Geographic position information determination method and device, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a geographic position information determination method and device, electronic equipment, a storage medium and a program product. The method comprises the steps that an original feature data set of a target address is acquired, the original feature data set comprises attribute feature data of multiple attributes of the target address, and the attribute feature data of at least part of the attributes are first type attribute feature data; converting the first type of attribute feature data in the original feature data set into second type of attribute feature data to obtain a target feature data set of the target address; and determining geographical location information of the target address based on the target feature data set. According to the embodiment of the invention, by utilizing the technical scheme, the accuracy of positioning the target address can be improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular, to a method, device, electronic device, storage medium, and program product for determining geographic location information. Background Art

[0002] At present, in many scenarios, there is a need to determine the geographical location information corresponding to the address. Take the positioning scenario as an example. In the positioning scenario, it is necessary to determine the geographical location information corresponding to the positioning address to achieve positioning. However, in the related technology, the accuracy of positioning is low. Summary of the invention

[0003] The embodiments of the present disclosure provide a method, device, electronic device, storage medium and program product for determining geographic location information to improve positioning accuracy.

[0004] In a first aspect, an embodiment of the present disclosure provides a method for determining geographic location information, including:

[0005] Acquire an original feature data set of the target address, wherein the original feature data set includes attribute feature data of multiple attributes of the target address, and the attribute feature data of at least some attributes are first type attribute feature data;

[0006] Converting the first type of attribute feature data in the original feature data set into second type of attribute feature data to obtain a target feature data set for the target address;

[0007] The geographic location information of the target address is determined based on the target feature data set.

[0008] In a second aspect, an embodiment of the present disclosure further provides a device for determining geographic location information, including:

[0009] A data set acquisition module, configured to acquire an original feature data set of a target address, wherein the original feature data set includes attribute feature data of multiple attributes of the target address, and the attribute feature data of at least some attributes are first type attribute feature data;

[0010] A data conversion module, used for converting the first type of attribute feature data in the original feature data set into second type of attribute feature data to obtain a target feature data set of the target address;

[0011] A location determination module is used to determine the geographic location information of the target address based on the target feature data set.

[0012] In a third aspect, an embodiment of the present disclosure further provides an electronic device, including:

[0013] one or more processors;

[0014] a memory for storing one or more programs,

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining geographic location information as described in the embodiment of the present disclosure.

[0016] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for determining geographic location information as described in the embodiment of the present disclosure.

[0017] In a fifth aspect, the embodiments of the present disclosure further provide a computer program product. When the computer program product is executed by a computer, the computer implements the method for determining geographic location information as described in the embodiments of the present disclosure.

[0018] The method, device, electronic device, storage medium and program product for determining geographic location information provided by the embodiments of the present disclosure convert different types of attribute feature data of the target address into attribute feature data of the same type, and determine the geographic location information of the target address based on the converted attribute feature data, thereby improving the accuracy of locating the target address. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0020] Figure 1 A flowchart of a method for determining geographic location information provided by an embodiment of the present disclosure;

[0021] Figure 2 A flowchart of another method for determining geographic location information provided by an embodiment of the present disclosure;

[0022] Figure 3 A schematic diagram of a prediction process of geographic location information provided by an embodiment of the present disclosure;

[0023] Figure 4 A structural block diagram of a device for determining geographic location information provided by an embodiment of the present disclosure;

[0024] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0026] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0027] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0028] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0029] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0030] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0031] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0032] Figure 1 The present invention provides a flowchart of a method for determining geographic location information provided by an embodiment of the present invention. The method can be executed by a device for determining geographic location information, wherein the device can be implemented by software and / or hardware and can be configured in an electronic device, typically a computer, a mobile phone or a tablet computer. The method for determining geographic location information provided by an embodiment of the present invention is applicable to a scenario of determining geographic location information corresponding to a positioning address. Figure 1As shown, the method for determining geographic location information provided in this embodiment may include:

[0033] S101. Acquire an original feature data set of a target address, wherein the original feature data set includes attribute feature data of multiple attributes of the target address, and the attribute feature data of at least some attributes are first type attribute feature data.

[0034] The target address can be understood as the address whose geographic location information is to be determined, which can be input by the user or a pre-stored address. For example, in some scenarios, the current user can input the address whose location information is to be determined as the target address; in other scenarios, the current user can obtain a pre-stored address as the target address, such as in the positioning scenario, the address of the current user to be positioned can be obtained as the target address, and so on. The positioning scenario is used as an example for explanation below.

[0035] The original feature data set can be understood as the feature data set of the target address that is originally obtained. The original feature data set contains attribute feature data of multiple attributes of the target address. These multiple attributes can be flexibly set as needed. Taking the positioning scene as an example, for example, these multiple attributes can include one or more of the following: driving track attributes, historical positioning point attributes, target positioning point attributes, non-target positioning point distribution attributes, commonly used positioning location attributes, geographical location range attributes, regional feature attributes, positive geographical location attributes, etc. Among them, the driving track attribute can be used to describe the attributes of the driving track near the target address (such as within a preset distance range from the target address), such as the distribution of the driving track near the target address. The historical positioning point attribute can be used to describe the attributes of the historical positioning points associated with the target address, such as the geographical location information of the historical positioning points. The positioning points corresponding to the target positioning point attributes and the positioning point distribution attributes can be positioning points in the preset positioning point set corresponding to the target address. The positioning points in the preset positioning point set can be pre-set positioning points, which can include a preset target positioning point corresponding to the target address and a preset non-target positioning point other than the preset target positioning point. This preset target positioning point can be a pre-set preferred positioning point corresponding to the target address. The target location point attribute can be used to describe the attributes of the preset target location point of the target address, such as the geographic location information of the preset target location point. The location point distribution attribute can be used to describe the distribution of each preset non-target location point in the preset location point set corresponding to the target address. The commonly used location location attribute can be used to describe the attributes of the commonly used location locations corresponding to the target address, such as the geographic location information of the commonly used location locations. The acquisition and processing of the above-mentioned related data must comply with the provisions of laws and regulations and obtain full authorization from the relevant parties. The geographic location range attribute can be used to describe the geographic location range of the geographic location corresponding to the target address, such as the range of selectable values ​​corresponding to the geographic location coordinates corresponding to the target address. The regional feature attribute can be used to describe the regional characteristics of the target area where the target address is located, such as the regional distribution characteristics of the target area where the target address is located. The positive geographic location attribute can be used to describe the attributes of the positive geographic location corresponding to the target address, such as the geographic location information of the positive geographic location corresponding to the target address. The positive geographic location can be understood as the geographic location obtained by converting the address text of the target address based on the forward geocoding method.

