WO2021174917A1

WO2021174917A1 - Artificial intelligence-based poi positioning method and device, computer device, and medium

Info

Publication number: WO2021174917A1
Application number: PCT/CN2020/131521
Authority: WO
Inventors: 张登峰
Original assignee: 平安科技（深圳）有限公司
Priority date: 2020-10-13
Filing date: 2020-11-25
Publication date: 2021-09-10
Also published as: CN112235714B; CN112235714A

Abstract

Provided are an artificial intelligence-based POI positioning method and device, a computer device, and a medium. The positioning method comprises: obtaining the service set identifiers and latitude and longitude data of multiple WIFIs to be classified of a user (S11); calculating, according to the latitude and longitude data, the attribute matrices of the multiple WIFIs to be classified (S12); generating, according to the attribute matrices, multiple attribute topological graphs, each attribute topological graph comprising several WIFIs to be classified (S13); inputting the service set identifiers of the several WIFIs to be classified in each attribute topological graph into a private-public binary classification model for classification, and determining, according to the classification result, the attribute label of each WIFI to be classified in each attribute topological graph (S14); obtaining multiple target WIFIs to be classified of which the attribute labels are public, and positioning a POI according to the service set identifier and latitude and longitude data of each target WIFI to be classified (S15). The positioning method applies artificial intelligence technology to POI positioning and can precisely position the POIs of a public WIFI.

Description

Artificial intelligence-based POI positioning method, device, computer equipment and medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on October 13, 2020, the application number is 202011092085.2, and the invention title is "artificial intelligence-based POI positioning method, device, computer equipment and medium", and its entire content Incorporated in this application by reference.

Technical field

This application relates to the field of positioning technology, in particular to a POI positioning method, device, computer equipment and medium based on artificial intelligence.

Background technique

In a geographic information system, a POI (Point of Interest) can be a house, a shop, a post box, or a bus stop, etc. With the increasing demand for indoor location services, more and more researchers have devoted themselves to the research field of indoor location technology. Among them, due to the widespread deployment of WIFI networks and devices and the widespread use of smart mobile devices, WIFI-based indoor positioning technology has become a research hotspot.

In the process of implementing this application, the inventor found that the prior art collects a large amount of LBS data (such as the longitude and latitude data of the Wi-Fi that the user has connected to) to classify and locate the POI. However, this method is limited by the longitude and latitude data. Accuracy, once the latitude and longitude data is wrong, the classification and positioning of the POI will inevitably be wrong; and for some smaller POIs, the longitude and latitude data cannot meet the granularity requirements of the classification and positioning, and the accuracy of the POI classification and positioning is low.

Summary of the invention

In view of the above, it is necessary to propose a POI positioning method, device, computer equipment and medium based on artificial intelligence, which can accurately locate the POI of the public WIFI.

The first aspect of the present application provides a POI positioning method based on artificial intelligence, the method including:

Obtain the user's multiple service set identifiers and latitude and longitude data of the WIFI to be classified;

Calculating attribute matrices of the plurality of WIFIs to be classified according to the latitude and longitude data;

Generate a plurality of attribute topology maps according to the attribute matrix, wherein each attribute topology map includes several WIFIs to be classified;

Enter the service set identifiers of several WIFIs to be classified in each attribute topology map into the private-public binary classification model for classification, and determine the attributes of each WIFI to be classified in each attribute topology map according to the classification results Label;

Acquire multiple target WIFIs to be classified corresponding to the common attribute with the attribute tag, and locate the POI according to the service set identifier and latitude and longitude data of each of the target WIFIs to be classified.

