images based on the positioning distance between the live-action images to obtain more than one similar positioning cluster. And then, clustering the images in the similar positioning clusters respectively based on the content similarity to obtain more than one similar content cluster, so that the live-action images contained in the similar positioning clusters are close to each other in shooting position. And clustering the images in the similar positioning clusters based on the content similarity to obtain more than one similar content cluster. And then respectively carrying out signboard judgment on the live-action images in the similar content clusters to determine signboard areas. The signboard region specified in each live view image is subjected to ID (identification) uniqueness processing. And determining a signboard area ID sequence contained in each live-action image and acquiring a frequent item sequence from the signboard area ID sequence. And then character recognition is carried out on the signboard area corresponding to each ID in the frequent item sequence. And aiming at the live-action image containing the frequent item sequence, selecting n-1 geographical position point pairs from the frequent item sequence, wherein the set formed by the n-1 geographical position point pairs contains the geographical position points corresponding to all the signboard IDs in the frequent item sequence, the sum of the corresponding signboard distances of each geographical position point pair in the live-action image is minimum, and n is the number of the signboards contained in the frequent item sequence.

At 402, at least two live-action images collected by the same terminal device and containing the same geographical location point pair are obtained.

After the geographical location point pairs of each live-action image are mined, the reverse indexes of the live-action images can be established by utilizing the geographical location point pairs. In this step, the reverse index may be searched to obtain the live-action images of the same geographical location point pair, but it is required to ensure that the obtained live-action images are collected by the same terminal device and the number of the obtained live-action images is at least two.

In 403, the spatial relationship of the same geographical location point pair is determined by using the shooting parameters of at least two live-action images.

The shooting parameters involved in this step mainly include:

1) the positioning coordinates of the live-action image are coordinates of a shooting point for shooting the live-action image, and generally, when the terminal device shoots the image, the current positioning coordinates of the terminal device are acquired as the positioning coordinates of the shot image.

2) Shooting angles and shooting distances of the signs of the geographical location point pairs in the live-action images.

Due to the setting or the function of the shooting equipment, some live-action images have the shooting parameters, and some live-action images do not have the shooting parameters. In the present application, only live-action images having the above-described imaging parameters are acquired and used to determine the spatial relationship of the geographical point pairs.

In the step, the shooting parameters of the live-action image are mainly utilized, and calculation is carried out based on the geometric relations such as sine theorem and cosine theorem, so that the coordinates of two geographical position points in the geographical position point pair are obtained; the spatial relationship of the two geographical location points is determined based on the coordinates of the two geographical location points.

Taking fig. 5 as an example, it is assumed that two live-action images captured by the same terminal device each include a geographical location point pair composed of a geographical location point M and a geographical location point N. The corresponding shooting position coordinate in the first live-action image is a shooting point A, and the included angles alpha and beta in the image can be determined by the shooting angle. The corresponding shooting position coordinate in the second live-action image is a shooting point B, and the included angles gamma and delta in the image can be determined by the shooting angle. The distance x between the two shot points can be obtained from the positioning coordinates of the two live-action images.

According to the sine theorem, the distance P between the geographic position point M and the shooting point a and the distance Q between the geographic position point N and the shooting point a can be obtained:

according to the distance information, the included angle information and the positioning coordinates of the shooting points A and B, the coordinates of the two geographic position points can be determined.

It should be noted that, since the same terminal device may capture more than two live-action images containing the same geographic location point pair (M, N), in this step, two live-action images may be actually used to determine the coordinates of the geographic location points M and N. For this case, the coordinates of the geographic location point M may be obtained by processing the multiple determined coordinates of the geographic location point M in a manner such as averaging, clustering, or median. Similarly, the coordinates of the geographic position point N are obtained after the determined multiple coordinates of the geographic position point N are processed in manners such as averaging, clustering center finding, median finding, and the like.