[0036] The data type of the attribute feature data contained in the original feature data set is not limited. For example, some or all of the attribute feature data in the original feature data set may be first type attribute feature data. In some examples, some of the attribute feature data in the original feature data set may be first type attribute feature data, and at least some of the attribute feature data other than the first type attribute feature data may be second type attribute feature data. The first type attribute feature data and the second type attribute feature data may have different data types. Optionally, the first type attribute feature data is character type attribute feature data, and the second type attribute feature data is picture type attribute feature data. For example, the data type of the attribute feature data of some attributes of the target address may be character type; and the data type of the attribute feature data of another part of the attributes may be picture type.

[0037] In some examples, the second type of attribute feature data in the original feature data set may include attribute feature data of the driving trajectory attribute of the target address, such as the driving trajectory attribute of the target address corresponds to the driving trajectory map near the target address, and the driving trajectory near the target address is presented in the form of a picture, rather than converting each driving trajectory near the target address into a large number of trajectory points for presentation, which can reduce the volume of the original feature data set, thereby reducing the resources occupied by obtaining the original feature data set. This driving trajectory map can be used to present the driving trajectory near the target address. Optionally, the original feature data set also includes the second type of attribute feature data, and the second type of attribute feature data includes a driving trajectory map corresponding to the driving trajectory attribute of the target address, and the driving trajectory map is used to present the driving trajectory within a preset distance range from the target address. The preset distance range can be set as needed. For example, the preset distance range can be a square area centered on the initial positioning point corresponding to the target address, and the side length of the square area can be preset, so that the side length of the square area can be set to 400m or 800m, etc.; the side of the square area can be along the east-west direction or the north-south direction, etc. The initial positioning point corresponding to the target address may be a positioning point preliminarily determined based on the target address, and the determination method is not limited. For example, the initial positioning point may be a positioning point corresponding to the positioning address of the target address at a preset administrative level, the positive geographical location of the target address, the center of a commonly used positioning location corresponding to the target address (such as the center of a commonly used positioning location corresponding to the target address), the center of each historical positioning point corresponding to the target address, etc. The preset administrative level may be set as required. For example, the preset administrative level may be an administrative level that supports input by selection.

[0038] Specifically, the original feature data set of the target address may be obtained. Taking the positioning scenario as an example, illustratively, when a positioning request for a certain positioning address (such as the target address) is received, the original feature data set of the positioning address may be obtained.

[0039] S102: Convert the first type attribute feature data in the original feature data set into second type attribute feature data to obtain a target feature data set for the target address.

[0040] In this embodiment, after the original feature data set of the target address is obtained, the attribute features other than the second type attribute features in the original feature data set can be converted into the second type attribute feature data. For example, when the first type attribute feature data is character type attribute feature data and the second type attribute feature data is picture type attribute feature data, a picture for presenting the data features of the second type data feature data can be generated as the converted second type attribute feature data, thereby obtaining the target feature data set of the target address. The target feature data set can be a feature data set obtained by converting the first type attribute feature data in the original feature data set into the second type data feature data, and the attribute feature data of each attribute contained in the target feature data set can all be second type attribute feature data.

[0041] S103: Determine the geographic location information of the target address based on the target feature data set.

[0042] The geographical location information of the target address can be understood as the information of the geographical location corresponding to the target address, such as the geographical coordinates of the geographical location corresponding to the target address. The geographical coordinates can be understood as the coordinates in the geographical coordinate system, such as longitude and latitude.

[0043] Specifically, after obtaining the target feature data set of the target geographic location, the geographic location information of the target address may be determined based on the target feature data set.

[0044] For example, a geographic location determination model can be pre-trained, and this geographic location determination model can be used to locate the input feature data set, so that after obtaining the target feature data set of the target geographic location, this target feature data set can be input into this geographic location determination model, and the target geographic location corresponding to the target address can be determined by this geographic location determination model. Thus, the location information of this target geographic location in the geographic coordinate system can be obtained as the geographic location information of the target address, for example, the location information of the target geographic location in the geographic coordinate system can be directly obtained as the geographic location information of the target address; or, the confidence of the target geographic location is calculated, and when the confidence of the target address position is greater than or equal to a preset confidence threshold, the location information of the target geographic location in the geographic coordinate system can be obtained as the geographic location information of the target address.