The second aspect of the present application provides a POI positioning device based on artificial intelligence, the device comprising:

The obtaining module is used to obtain the service set identifiers and latitude and longitude data of multiple WIFIs to be classified by the user;

A calculation module, configured to calculate attribute matrices of the plurality of WIFIs to be classified according to the latitude and longitude data;

A generating module, configured to generate a plurality of attribute topology maps according to the attribute matrix, wherein each attribute topology map includes several WIFIs to be classified;

The classification module is used to input several WIFI service set identifiers to be classified in each attribute topology map into the private-public binary classification model for classification, and determine each to-be-categorized WIFI service set identifier in each attribute topology map according to the classification result. Attribute label of classified WIFI;

The positioning module is configured to obtain multiple target WIFIs to be classified corresponding to the common attribute with the attribute tag, and locate the POI according to the service set identifier and latitude and longitude data of each target WIFI to be classified.

A third aspect of the present application provides a computer device, the computer device includes:

The memory is used to store computer-readable instructions;

The processor is configured to implement the following steps when executing the computer-readable instructions:

A fourth aspect of the present application provides a computer-readable storage medium having computer-readable instructions stored on the computer-readable storage medium, and when the computer-readable instructions are executed by a processor, the following steps are implemented:

In summary, the artificial intelligence-based POI positioning methods, devices, computer equipment, and media described in this application can be applied in fields such as smart government affairs, thereby promoting the development of smart cities. This application obtains the service set identifiers and latitude and longitude data of the multiple WIFIs to be classified of the user, calculates the attribute matrix of the multiple WIFIs to be classified according to the latitude and longitude data, and generates multiple attribute topology maps according to the attribute matrix, Realize the first classification of multiple WIFIs to be classified; then enter the service set identifiers of several WIFIs to be classified in each attribute topology map into the private-public binary classification model for classification, and then classify according to the classification The result determines the attribute label of each WIFI to be classified in each attribute topology map, realizes the second classification of multiple WIFIs to be classified, and verifies the private-public binary classification model combined with the attribute topology map. Classification accuracy rate, the resulting attribute label has a higher accuracy rate, which improves the accuracy of subsequent locating the POI of the WIFI to be classified; finally, for the multiple target WIFI to be classified corresponding to the common attribute, the attribute label is a common attribute, according to each The cross-validation of the service set identifier and the latitude and longitude data of the target WIFI to be classified is used to locate the POI, which improves the accuracy of the positioning of the POI.

Description of the drawings

FIG. 1 is a flowchart of a POI positioning method based on artificial intelligence provided in Embodiment 1 of the present application.

Fig. 2 is a structural diagram of a POI positioning device based on artificial intelligence provided in the second embodiment of the present application.

FIG. 3 is a schematic structural diagram of a computer device provided in Embodiment 3 of the present application.

Detailed ways

In order to be able to understand the above objectives, features and advantages of the application more clearly, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the application and the features in the embodiments can be combined with each other if there is no conflict.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of this application. The terms used in the specification of the application herein are only for the purpose of describing specific embodiments, and are not intended to limit the application.

The artificial intelligence-based POI positioning method is executed by computer equipment, and accordingly, the artificial intelligence-based POI positioning device runs in the computer equipment.

FIG. 1 is a flowchart of a POI positioning method based on artificial intelligence provided in Embodiment 1 of the present application. The artificial intelligence-based POI positioning method specifically includes the following steps. According to different requirements, the sequence of the steps in the flowchart can be changed, and some of the steps can be omitted.

S11. Obtain service set identifiers and latitude and longitude data of multiple WIFIs to be classified by the user.

Wherein, the multiple WIFIs to be classified of the user may refer to multiple WIFIs to be classified of the same user, or may refer to the WIFIs to be classified of multiple users.

The computer equipment can obtain the Service Set Identifier (SSID) and latitude and longitude data of multiple WIFIs automatically or passively reported by the user's terminal device, and determine the WIFI corresponding to the multiple WIFI service set identities reported by the terminal device as to be classified WIFI.

The terminal device can automatically or passively report latitude and longitude data based on location-based services (LBS). LBS uses various types of positioning technologies to obtain the current location of the positioning device, and provides information resources and basic services to the positioning device through the mobile Internet.

The service set identifier SSID is used to uniquely identify a WIFI, one service set identifier corresponds to one longitude and latitude data, and one longitude and latitude data can correspond to multiple service set identifiers.