After the coordinates of the two geographical position points are obtained, the relative position relationship of the two geographical position points in space, such as the relationship in direction and the distance relationship, can be determined.

The information on the spatial relationship related in the embodiment of the present application may include: the type and value of the spatial relationship. The types of spatial relationships primarily include types of spatial relationships in some orientations, such as east, south, west, north, southeast, northeast, southwest, northwest, left, right, upstairs, downstairs, and so forth. Values may include values for distances, values for floors, and the like. It can be seen that the spatial relationship of the geographical location points is relative.

Fig. 6 is a flowchart of another method for generating a spatial relationship list according to an embodiment of the present application, and as shown in fig. 6, the method may include the following steps:

in 601, a text containing geo-location point information is obtained from the internet.

In the present application, a text containing information of the geographic location point may be obtained from an official network associated with the geographic location point, for example, a text of "drag for six layers of shopping center of five-color city in Qinghe Zhongjie of Haihe district of Beijing city on seabed" from the submarine drag-out official network, and a text of "Qinghua science and technology park of Beijing Qinghua garden branch of Haihe district of Bijing district of Binghua district, G layer of science and technology building, 200 meters south of east gate of Qinghua university" from the recruiter bank.

In addition to the data sources described above, text containing information on geographical location points may also be obtained from other data sources.

In 602, inputting the text into a pre-trained geographic position point spatial relationship extraction model, and acquiring information of a spatial relationship output by the geographic position point spatial relationship extraction model; the geographic position spatial relationship extraction model comprises an embedding layer, a Transformer layer and a mapping layer.

The structure of the geographic position point spatial relationship extraction model involved in the embodiment of the present application may be as shown in fig. 7, and the embedding layer may include a plurality of embedding layers.

First, for a text, which can be regarded as a sequence of at least one sentence, a delimiter [ CLS ] can be added before the text first]Adding separators [ SEP ] between sentences]Each character and separator is referred to as a Token. The input sequence X may be expressed as X ═ X₁,x₂,…,x_nN is the number of Token, x_iOne of which is denoted Token. It should be noted that, in the present application, the embedding layer uses characters as granularity as Token, which can effectively solve the problem of long-term suffix.

The first Embedding layer, denoted as Token Embedding, is used for character encoding of each Token (element) in the text, and the Token in the text may include characters in the text and separators.

The second Embedding layer, which is shown as Position Embedding, is used for Position coding each Token, and may code Position information of each Token in the text, for example, Position numbers of each Token in order, and encode each Position number.

And a third Embedding layer, denoted as sequence Embedding, for encoding the Sentence mark to which each Token belongs. For example, the sentences in the text are numbered in sequence as sentence marks, and the sentence marks to which each Token belongs are encoded.

After passing through the embedding layers, the Token, the position information and the sentence mark to which the Token belongs are converted into dense vector representation. Wherein e is_iVector representation representing the ith Token, e_xiThe vector representation representing the ith Token as a character is obtained by searching a word vector matrix and converting the character into a dense vector. e.g. of the type_qiThe vector representation representing the position of the ith Token is obtained by searching a word vector matrix and converting the position into a dense vector. e.g. of the type_siThe vector representation of the statement identifier of the ith Token is obtained by searching a word vector matrix and converting the statement representation into a dense vector.

The coding result of each embedded layer is output to a transform layer (shown as a multi-layer transform in the figure), and the transform layer performs multi-layer Attention mechanism processing and outputs an implicit vector. For example, one dense vector sequence E ═ E₁，e₂，…，e_nThe output is an implicit vector sequence h ═ phi containing context information_θ(E)＝{h₁，h₂，…，h_n}. Wherein n is the length of the input sequence, i.e. the number of Token contained.

The mapping layer may include a CRF (Conditional Random Field) for predicting information of spatial relationships contained in the text of the input model using the hidden vectors output by the transform layer.