[0045] Taking the feature data of the second type of feature data as picture type as an example, illustratively, the geographic location model can output a picture containing the predicted geographic location corresponding to the target address. For example, in some examples, this picture may only present one predicted point. In this case, based on the position information of this point in this picture, that is, based on the position information of this point in the picture coordinate system, its position information in the geographic coordinate system can be determined as the geographic location information of the target address; in other examples, this picture may present multiple predicted candidate points and the probability of each candidate point being the real point corresponding to the target address. In this case, according to the probability of each candidate point being the real point corresponding to the target address, the candidate point with the highest probability can be selected, and based on the position information of this point in this picture, that is, based on the position information of this point in the picture coordinate system, its position information in the geographic coordinate system can be determined as the geographic location information of the target address.

[0046] The method for determining geographic location information provided in this embodiment obtains an original feature data set of a target address, wherein the original feature data set contains attribute feature data of multiple attributes of the target address, and at least the attribute feature data of some attributes are first-type attribute feature data; the first-type data feature data in the original feature data set is converted into second-type attribute feature data to obtain a target feature data set of the target address; and the geographic location information of the target address is determined based on the target feature data set of the target address. This embodiment utilizes the above technical solution to uniformly convert different types of attribute feature data of the target address into the same type of attribute feature data, and determines the geographic location information of the target address based on the converted attribute feature data, which can improve the accuracy of locating the target address.

[0047] In some embodiments, taking the first type of attribute feature data as character type attribute feature data and the second type of data feature data as picture type attribute feature data as an example, for the attribute with the first type of attribute feature data, the image processing method corresponding to this attribute can be used to perform image processing on the first type of attribute feature of this attribute to improve the accuracy of type conversion; and the image obtained by the image processing is used as the second type of attribute feature data of this attribute. At this time, optionally, the conversion of the first type of attribute feature data in the original feature data set into the second type of attribute feature data includes: for the target attribute in the at least part of the attributes, the image processing method corresponding to the target attribute is used to perform image processing on the first type of attribute feature data of the target attribute to obtain the second type of attribute feature data of the target attribute. Among them, the target attribute can be understood as an attribute whose first type of attribute feature data needs to be image processed. The image processing methods corresponding to different attributes can be the same or different, and the image processing methods corresponding to each attribute are not limited.

[0048] In some embodiments, the first type of attribute characteristic data of the target attribute is processed in a graphical manner corresponding to the target attribute to obtain the second type of attribute characteristic data of the target attribute, including at least one of the following: when the target attribute is an associated point attribute, a heat map of associated points of the target address is generated based on the first type of attribute characteristic data of the target attribute as the second type of characteristic data of the target attribute; when the target attribute is a geographic location range attribute, a geographic location range map of the target address is generated based on the first type of attribute characteristic data of the target attribute as the second type of characteristic data of the target attribute; when the target attribute is an area characteristic attribute, an area characteristic map of the target area where the target address is located is generated based on the first type of attribute characteristic data of the target attribute as the second type of characteristic data of the target attribute.

[0049] Among them, the associated point attributes can be understood as attributes associated with the associated points of the target address. The first type of attribute feature data of the associated point attributes can be point data. The associated points of the target address can be understood as points associated with the target address, such as the historical positioning points of the target address, preset target positioning points, preset non-target positioning points, commonly used positioning locations and / or positive geographical locations, etc. Exemplarily, the associated point attributes of the target address may include historical positioning point attributes, target positioning point attributes, positioning point distribution attributes, commonly used positioning location attributes and / or positive geographical location attributes, etc. A heat map is a type of chart that visualizes data, which uses color coding to display the density and distribution of points. The target area can be understood as the area where the target address is located, which can be an area of ​​interest (AOI) or a geographic space (Block) area corresponding to the target address.

[0050] Exemplarily, when the target attribute is an associated point attribute, an associated point heat map corresponding to the target attribute can be generated based on the first type of attribute feature data of the target attribute, such as the associated point data corresponding to the target attribute, as the second type of attribute feature data of the target attribute.

[0051] In the case where the target attribute is a geographic location range attribute, a geographic range map of the target address can be generated based on the first type of attribute feature data of the target attribute. For example, the area radius of the area of ​​interest corresponding to each address category can be counted in advance based on the AOI data corresponding to each address category. Thus, for the target address, the area radius corresponding to this address category can be obtained based on the address category of the target address, and the area radius combined with Gaussian blur forms a Gaussian blur circle range, and a picture for presenting this range is generated as the second type of attribute feature data of the target attribute.

[0052] In the case where the target attribute is a regional characteristic attribute, a regional characteristic map of the target area where the target address is located can be generated based on the first type of attribute characteristic data of the target attribute. For example, based on the AOI data corresponding to the target attribute, the AOI area or Block area corresponding to the target address can be determined, and a regional characteristic map for presenting this area can be generated as the second type of attribute characteristic data of the target attribute.

[0053] In the above implementation, different pictorial methods may be used to pictorially process the first type attribute feature data of different types of attributes, which can further improve the accuracy of the second type attribute feature data obtained by pictorial processing and improve the accuracy of the determined geographic location information.

[0054] In some embodiments, the target address is the location address of a target location event, the associated point attributes include historical location point attributes, and the generating of the associated point heat map of the target address based on the first type of attribute feature data of the target attributes includes: grading the target address according to administrative levels to obtain a multi-level location address of the target address at different administrative levels; for the location address of the target level in the multi-level location address, based on the historical location point data matching the location address of the target level, generating a historical location point heat map corresponding to the location address of the target level.

[0055] Exemplarily, for a target address of a text type, the administrative level information of the target address can be obtained by word segmentation, and the administrative level information can be combined to obtain the location address of the target address at different administrative levels. For example, the location address information of each administrative level can be combined in the form of province + city + district + street + road + point of interest (POI), such as the location address of the district, the location address of the road, etc.; for each location address obtained by the combination, the historical location point data matching the location address is obtained, such as the historical location point data corresponding to the corresponding historical location point within the range of the location address is obtained, and the historical location point heat map corresponding to the location address is generated based on the obtained historical location point data. Among them, the historical location point heat map can be understood as a heat map of the historical location point.