By obtaining the service set identifiers and latitude and longitude data of multiple WIFIs to be classified by the user, and performing accurate POI positioning for each WIFI to be classified according to the service set identifiers and latitude and longitude data, the behavior of one user or multiple users can be realized Analysis.

S12: Calculate attribute matrices of the multiple WIFIs to be classified according to the latitude and longitude data.

The latitude and longitude data can locate the geographic location of the WIFI to a certain extent. The latitude and longitude data of adjacent or similar WIFIs are the same or not much different. The latitude and longitude data can preliminarily classify multiple WIFIs to be classified.

In an optional embodiment, the calculating the attribute matrix of the plurality of WIFIs to be classified according to the latitude and longitude data includes:

Calculate the distance between any two WIFIs to be classified according to the latitude and longitude data;

Generating a distance matrix according to the distance;

Comparing any distance in the distance matrix with a preset distance threshold;

When any distance in the distance matrix is greater than or equal to the preset distance threshold, updating any distance in the distance matrix as the first category identifier;

When any distance in the distance matrix is less than the preset distance threshold, updating any distance in the distance matrix as a second category identifier;

The attribute matrix is obtained according to the updated distance matrix.

Wherein, the distance may be Euclidean distance, cosine angle, Manhattan distance, Chebyshev distance, power distance, etc. The closer the distance, the closer the latitude and longitude data of the corresponding two WIFIs, and the more the two WIFIs belong to the same category (private WIFI type, or public WIFI type); the farther the distance, the greater the latitude and longitude data of the corresponding two WIFIs. When separated, the two WIFIs belong to different categories.

Wherein, the first category identifier may be 1, and the second category identifier may be 0.

S13: Generate a plurality of attribute topology maps according to the attribute matrix, wherein each attribute topology map includes several WIFIs to be classified.

The elements in the attribute matrix are category identifiers, and WIFIs corresponding to elements with the same category identifier are clustered together to generate an attribute topology map.

In an optional embodiment, the generating a plurality of attribute topological graphs according to the attribute matrix includes:

Acquiring the attribute matrix as the two first WIFIs corresponding to the first category identifier, acquiring the attribute matrix as the two second WIFIs corresponding to the second category identifier;

A first attribute topology diagram is generated according to a plurality of the first WIFIs and a second attribute topology diagram is generated according to a plurality of the second WIFIs, wherein the vertex in the first attribute topology diagram is the first WIFI, and the first attribute topology diagram is The vertex in the two-attribute topological graph is the second WIFI.

If there is a first category identifier corresponding to two vertices in the first attribute topology graph, an edge is established between the two vertices. If there is a second category identifier corresponding to the two vertices in the second attribute topology graph, an edge is established between the two vertices.

According to the attribute matrix, multiple attribute topological graphs are generated, which can realize the initial classification of multiple WIFIs to be classified, categorize WIFIs with the same category into one category, and categorize WIFIs with different categories into different categories.

S14. Input the service set identifiers of several WIFIs to be classified in each attribute topology map into the private-public binary classification model for classification, and determine each WIFI to be classified in each attribute topology map according to the classification results The attribute label.

Among them, the private-public two-classification model is obtained by pre-training, and is used for the secondary classification of the WIFI to be classified, and to determine whether the WIFI to be classified is a public WIFI or a private WIFI.

In an optional embodiment, the service set identifiers of several WIFIs to be classified in each attribute topology map are input into a private-public binary classification model for classification, and each attribute topology is determined according to the classification result The attribute label of each WIFI to be classified in the figure includes:

For each attribute topology map, input the service set identifiers of several WIFIs to be classified in the attribute topology map into the private-public two-classification model for classification to obtain the predicted attribute label of each WIFI to be classified;

Acquiring target attribute tags with the same predicted attribute tags in the predicted attribute tags;

Calculating the number of the target attribute tags;

The maximum number of target attribute labels is determined as the attribute label of each WIFI to be classified in the attribute topology map.