Obtaining the sequence h of the hidden vector ═ h { [ h ]₁，h₂，…，h_nAfter, we use the CRF prediction tag to get the output Y of the model ═ Y }₁，y₂，…，y_nIn which y is_iIs a corresponding input x_iThe predictive tag of (1).

For each token x_iWe can get a probability distribution by the following formula

The number of output tags is tabulated.

Then Y ═ Y for each prediction sequence₁，y₂，…，y_nWe can get a score for this sequence:

finally, we can use the softmax (fully-connected layer) layer to obtain the probability P of each predicted sequence Y_r：

Wherein the content of the first and second substances,

refers to any of all the resulting predicted sequences.

And finally, a prediction sequence Y with the maximum probability is taken, wherein the prediction sequence comprises the prediction of the spatial relationship information of the geographic position points, including the type and value of the spatial relationship. Further, the prediction sequence also includes a prediction of a geographic location point. Finally, the method can be expressed as a quadruplet R ═ S, O, P, a >, wherein S and O are geographical location points, P is a spatial relationship type, and a is a spatial relationship value.

After the model is extracted by the spatial relationship of the geographic position points, a text is input, namely that six layers of shopping centers of five-color cities in the street in the Qing river of the Haihe district of Beijing city are fished by the seabed, the type of the spatial relationship of the geographic position points of the submarine fishing and the five-color cities is extracted from the six layers of shopping centers is ' floor ', the value is ' 6 layers ', and the model can be expressed as a four-tuple R ═ submarine fishing, five-color cities, floors and 6 layers '.

The input text "Qinghua scientific and technological park in Zhi Xinghuan Qinghua district of Beijing Qinghua park of Qinghua Bank", science and technology mansion B seat G layer, 200 m from the east of Qinghua university "extracts the spatial position relation type of the geographical position point" the Qinghua university Dongmen "and" the Qinghua university Dongmen "as" south ", the value is" 200 m ", can be expressed as the four-tuple R ═ the < the Xinghen bank, the Qinghua university Dongmen, south, 200 m >.

In the embodiment, the method and the device can extract the spatial relationship information of the geographic position points from the text containing the information of the geographic position points in the Internet.

In addition, a description system representing the spatial relationship is defined in the embodiment of the application, and is similar to the triplets < entity 1, entity 2, relationship > in the common-sense knowledge graph, and the expressions of the spatial relationship are more standard and uniform by adopting < geographic position point 1, geographic position point 2, spatial relationship types and spatial relationship values >, so that systematic calculation, reasoning and storage of spatial relationship knowledge become possible.

In the process of extracting the spatial relationship information of the geographic position points, the spatial relationship extraction model of the geographic position points is one of the key points.

The above is a detailed description of the method provided by the present application, and the following is a detailed description of the apparatus provided by the present application.

Fig. 8 is a structural diagram of a device for acquiring geographic location point information according to an embodiment of the present disclosure, where the device may be an application located at a server, or may also be a functional unit such as a Software Development Kit (SDK) or a plug-in the application located at the server, or may also be located in a computer system, which is not particularly limited in this embodiment of the present disclosure. As shown in fig. 8, the apparatus may include: the system comprises a spatial relationship acquisition unit 01, a spatial relationship concatenation unit 02, a knowledge base processing unit 03 and an information generation unit 04. The main functions of each component unit are as follows:

the spatial relationship obtaining unit 01 is configured to obtain a newly generated spatial relationship list, where the spatial relationship list includes more than one spatial relationship data, and the spatial relationship data includes spatial relationship information between two geographic location points.

The newly generated spatial relationship list is obtained by extracting spatial relationship information between adjacent geographic position points from at least one of professionally collected live-action images, crowd-sourced collected live-action images and internet texts.

And the spatial relationship concatenation unit 02 is configured to concatenate the spatial relationship data in the spatial relationship list to obtain at least one concatenation set.