[0056] In the above implementation, the target address can be classified according to the administrative level, and based on the historical positioning point data at different administrative levels, a heat map of the historical positioning points of the target address at each administrative level is generated. Compared with the technical solution of obtaining the historical positioning point data based only on the target address, which is the positioning address at the minimum level, the number of historical positioning points can be further increased, and the accuracy of the determined geographic location information can be improved.

[0057] Figure 2A flow chart of another method for determining geographic location information provided for an embodiment of the present disclosure. The scheme in this embodiment may be combined with one or more optional schemes in the above-mentioned embodiments. Optionally, the method for determining the geographic location information of the target address based on the target feature data set includes inputting the target feature data set into a pre-trained geographic location determination model, and obtaining a geographic location distribution probability map output by the geographic location determination model, wherein the geographic location distribution probability map indicates the distribution probability of the target address at different candidate geographic locations; inputting the target feature data set and the geographic location distribution probability map into a pre-trained geographic location evaluation model, and determining the confidence of the geographic location distribution probability map through the geographic location evaluation model; if the confidence is greater than or equal to a preset confidence threshold, obtaining the geographic coordinates of the target geographic location as the geographic location information of the target address, wherein the target geographic location is the candidate geographic location with the highest distribution probability corresponding to the target address in the geographic location distribution probability map.

[0058] Correspondingly, such as Figure 2 As shown, the method for determining geographic location information provided in this embodiment may include:

[0059] S201. Acquire an original feature data set of a target address, wherein the original feature data set includes attribute feature data of multiple attributes of the target address, and the attribute feature data of at least some attributes are first type attribute feature data.

[0060] In some examples, taking the positioning scenario as an example, the original feature data set of the target address may include the first feature data of the target address, and may further include the second feature data of the target address. The positioning range when the candidate geographical location is initially determined based on the first feature data is narrowed by the geographical location range corresponding to the second feature data, so as to further improve the accuracy of the determined geographical location information. The first feature data may be labeled data associated with the target address, which can be used to determine the geographical location information of the target address, so that the first feature data may be the core data for determining the geographical location information of the target address; the second feature data may be unlabeled data associated with the target address, which can be used to describe the background information characteristics of the target address, such as providing some candidate point information in the process of determining the geographical location information of the target address. Thus, the target address can be located based on the geographical location range corresponding to the first feature data and the candidate point information. Optionally, the target address is the location address of the target location event, and the attribute feature data includes first feature data and second feature data, wherein the first feature data is labeled data corresponding to the target address; the second feature data is unlabeled data corresponding to the target address, and the second feature data includes a driving trajectory map and / or historical location point information; the geographic location determination model determines the candidate geographic location corresponding to the target address based on the first feature data and the geographic location range corresponding to the second feature data. For example, the first feature data may include feature data of a preset target location point of the target address, distribution feature data of preset non-target location points, feature data of commonly used location locations, feature data of a geographic location range, regional feature data of a target area, and / or feature data of a positive geographic location, etc.; the second feature data may include feature data of the driving trajectory of the target address (such as a driving trajectory map) and / or feature data of a historical location point (such as historical location point data), etc.

[0061] S202: Convert the first type attribute feature data in the original feature data set into second type attribute feature data to obtain a target feature data set for the target address.

[0062] S203: Input the target feature data set into a pre-trained geographic location determination model, and obtain a geographic location distribution probability map output by the geographic location determination model, wherein the geographic location distribution probability map indicates the distribution probability of the target address at different candidate geographic locations.

[0063] The geographic location determination model may be a model for determining the geographic location corresponding to an address, and its input may be a target feature data set of a target address, and its output may be a geographic location distribution probability map of the target address. The model structure of the geographic location determination model is not limited. For example, the geographic location determination model may be a deep learning model for image segmentation, such as a UNet (U-shaped Network) model, or a D-LinkNet (Densely Connected Link Network) model, etc.

[0064] The geographic location distribution probability map can be understood as a probability map of each candidate geographic location of the target address being the real geographic location corresponding to the target address. The geographic location distribution probability map can present the points corresponding to each candidate geographic location of the target address in the image coordinate system. The points corresponding to candidate geographic locations with different distribution probabilities can have different display styles in the geographic location distribution probability map. For example, the points corresponding to candidate geographic locations with different distribution probabilities can be presented in different colors in the geographic location distribution probability map, or the brightness of the points corresponding to each candidate geographic location in the geographic location distribution probability map can be positively correlated with its distribution probability, and so on. Among them, the candidate geographic location can be understood as the geographic location that the target address may correspond to, and the distribution probability of the target address at a candidate geographic location can be understood as the probability that this candidate geographic location is the real geographic location corresponding to the target address. Each candidate geographic location of the target address and the distribution probability of the target address at each candidate geographic location can be determined by the geographic location determination model based on the target feature data set of the target address.

[0065] Specifically, the target feature data set of the target address may be input into a pre-trained geographic location determination model, and a geographic location distribution probability map of the target address generated by the geographic location determination model based on the target feature data set may be obtained.

[0066] S204: Input the target feature data set and the geographic location distribution probability map into a pre-trained geographic location evaluation model, and determine the confidence of the geographic location distribution probability map through the geographic location evaluation model.

[0067] The geographic location evaluation model can be used to evaluate the target geographic location determined by the geographic location determination model. For example, the geographic location evaluation model can be used to determine the confidence level of the target geographic location. The model structure of the geographic location evaluation model is not limited.