Since several Wi-Fis to be classified corresponding to the same attribute topology map have the same attribute label, the private-public two-classification model is used to classify the service set identifiers of several Wi-Fis to be classified. The attribute tags should all be the same or have a larger number of the same.

In an optional embodiment, after the calculating the number of the target attribute tags, the method further includes:

Judge whether the maximum number of target attribute tags matches the corresponding attribute topology map;

When the maximum number of target attribute labels matches the corresponding attribute topology map, determining the maximum number of target attribute labels as the attribute label of each WIFI to be classified in the attribute topology map;

When the maximum number of target attribute labels do not match the corresponding attribute topological map, recalculate the attribute matrices of the multiple WIFIs to be classified according to the latitude and longitude data, and generate multiple attribute topological maps according to the regenerated attribute matrix until The maximum number of target attribute labels matches the corresponding attribute topology map.

In this optional embodiment, after the preliminary classification of multiple WIFIs to be classified is achieved through the attribute topology, the private-public binary classification model is then used to perform secondary classification of several WIFIs to be classified in the same attribute topology. The attribute labels are obtained by classification, and the attribute topological graph is used to check whether the attribute labels are correctly classified, which improves the correct rate of the attribute label classification.

When the attribute topology map is used to verify that the attribute label is not correctly classified, the distance between any two WIFIs to be classified is recalculated according to the latitude and longitude data. The distance calculation formula at this time is different from the previous distance calculation formula. For example, the Euclidean distance is used for the first time, and the cosine similarity is used for the second time.

In an optional embodiment, the training process of the private-public binary classification model includes:

Obtain the service set identifiers of multiple WIFIs whose attribute tags are private attributes and the service set identifiers of multiple WIFI whose attribute tags are public;

The service set identifier and the corresponding attribute label are used as a data set, and the support vector machine is trained using the data set to obtain a private-public binary classification model.

The service set identifiers of multiple WIFIs can be obtained, and the service set identifiers of multiple WIFIs can be marked with attribute tags using the labeling tool, and the service set identifiers of multiple WIFIs with attribute tags are used as the training private-public binary classification model. data set.

S15: Obtain multiple target WIFIs to be classified corresponding to the common attribute with the attribute tag, and locate the POI according to the service set identifier and latitude and longitude data of each of the target WIFIs to be classified.

The POI positioning of private WIFI has no commercial value. Therefore, this application only performs POI positioning for public WIFI.

In an optional embodiment, the locating the POI according to the service set identifier and the latitude and longitude data of the WIFI to be classified by the target includes:

Calling the preset first search POI interface to search for multiple first POIs corresponding to the latitude and longitude data;

Calling a preset second search POI interface to search for multiple second POIs corresponding to the service set identifier and the latitude and longitude data;

Matching the plurality of first POIs with the plurality of second POIs;

Determining the same POI among the plurality of first POIs and the plurality of second POIs as the target POI;

It is determined that the target POI is the POI of the target WIFI to be classified.

For the filtered public Wi-Fi data, you can call the preset first search POI interface (for example, the API of "Search POI"-"Keyword Search" provided by AutoNavi Maps), enter the SSID corresponding to the public Wi-Fi and Its latitude and longitude data. For some public WIFI, because the SSID name is abstract and meaningless, it is impossible to infer the POI, you can further call the preset second search POI interface (for example, the "search POI"-"surround search" API provided by Baidu Maps) , Enter the latitude and longitude data corresponding to the WIFI, and return possible POIs.

Through the cross-validation of SSID and latitude and longitude data, data will be returned only when both are satisfied, which can effectively ensure the correctness of the POI returned by the search process.

When returning POI information, it will not only return the name of the POI, but also return high-quality information such as the multi-level classification of the POI.

In an optional embodiment, after the POI is located according to the service set identifier and latitude and longitude data of the WIFI to be classified for each target, the method may further include:

Calculate the quantity with the same POI;

Get the name of the POI corresponding to the maximum number;

Recommend commodities corresponding to the name to the user.