When the spatial relationship data are concatenated, if two spatial relationship data contain a same geographical location point, the two spatial relationship data can be concatenated, and by analogy, a plurality of spatial relationship data can be concatenated to form a concatenated set. If one spatial relationship data and other spatial relationship data in a newly generated spatial relationship list cannot be connected in series, the spatial relationship data forms a series set by itself.

The knowledge base processing unit 03 is configured to, if at least one piece of spatial relationship data in the concatenated set exists in the existing knowledge base, write the spatial relationship data in the concatenated set into the knowledge base.

As a preferred embodiment, the knowledge base processing unit 03 may respectively execute, as the current spatial relationship data, each spatial relationship data in the concatenated set:

determining the grids to which the geographic position points contained in the current spatial relationship data belong;

inquiring current spatial relation data in the spatial relation data corresponding to the cell in the knowledge base, and if the current spatial relation data are inquired, determining that the current spatial relation data exist in the existing knowledge base; otherwise, determining that the current spatial relationship data does not exist in the existing knowledge base.

The geographical location area is divided into cells in advance, and an overlapping area exists between adjacent cells; the knowledge base processing unit 03 may correspond the spatial relationship data in the knowledge base to at least one cell in advance according to the geographic location of the included geographic location point.

As a preferred embodiment, when determining the cell to which the geographic location point included in the current spatial relationship belongs, the knowledge base processing unit 03 may determine the cell to which the geographic location point belongs according to the fuzzy coordinate information of the geographic location point included in the current spatial relationship; the known coordinate information includes precise coordinate information; wherein the accuracy of the blurred coordinate information is less than the accurate coordinate information.

Further, if all the spatial relationship data in the concatenated set does not exist in the existing knowledge base, the knowledge base processing unit 03 determines whether spatial relationship data obtained from the professionally collected live-action images exists in the concatenated set, and if so, writes the spatial relationship data in the concatenated set into the knowledge base.

Further, if there is no spatial relationship data obtained from professionally collected live-action images in the concatenated set, the knowledge base processing unit 03 may write the spatial relationship data in the concatenated set into the list to be verified. And moreover, a professional acquisition team can be further informed, and then the professional acquisition team acquires and verifies the information of each geographic position point of the corresponding area in the list to be verified.

And the information generating unit 04 is configured to analyze the geographical location points included in the spatial relationship data newly written into the knowledge base to obtain geographical location point information included in the spatial relationship data newly written into the knowledge base.

The information generating unit 04 may obtain the coordinate information of the other geographic location points in the spatial relationship data newly written in the knowledge base by using the known coordinate information of at least one geographic location point included in the spatial relationship data newly written in the knowledge base.

As a preferred embodiment, if the spatial relationship data newly written in the knowledge base includes spatial relationship data obtained from a professional captured live-action image, the information generating unit 04 calculates other geographical position points included in the spatial relationship data newly written in the knowledge base based on the spatial relationship by using coordinate information of the geographical position points carried in the professional captured live-action image, obtains coordinate information of the other geographical position points, and writes the coordinate information in the map database.

As a preferred embodiment, when the geographical position point included in the spatial relationship data newly written in the knowledge base has the accurate coordinate information in the existing map database, the information generating unit 04 calculates the other geographical position point included in the spatial relationship data newly written in the knowledge base based on the spatial relationship using the geographical position point having the accurate coordinate information, obtains the coordinate information of the other geographical position point, and writes the coordinate information in the map database.

In addition, the information generating unit 04 may determine the state information of the geographical location point included in the spatial relationship data newly written into the knowledge base by performing at least one of the following manners:

and if the two adjacent geographical position points contained in the spatial relationship data newly written into the knowledge base are not adjacent in the existing knowledge base, determining that the state of the geographical position point between the two adjacent geographical position points in the existing knowledge base is closed, and deleting the spatial relationship data containing the geographical position point in the closed state in the knowledge base.