[0068] Specifically, after obtaining the geographic location distribution probability map of the target address output by the geographic location determination model, the target feature data set of the target address and the geographic location distribution probability map of the target address can be input into a pre-trained geographic location evaluation model. The geographic location evaluation model can evaluate the geographic location distribution probability map output by the geographic location determination model based on the target feature data of the target address to obtain the confidence level of the geographic location distribution probability map.

[0069] S205. If the confidence is greater than or equal to a preset confidence threshold, the geographic coordinates of the target geographic location are obtained as the geographic location information of the target address, and the target geographic location is the candidate geographic location with the highest distribution probability corresponding to the target address in the geographic location distribution probability map.

[0070] The target geographic location can be understood as the candidate geographic location with the highest distribution probability of the target address in the distribution probability map, such as the geographic location corresponding to the point with the highest distribution probability in the distribution probability map. This confidence can be understood as reliability or confidence level.

[0071] Exemplarily, if the confidence of the geographic location distribution probability map output by the geographic location determination model is greater than or equal to the preset confidence threshold, it can be said that the reliability of the geographic location distribution probability map is high. In this case, the geographic location information of the target address can be determined based on the target geographic location determined by the geographic location determination model. For example, based on the position information of the point with the highest distribution probability in the geographic location distribution probability map, the coordinate system conversion can be performed on this point to obtain the geographic coordinates of the target geographic location in the geographic coordinate system, such as obtaining the longitude and latitude of the target geographic location in the geographic coordinate system as the geographic location information of the target address. The specific value of the preset confidence threshold is not limited. For example, the preset confidence can be set to a value such as 0.9 or 0.95.

[0072] In addition, if the confidence of the target geographic location is less than a preset confidence threshold, it can be said that the reliability of the geographic location distribution probability map output by the geographic location determination model is low. In this case, the geographic location information of the target address may not be determined based on the geographic location distribution probability map output by the geographic location determination model. For example, the geographic location information of the target address may be determined based on other determination methods. This other determination method may be flexibly set as needed, and this embodiment does not limit this. Exemplarily, the geographic location information of the target address may be determined based on the positive initial positioning point of the target address, etc.

[0073] The method for determining geographic location information provided in this embodiment evaluates the geographic location determination result of the geographic location determination model through a geographic location evaluation model, and determines the geographic location information of the target address based on the geographic location determination result of the geographic location determination model only when its evaluation result meets the requirements, which can further improve the accuracy of the determined geographic location information.

[0074] In the related art, the longitude and latitude corresponding to the location address can be obtained by clustering the historical location point data. However, this method requires more data for clustering, and because only a single feature is calculated, the accuracy of the determined longitude and latitude is poor. In addition, due to the variety of location address writing methods, sometimes there are few or even no historical location points found. At this time, the longitude and latitude determined by clustering the historical location point data is particularly inaccurate.

[0075] In view of this, the embodiments of the present disclosure provide a method for determining geographic location information, which fully considers the prior information of the positioning address (such as historical positioning point attribute information, target positioning point attribute information and positioning point distribution attribute information, etc.) and neighborhood information (such as geographic location range attribute information and regional feature attribute information, etc.), adopts the conversion between different modal dimension features for the positioning address information, obtains the historical positioning point information of different positioning events within the address range of different administrative levels through the text features of the positioning address, associates the different positioning events, and uses the second feature data to expand the feature data and improve the positioning effect. By setting the geographic location evaluation model, the accuracy of the positioning result can be predicted.

[0076] Figure 3 A schematic diagram of a prediction process of geographic location information provided by an embodiment of the present disclosure, such as Figure 3 As shown, the method for determining the geographical location information provided in this embodiment can be described as follows:

[0077] A1. Obtain the original feature data set of the positioning address (i.e., the target address).

[0078] A2. Perform feature conversion on the first type of attribute features in the original feature data set to obtain a target feature data set for the location address.

[0079] For example, multiple features can be integrated, and point, line, surface and text features can be converted into image modalities in a corresponding manner for modeling to achieve feature unification. The specific description is as follows:

[0080] Graphicalization of point data: The relevant point data of the location address, such as historical location points and other information, is statistically analyzed by layer to form image features (i.e., a heat map).

[0081] Graphicalization of text features: The area radius of the area of ​​interest corresponding to each address category can be counted in advance based on the AOI data corresponding to each address category. Therefore, for the current location address, the area radius corresponding to this address category can be obtained according to the address category of the location address, and then the area radius is combined with Gaussian blur to form a Gaussian blur circle range, and this range is presented through a picture to provide optional range information to the model.

[0082] Pictorialization of AOI data: Since AOI data has multiple surfaces, taking into account the characteristics of the positioning scenario, this embodiment can obtain the AOI of the center through the existing longitude and latitude, and use the geographic location determination model to narrow the prediction range. Therefore, the AOI at the location of the initial point (i.e., the initial positioning point) can be converted into a binary image using a binary method to form the spatial characteristics of the place (i.e., regional characteristics).

[0083] Among them, when the text features are visualized, a mapping method from text features to spatial features can be established based on the way of hierarchical association of text with spatial features. For example, statistics of different positioning events can be performed based on text. The specific process can be to obtain addresses of different levels by word segmentation for the text strings corresponding to the historical positioning points in the existing database (i.e., the positioning addresses of the text type), and to count the related historical positioning points based on the addresses of different levels, thereby forming a multi-level feature of the positioning address. From the feature point of view, the positioning address information of each administrative level can be obtained by combining the province + city + district + street + road + point of interest (POI), such as the positioning address of the district, the positioning address of the road, etc.