Exemplarily, suppose there are 100 WIFIs to be classified for the same user. After classifying the 100 WIFIs to be classified by combining the attribute topology map and the private-public binary classification model, 30 public WIFIs to be classified are determined. Classified WIFI. Of these 30 public WIFIs to be classified, there are 20 WIFIs to be classified and the POI corresponding to coffee is coffee, then coffee can be recommended to the user, which realizes the function of recommending products to the user according to the WIFI used by the user, and improves the efficiency of product recommendation. .

In summary, this application obtains the service set identifiers and latitude and longitude data of multiple WIFIs to be classified of the user, calculates the attribute matrix of the multiple WIFIs to be classified according to the latitude and longitude data, and generates multiple attributes according to the attribute matrix. The topology diagram realizes the first classification of multiple WIFIs to be classified; and then enters the service set identifiers of several WIFIs to be classified in each attribute topology diagram into the private-public binary classification model for classification. According to the classification results, the attribute label of each WIFI to be classified in each attribute topology map is determined, and the second classification of multiple WIFIs to be classified is realized, and combined with the attribute topology map, the private-public two are verified. The classification accuracy rate of the classification model, and the resulting attribute label has a higher accuracy rate, which improves the accuracy of subsequent locating the POI of the WIFI to be classified; finally, for the plurality of target WIFIs to be classified corresponding to the common attribute, the attribute labels are public. The POI is located by cross-validation according to the service set identification and the latitude and longitude data of the WIFI to be classified for each target, which improves the accuracy of the positioning of the POI.

This application can be applied to scenarios such as smart education, smart communities, and smart government affairs, so as to promote the construction of smart cities.

It should be emphasized that, in order to further ensure the privacy and security of the above-mentioned POI, the above-mentioned POI can be stored in a node of the blockchain.

In some embodiments, the artificial intelligence-based POI positioning device 20 may include multiple functional modules composed of computer-readable instruction segments. The computer-readable instructions of each program segment in the artificial intelligence-based POI positioning device 20 can be stored in the memory of the computer device and executed by at least one processor to execute (see Figure 1 for details). The function of POI positioning.

In this embodiment, the artificial intelligence-based POI positioning device 20 can be divided into multiple functional modules according to the functions it performs. The functional modules may include: an acquisition module 201, a calculation module 202, a generation module 203, a classification module 204, a positioning module 205, and a recommendation module 206. The module referred to in this application refers to a series of computer-readable instruction segments that can be executed by at least one processor and can complete fixed functions, and are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

The obtaining module 201 is used to obtain service set identifiers and latitude and longitude data of multiple WIFIs to be classified by the user.

The calculation module 202 is configured to calculate the attribute matrix of the plurality of WIFIs to be classified according to the latitude and longitude data.

In an optional embodiment, the calculation module 202 calculating the attribute matrix of the plurality of WIFIs to be classified according to the latitude and longitude data includes:

Generating a distance matrix according to the distance;

Comparing any distance in the distance matrix with a preset distance threshold;

The attribute matrix is obtained according to the updated distance matrix.

The generating module 203 is configured to generate multiple attribute topology maps according to the attribute matrix, wherein each attribute topology map includes several WIFIs to be classified.

In an optional embodiment, the generating module 203 generating multiple attribute topology maps according to the attribute matrix includes:

The classification module 204 is used for inputting the service set identifiers of several Wi-Fi to be classified in each attribute topology map into the private-public binary classification model for classification, and determining each attribute topology map according to the classification result. The attribute label of each WIFI to be classified.