And if the coordinate information of one geographical position point contained in the spatial relationship data newly written into the knowledge base is overlapped with the coordinate information of another geographical position point in the existing map database, determining that the state of the other geographical position point is changed, the state of one geographical position point is newly increased, and deleting the spatial relationship data containing the geographical position point with the changed state in the knowledge base.

And if the geographical position points contained in the spatial relationship data which is newly written into the knowledge base do not exist in the existing map database, determining that the state of the geographical position points is newly increased.

After the coordinate information and the state change information of the newly warehoused geographic position point are obtained through the method provided by the embodiment of the application, the method can be applied to various scenes. For example, when a location query request from a terminal device is acquired, a query may be performed based on the updated map database and corresponding location information may be returned. As another example, when a navigation request from a terminal device is acquired, a query may be made based on the updated map database and a navigation result may be returned. As another example, when a route query request from a terminal device is acquired, a query may be made based on the updated map database and route results may be returned. And so on.

According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.

Fig. 9 is a block diagram of an electronic device according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.

As shown in fig. 9, the electronic apparatus includes: one or more processors 901, memory 902, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). Fig. 9 illustrates an example of a processor 901.

Memory 902 is a non-transitory computer readable storage medium as provided herein. The memory stores instructions executable by at least one processor to cause the at least one processor to perform the method for obtaining geographical location point information provided herein. The non-transitory computer-readable storage medium of the present application stores computer instructions for causing a computer to execute the method of acquiring geographical location point information provided herein.

The memory 902, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/units corresponding to the method of acquiring geographical location point information in the embodiments of the present application. The processor 901 executes various functional applications of the server and data processing by executing non-transitory software programs, instructions, and units stored in the memory 902, that is, implements the method of acquiring geographical location point information in the above method embodiments.

The memory 902 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 902 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 902 may optionally include memory located remotely from the processor 901, which may be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device may further include: an input device 903 and an output device 904. The processor 901, the memory 902, the input device 903 and the output device 904 may be connected by a bus or other means, and fig. 9 illustrates the connection by a bus as an example.

The input device 903 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic device, such as a touch screen, keypad, mouse, track pad, touch pad, pointer, one or more mouse buttons, track ball, joystick, or other input device. The output devices 904 may include a display device, auxiliary lighting devices (e.g., LEDs), tactile feedback devices (e.g., vibrating motors), and the like. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.

Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.

The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method of obtaining geographical location point information, comprising:

2. The method of claim 1, wherein the newly generated spatial relationship list is obtained by extracting spatial relationship information between geographical location points from at least one of professionally captured live-action images, crowd-sourced captured live-action images, and internet text.

3. The method according to claim 1, wherein when it is determined that at least one spatial relationship data in the concatenated set exists in the existing knowledge base, performing, as the current spatial relationship data, each spatial relationship data in the concatenated set:

inquiring the current spatial relationship data in the spatial relationship data corresponding to the cell in the knowledge base, and if the current spatial relationship data is inquired, determining that the current spatial relationship data exists in the existing knowledge base; otherwise, determining that the current spatial relationship data does not exist in the existing knowledge base.

4. The method as claimed in claim 3, wherein the geographical location area is pre-divided into cells, there is an overlapping area between adjacent cells, and the spatial relationship data in the knowledge base is pre-mapped to at least one cell according to the geographical location of the included geographical location point.

5. The method of claim 3, wherein the determining the cell to which the geographic location point included in the current spatial relationship belongs comprises: determining the region lattice according to the fuzzy coordinate information of the geographic position points contained in the current spatial relationship;

the known coordinate information comprises precise coordinate information;

wherein the precision of the blurred coordinate information is less than the precision coordinate information.

6. The method of claim 1, further comprising:

and if all the spatial relationship data in the serial set do not exist in the existing knowledge base, determining whether the spatial relationship data obtained by the specially acquired live-action images exist in the serial set, and if so, writing the spatial relationship data in the serial set into the knowledge base.