[0084] In addition, in the positioning task, there are often a lot of unlabeled longitude and latitude data (i.e., the second feature data). This embodiment can also use unlabeled data to determine the optional geographical location range of the positioning address. For example, the unlabeled data is classified and layered and converted into an array to be introduced into the geographical location determination model to provide some candidate information for the geographical location determination model. Taking the unlabeled data including driving trajectory data and historical positioning point data near the positioning address as an example, the geographical location determination model can use the driving trajectory and / or historical positioning points near the positioning address as the optional geographical location range to locate the positioning address. Exemplarily, for the driving trajectory data near the positioning address, it can be visualized in a grid-based statistical manner, and the form of the road network is introduced into the geographical location determination model, thereby inputting spatial division information into the geographical location determination model; for the historical positioning point data, the historical positioning point data can be visualized by statistically forming a heat map, thereby introducing thermal information of the historical positioning points.

[0085] A3. The attribute feature data in the target feature data set of the positioning address are spliced ​​and input into the geographic location determination model, and the probability map output by the geographic location determination model (ie, the geographic location distribution probability map) is obtained.

[0086] A4. Perform coordinate system conversion on the point with the highest distribution probability in the probability map to obtain the longitude and latitude corresponding to this point (i.e., geographic location information); and input the target feature data set of the positioning address and this probability map into the geographic location assessment model (i.e., geographic location assessment model), and obtain the confidence of this probability map output by the geographic location assessment model.

[0087] In this embodiment, the probability map output by the geographic location determination model and the original features (i.e., the target feature data set of the target address) can be input into the geographic location assessment model to obtain the confidence of the probability map. The probability map output by the geographic location determination model is used as the input of the geographic location assessment model, so that the geographic location assessment model and the geographic location determination model can share the target feature data set after type conversion, thereby reducing the amount of calculation.

[0088] In this embodiment, the prediction results of the geographic location determination model are scored and evaluated. If the prediction result of the geographic location determination model is a high-confidence result, the prediction result of the geographic location determination model is used to determine the longitude and latitude of the positioning address; if the prediction result of the geographic location determination model is a low-confidence result, a pre-set determination method other than the geographic location determination model is used to determine the longitude and latitude of the positioning address, thereby further improving the accuracy of the determined longitude and latitude and improving positioning efficiency.

[0089] Figure 4 This is a structural block diagram of a device for determining geographic location information provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware, and can be configured in an electronic device, typically a computer, a mobile phone, or a tablet computer, and can determine the geographic location information corresponding to the positioning address by executing the method for determining geographic location information. Figure 1 As shown, the apparatus for determining geographic location information provided in this embodiment may include: a data set acquisition module 401, a data conversion module 402 and a location determination module 403, wherein:

[0090] The data set acquisition module 401 is used to acquire an original feature data set of a target address, wherein the original feature data set includes attribute feature data of multiple attributes of the target address, and the attribute feature data of at least some attributes are first type attribute feature data;

[0091] A data conversion module 402 is used to convert the first type of attribute feature data in the original feature data set into second type of attribute feature data to obtain a target feature data set of the target address;

[0092] The location determination module 403 is used to determine the geographical location information of the target address based on the target feature data set.

[0093] The device for determining geographic location information provided in this embodiment obtains the original feature data set of the target address through the data set acquisition module, and the original feature data set contains attribute feature data of multiple attributes of the target address, and at least the attribute feature data of some attributes are first-type attribute feature data; the first-type data feature data in the original feature data set is converted into second-type attribute feature data through the data conversion module to obtain the target feature data set of the target address; and the geographic location information of the target address is determined based on the target feature data set of the target address through the location determination module. This embodiment uses the above technical solution to uniformly convert different types of attribute feature data of the target address into the same type of attribute feature data, and determines the geographic location information of the target address based on the converted attribute feature data, which can improve the accuracy of locating the target address.

[0094] Optionally, the first type of attribute feature data is character type attribute feature data, and the second type of attribute feature data is picture type attribute feature data.

[0095] Optionally, the data conversion module 402 can be specifically used to: for the target attribute among the at least part of the attributes, use a graphics processing method corresponding to the target attribute to perform graphics processing on the first type attribute feature data of the target attribute to obtain the second type attribute feature data of the target attribute.

[0096] Optionally, the data conversion module 402 may include at least one of the following: a first conversion unit, used to generate an associated point heat map of the target address based on the first type of attribute characteristic data of the target attribute, as the second type of characteristic data of the target attribute, when the target attribute is an associated point attribute; a second conversion unit, used to generate a geographical location range map of the target address based on the first type of attribute characteristic data of the target attribute, as the second type of characteristic data of the target attribute, when the target attribute is a geographical location range attribute; a third conversion unit, used to generate an regional characteristic map of the target area where the target address is located, based on the first type of attribute characteristic data of the target attribute, as the second type of characteristic data of the target attribute, when the target attribute is an regional characteristic attribute.

[0097] Optionally, the target address is the location address of a target location event, the associated point attributes include historical location point attributes, and the first conversion unit can be specifically used to: classify the target address according to administrative levels to obtain a multi-level location address of the target address at different administrative levels; for the location address of the target level in the multi-level location address, based on the historical location point data matching the location address of the target level, generate a historical location point heat map corresponding to the location address of the target level.

[0098] Optionally, the original feature data set also includes second type attribute feature data, and the second type attribute feature data includes a driving trajectory map corresponding to the driving trajectory attributes of the target address, and the driving trajectory map is used to present the driving trajectory within a preset distance range from the target address.