In an optional embodiment, the classification module 204 inputs several WIFI service set identifiers to be classified in each attribute topology map into a private-public binary classification model for classification, and determines each service set according to the classification result. The attribute label of each WIFI to be classified in the attribute topology map includes:

Calculating the number of the target attribute tags;

The classification module 204 is further configured to determine whether the maximum number of target attribute labels matches the corresponding attribute topology map after the calculation of the number of target attribute labels; when the maximum number of target attribute labels matches the corresponding attribute topology When the graphs are matched, the maximum number of target attribute labels is determined as the attribute label of each WIFI to be classified in the attribute topology diagram; when the maximum number of target attribute labels does not match the corresponding attribute topology diagram, re-according to the The latitude and longitude data calculate the attribute matrix of the plurality of WIFIs to be classified, and generate a plurality of attribute topology maps according to the regenerated attribute matrix until the maximum number of target attribute labels matches the corresponding attribute topology map.

The positioning module 205 is configured to obtain multiple target WIFIs to be classified corresponding to the common attribute with the attribute tag, and locate the POI according to the service set identifier and latitude and longitude data of each target WIFI to be classified.

In an optional embodiment, the positioning module 205 locating the POI according to the service set identifier and latitude and longitude data of the target WIFI to be classified includes:

Matching the plurality of first POIs with the plurality of second POIs;

The recommendation module 206 is configured to calculate the number of the same POI after locating the POI according to the service set identifier and latitude and longitude data of the WIFI to be classified for each target; obtain the name of the POI corresponding to the maximum number; The user recommends the commodity corresponding to the name.

Refer to FIG. 3, which is a schematic structural diagram of a computer device provided in Embodiment 3 of this application. In a preferred embodiment of the present application, the computer device 3 includes a memory 31, at least one processor 32, at least one communication bus 33, and a transceiver 34.

Those skilled in the art should understand that the structure of the computer device shown in FIG. 3 does not constitute a limitation of the embodiment of the present application. It may be a bus-type structure or a star structure. The computer device 3 may also include a graph Show more or less other hardware or software, or different component arrangements.

In some embodiments, the computer device 3 is a computer device that can automatically perform numerical calculation and/or information processing in accordance with pre-set or stored instructions. Its hardware includes, but is not limited to, a microprocessor and an application specific integrated circuit. , Programmable gate arrays, digital processors and embedded devices, etc. The computer device 3 may also include a client device, and the client device includes but is not limited to any electronic product that can interact with a client through a keyboard, a mouse, a remote control, a touch panel, or a voice control device, etc., for example, Personal computers, tablet computers, smart phones, digital cameras, etc.

It should be noted that the computer device 3 is only an example. If other existing or future electronic products can be adapted to this application, they should also be included in the scope of protection of this application and included here by reference. .

In some embodiments, computer-readable instructions are stored in the memory 31, and when the computer-readable instructions are executed by the at least one processor 32, all or all of the aforementioned artificial intelligence-based POI positioning methods are implemented. Part of the steps. The memory 31 includes volatile and non-volatile memory, such as random access memory (Random Access Memory, RAM), read-only memory (Read-Only Memory, ROM), and programmable read-only memory (Programmable Read-Only). Memory, PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electronic Erasable Programmable Read-Only Memory, OTPROM Read memory (Electrically-Erasable Programmable Read-Only Memory, EEPROM), CD-ROM (Compact Disc Read-Only Memory, CD-ROM) or other optical disk storage, magnetic disk storage, tape storage, or capable of carrying or storing data Computer-readable storage medium. The computer-readable storage medium may be non-volatile or volatile.

Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, where the storage program area may store an operating system, an application program required by at least one function, etc.; the storage data area may store Data created by the use of nodes, etc.

The blockchain referred to in this application is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information for verification. The validity of the information (anti-counterfeiting) and the generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

In some embodiments, the at least one processor 32 is the control core (Control Unit) of the computer device 3, which uses various interfaces and lines to connect the various components of the entire computer device 3, and is stored in the computer device 3 through operation or execution. The programs or modules in the memory 31 and the data stored in the memory 31 are called to execute various functions of the computer device 3 and process data. For example, when the at least one processor 32 executes the computer-readable instructions stored in the memory, all or part of the steps of the artificial intelligence-based POI positioning method described in the embodiments of the present application are implemented; or the artificial intelligence-based POI is implemented All or part of the function of the positioning device. The at least one processor 32 may be composed of integrated circuits, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits with the same function or different functions, including one or more central processing units. (Central Processing unit, CPU), a combination of microprocessors, digital processing chips, graphics processors, and various control chips.