7. The method of claim 6, further comprising:

and if the spatial relationship data obtained by the professionally collected live-action images does not exist in the serial connection set, writing the spatial relationship data in the serial connection set into a list to be verified.

8. The method according to any one of claims 1 to 7, wherein the analyzing the geographical location points included in the spatial relationship data newly written into the knowledge base to obtain the geographical location point information included in the spatial relationship data newly written into the knowledge base comprises:

if the spatial relationship data newly written into the knowledge base contains spatial relationship data obtained by a professional collected live-action image, calculating other geographical position points contained in the spatial relationship data newly written into the knowledge base based on the spatial relationship by using coordinate information of the geographical position points carried by the professional collected live-action image to obtain coordinate information of the other geographical position points and writing the coordinate information into a map database; and/or the presence of a gas in the gas,

if the geographical position points contained in the spatial relationship data newly written into the knowledge base have accurate coordinate information in the existing map database, the geographical position points with the accurate coordinate information are used for carrying out calculation based on the spatial relationship on other geographical position points contained in the spatial relationship data newly written into the knowledge base, so that the coordinate information of the other geographical position points is obtained and written into the map database.

9. The method according to any one of claims 1 to 7, wherein the analyzing the geographical location points included in the spatial relationship data newly written into the knowledge base to obtain the geographical location point information included in the spatial relationship data newly written into the knowledge base comprises:

if two adjacent geographical position points contained in the spatial relationship data newly written into the knowledge base are not adjacent in the existing knowledge base, determining that the state of the geographical position point between the two adjacent geographical position points is closed, and deleting the spatial relationship data containing the geographical position point in the knowledge base in the closed state; and/or the presence of a gas in the gas,

if the coordinate information of one geographical position point contained in the spatial relationship data newly written into the knowledge base is overlapped with the coordinate information of another geographical position point in the existing map database, determining that the state of the other geographical position point is changed, the state of the geographical position point is newly increased, and deleting the spatial relationship data containing the geographical position point with the changed state in the knowledge base; and/or the presence of a gas in the gas,

10. An apparatus for acquiring geographical location point information, comprising:

11. The apparatus of claim 10, wherein the newly generated spatial relationship list is obtained by extracting spatial relationship information between geographical location points from at least one of professionally captured live-action images, crowd-sourced captured live-action images, and internet text.

12. The apparatus according to claim 10, wherein the knowledge base processing unit is specifically configured to perform, as the current spatial relationship data, each piece of spatial relationship data in the concatenated set:

13. The apparatus of claim 12, wherein the geographic location area is pre-divided into cells with overlapping regions between adjacent cells;

the knowledge base processing unit is further configured to map the spatial relationship data in the knowledge base to at least one cell in advance according to the geographic location of the included geographic location point.

14. The apparatus according to claim 12, wherein the knowledge base processing unit, when determining the cell to which the geographic location point included in the current spatial relationship belongs, is specifically configured to: determining the region lattice according to the fuzzy coordinate information of the geographic position points contained in the current spatial relationship;

the known coordinate information comprises precise coordinate information;

15. The apparatus according to claim 10, wherein the knowledge base processing unit is further configured to determine whether spatial relationship data obtained from the professionally collected live-action image exists in the concatenated set if all spatial relationship data in the concatenated set does not exist in the existing knowledge base, and if so, write the spatial relationship data in the concatenated set into the knowledge base.

16. The apparatus of claim 15, wherein the knowledge base processing unit is further configured to write spatial relationship data in the concatenated collection into the list to be verified if spatial relationship data derived from professionally collected live-action images does not exist in the concatenated collection.

17. The apparatus according to any one of claims 10 to 16, wherein the information generating unit is specifically configured to:

18. The apparatus according to any one of claims 10 to 16, wherein the information generating unit is specifically configured to:

19. An electronic device, comprising:

at least one processor; and

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

20. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-9.