[0099] Optionally, the location determination module 403 can be specifically used to: input the target feature data set into a pre-trained geographic location determination model, and obtain a geographic location distribution probability map output by the geographic location determination model, wherein the geographic location distribution probability map indicates the distribution probability of the target address at different candidate geographic locations; input the target feature data set and the geographic location distribution probability map into a pre-trained geographic location evaluation model, and determine the confidence of the geographic location distribution probability map through the geographic location evaluation model; if the confidence is greater than or equal to a preset confidence threshold, obtain the geographic coordinates of the target geographic location as the geographic location information of the target address, and the target geographic location is the candidate geographic location with the highest distribution probability corresponding to the target address in the geographic location distribution probability map.

[0100] Optionally, the target address is the location address of the target positioning event, and the attribute feature data includes first feature data and second feature data, wherein the first feature data is labeled data corresponding to the target address; the second feature data is unlabeled data corresponding to the target address, and the second feature data includes a driving trajectory map and / or historical positioning point information; the geographic location determination model determines the candidate geographic location corresponding to the target address based on the geographic location range corresponding to the first feature data and the second feature data.

[0101] The device for determining geographic location information provided in the embodiments of the present disclosure can execute the method for determining geographic location information provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of executing the method for determining geographic location information. For technical details not fully described in this embodiment, please refer to the method for determining geographic location information provided in any embodiment of the present disclosure.

[0102] Reference below Figure 5, which shows a schematic diagram of the structure of an electronic device (such as a terminal device or a server) 500 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0103] like Figure 5 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0104] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0105] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0106] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0107] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0108] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0109] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains an original feature data set of a target address, wherein the original feature data set contains attribute feature data of multiple attributes of the target address, and at least the attribute feature data of some attributes are first type attribute feature data; converts the first type attribute feature data in the original feature data set into second type attribute feature data to obtain a target feature data set of the target address; and determines the geographic location information of the target address based on the target feature data set.

[0110] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0111] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0112] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a module does not, in some cases, constitute a limitation on the unit itself.

[0113] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0114] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0115] According to one or more embodiments of the present disclosure, Example 1 provides a method for determining geographic location information, including:

[0116] Acquire an original feature data set of the target address, wherein the original feature data set includes attribute feature data of multiple attributes of the target address, and the attribute feature data of at least some attributes are first type attribute feature data;

[0117] Converting the first type of attribute feature data in the original feature data set into second type of attribute feature data to obtain a target feature data set for the target address;

[0118] The geographic location information of the target address is determined based on the target feature data set.

[0119] According to one or more embodiments of the present disclosure, Example 2 is the method according to Example 1, wherein the first type of attribute feature data is character type attribute feature data, and the second type of attribute feature data is picture type attribute feature data.

[0120] According to one or more embodiments of the present disclosure, Example 3 is the method according to Example 2, wherein converting the first type of attribute feature data in the original feature data set into second type of attribute feature data comprises:

[0121] For a target attribute among the at least some attributes, a graphic processing method corresponding to the target attribute is used to perform graphic processing on the first type attribute feature data of the target attribute to obtain the second type attribute feature data of the target attribute.

[0122] According to one or more embodiments of the present disclosure, Example 4 is a method according to Example 3, wherein the image processing method corresponding to the target attribute is used to image the first type of attribute feature data of the target attribute to obtain the second type of attribute feature data of the target attribute, including at least one of the following:

[0123] In the case where the target attribute is an associated point attribute, generating an associated point heat map of the target address based on the first type attribute feature data of the target attribute as the second type feature data of the target attribute;

[0124] In the case where the target attribute is a geographical location range attribute, generating a geographical location range map of the target address based on the first type attribute feature data of the target attribute as the second type feature data of the target attribute;

[0125] In the case where the target attribute is a regional characteristic attribute, a regional characteristic map of the target area where the target address is located is generated based on the first type attribute characteristic data of the target attribute as the second type characteristic data of the target attribute.

[0126] According to one or more embodiments of the present disclosure, Example 5 is the method according to Example 4, wherein the target address is the location address of the target location event, the associated point attributes include historical location point attributes, and the generating of the associated point heat map of the target address based on the first type attribute feature data of the target attributes includes:

[0127] Classifying the target address according to the administrative level to obtain a multi-level positioning address of the target address at different administrative levels;

[0128] For the location address of the target level in the multi-level location addresses, based on the historical location point data matching the location address of the target level, a historical location point heat map corresponding to the location address of the target level is generated.

[0129] According to one or more embodiments of the present disclosure, Example 6 is based on the method described in Example 2, wherein the original feature data set also includes second type attribute feature data, and the second type attribute feature data includes a driving trajectory map corresponding to the driving trajectory attributes of the target address, and the driving trajectory map is used to present the driving trajectory within a preset distance range from the target address.

[0130] According to one or more embodiments of the present disclosure, Example 7 is a method according to any one of Examples 1-6, wherein determining the geographic location information of the target address based on the target feature data set includes:

[0131] Inputting the target feature data set into a pre-trained geographic location determination model, and obtaining a geographic location distribution probability map output by the geographic location determination model, wherein the geographic location distribution probability map indicates the distribution probability of the target address at different candidate geographic locations;

[0132] Inputting the target feature data set and the geographic location distribution probability map into a pre-trained geographic location evaluation model, and determining the confidence of the geographic location distribution probability map through the geographic location evaluation model;

[0133] If the confidence is greater than or equal to a preset confidence threshold, the geographic coordinates of the target geographic location are obtained as the geographic location information of the target address, and the target geographic location is the candidate geographic location with the highest distribution probability corresponding to the target address in the geographic location distribution probability map.

[0134] According to one or more embodiments of the present disclosure, Example 8 is the method according to Example 7, wherein the target address is a location address of a target location event, and the attribute feature data includes first feature data and second feature data, wherein:

[0135] The first characteristic data is labeled data corresponding to the target address;

[0136] The second feature data is unlabeled data corresponding to the target address, and the second feature data includes a driving trajectory map and / or historical positioning point information;

[0137] The geographic location determination model determines the candidate geographic location corresponding to the target address based on the first feature data and the geographic location range corresponding to the second feature data.

[0138] According to one or more embodiments of the present disclosure, Example 9 provides a device for determining geographic location information, including:

[0139] A data set acquisition module, configured to acquire an original feature data set of a target address, wherein the original feature data set includes attribute feature data of multiple attributes of the target address, and the attribute feature data of at least some attributes are first type attribute feature data;

[0140] A data conversion module, used for converting the first type of attribute feature data in the original feature data set into second type of attribute feature data to obtain a target feature data set of the target address;

[0141] A location determination module is used to determine the geographic location information of the target address based on the target feature data set.

[0142] According to one or more embodiments of the present disclosure, Example 10 provides an electronic device, including:

[0143] one or more processors;

[0144] a memory for storing one or more programs,

[0145] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining geographic location information as described in any one of Examples 1-8.

[0146] According to one or more embodiments of the present disclosure, Example 11 provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for determining geographic location information as described in any one of Examples 1-8.

[0147] According to one or more embodiments of the present disclosure, Example 12 provides a computer program product, and when the computer program product is executed by a computer, the computer implements the method for determining geographic location information as described in any one of Examples 1-8.

[0148] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0149] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0150] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A method for determining geographic location information, characterized in that: include: Acquire an original feature data set of the target address, wherein the original feature data set includes attribute feature data of multiple attributes of the target address, and the attribute feature data of at least some attributes are first type attribute feature data; Converting the first type of attribute feature data in the original feature data set into second type of attribute feature data to obtain a target feature data set for the target address; The geographic location information of the target address is determined based on the target feature data set.

2. The method according to claim 1, characterized in that The first type of attribute feature data is character type attribute feature data, and the second type of attribute feature data is picture type attribute feature data.

3. The method according to claim 2, characterized in that The converting the first type of attribute feature data in the original feature data set into second type of attribute feature data comprises: For a target attribute among the at least some attributes, a graphic processing method corresponding to the target attribute is used to perform graphic processing on the first type attribute feature data of the target attribute to obtain the second type attribute feature data of the target attribute.

4. The method according to claim 3, characterized in that The adopting a picture processing method corresponding to the target attribute to perform picture processing on the first type of attribute feature data of the target attribute to obtain the second type of attribute feature data of the target attribute includes at least one of the following: In the case where the target attribute is an associated point attribute, generating an associated point heat map of the target address based on the first type attribute feature data of the target attribute as the second type feature data of the target attribute; In the case where the target attribute is a geographical location range attribute, generating a geographical location range map of the target address based on the first type attribute feature data of the target attribute as the second type feature data of the target attribute; In the case where the target attribute is a regional characteristic attribute, a regional characteristic map of the target area where the target address is located is generated based on the first type attribute characteristic data of the target attribute as the second type characteristic data of the target attribute.

5. The method according to claim 4, characterized in that The target address is a location address of a target location event, the associated point attributes include historical location point attributes, and the associated point heat map of the target address is generated based on the first type of attribute feature data of the target attributes, including: Classifying the target address according to the administrative level to obtain a multi-level positioning address of the target address at different administrative levels; For the location address of the target level in the multi-level location addresses, based on the historical location point data matching the location address of the target level, a historical location point heat map corresponding to the location address of the target level is generated.

6. The method according to claim 2, characterized in that The original feature data set also includes second type attribute feature data, which includes a driving trajectory map corresponding to the driving trajectory attributes of the target address, and the driving trajectory map is used to present the driving trajectory within a preset distance range from the target address.

7. The method according to any one of claims 1 to 6, characterized in that: The determining of the geographic location information of the target address based on the target feature data set includes: Inputting the target feature data set into a pre-trained geographic location determination model, and obtaining a geographic location distribution probability map output by the geographic location determination model, wherein the geographic location distribution probability map indicates the distribution probability of the target address at different candidate geographic locations; Inputting the target feature data set and the geographic location distribution probability map into a pre-trained geographic location evaluation model, and determining the confidence of the geographic location distribution probability map through the geographic location evaluation model; If the confidence is greater than or equal to a preset confidence threshold, the geographic coordinates of the target geographic location are obtained as the geographic location information of the target address, and the target geographic location is the candidate geographic location with the highest distribution probability corresponding to the target address in the geographic location distribution probability map.

8. The method according to claim 7, characterized in that The target address is the location address of the target location event, and the attribute feature data includes first feature data and second feature data, wherein: The first characteristic data is labeled data corresponding to the target address; The second feature data is unlabeled data corresponding to the target address, and the second feature data includes a driving trajectory map and / or historical positioning point information; The geographic location determination model determines the candidate geographic location corresponding to the target address based on the first feature data and the geographic location range corresponding to the second feature data.

9. A device for determining geographic location information, characterized in that: include: A data set acquisition module, configured to acquire an original feature data set of a target address, wherein the original feature data set includes attribute feature data of multiple attributes of the target address, and the attribute feature data of at least some attributes are first type attribute feature data; A data conversion module, used for converting the first type of attribute feature data in the original feature data set into second type of attribute feature data to obtain a target feature data set of the target address; A location determination module is used to determine the geographic location information of the target address based on the target feature data set.

10. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the method for determining geographic location information according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining geographic location information according to any one of claims 1 to 8 when executed.

12. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method for determining geographic location information according to any one of claims 1 to 8 is implemented.

Images