In some embodiments, the at least one communication bus 33 is configured to implement connection and communication between the memory 31 and the at least one processor 32 and the like.

Although not shown, the computer device 3 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 32 through a power management device, so as to be realized by the power management device. Manage functions such as charging, discharging, and power management. The power supply may also include any components such as one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, and power status indicators. The computer device 3 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

The above-mentioned integrated unit implemented in the form of a software function module may be stored in a computer readable storage medium. The above-mentioned software function module is stored in a storage medium, and includes several instructions to make a computer device (which may be a personal computer, a computer device, or a network device, etc.) or a processor execute the method described in each embodiment of the present application part.

In the several embodiments provided in this application, it should be understood that the disclosed device and method may be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional modules in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be realized either in the form of hardware or in the form of hardware plus software functional modules.

For those skilled in the art, it is obvious that the present application is not limited to the details of the foregoing exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or basic characteristics of the application. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of this application is defined by the appended claims rather than the above description, and therefore it is intended to fall into the claims. All changes in the meaning and scope of the equivalent elements of are included in this application. Any reference signs in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "including" does not exclude other elements or the singular number does not exclude the plural number. Multiple units or devices stated in this application can also be implemented by one unit or device through software or hardware. Words such as first and second are used to denote names, but do not denote any specific order.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the application and not to limit them. Although the application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the application can be Make modifications or equivalent replacements without departing from the spirit and scope of the technical solution of the present application.

Claims

A POI positioning method based on artificial intelligence, wherein the method includes:

Obtain the user's multiple service set identifiers and latitude and longitude data of the WIFI to be classified;

Calculating attribute matrices of the plurality of WIFIs to be classified according to the latitude and longitude data;

Generate a plurality of attribute topology maps according to the attribute matrix, wherein each attribute topology map includes several WIFIs to be classified;

Enter the service set identifiers of several WIFIs to be classified in each attribute topology map into the private-public binary classification model for classification, and determine the attributes of each WIFI to be classified in each attribute topology map according to the classification results Label;

Acquire multiple target WIFIs to be classified corresponding to the common attribute with the attribute tag, and locate the POI according to the service set identifier and latitude and longitude data of each of the target WIFIs to be classified.
The artificial intelligence-based POI positioning method according to claim 1, wherein the calculating the attribute matrix of the plurality of WIFIs to be classified according to the latitude and longitude data comprises:

Calculate the distance between any two WIFIs to be classified according to the latitude and longitude data;

Generating a distance matrix according to the distance;

Comparing any distance in the distance matrix with a preset distance threshold;

When any distance in the distance matrix is greater than or equal to the preset distance threshold, updating any distance in the distance matrix as the first category identifier;

When any distance in the distance matrix is less than the preset distance threshold, updating any distance in the distance matrix as a second category identifier;

The attribute matrix is obtained according to the updated distance matrix.
The method for positioning POI based on artificial intelligence according to claim 2, wherein said generating a plurality of attribute topological maps according to said attribute matrix comprises:

Acquiring the attribute matrix as the two first WIFIs corresponding to the first category identifier, acquiring the attribute matrix as the two second WIFIs corresponding to the second category identifier;

A first attribute topology diagram is generated according to a plurality of the first WIFIs and a second attribute topology diagram is generated according to a plurality of the second WIFIs, wherein the vertex in the first attribute topology diagram is the first WIFI, and the first attribute topology diagram is The vertices in the two-attribute topological graph are the second WIFI; when the two vertices in the first attribute topological graph correspond to the first category identifier, an edge is established between the two vertices; the second When there is a second category identifier corresponding to two vertices in the attribute topology graph, an edge is established between the two vertices.
The artificial intelligence-based POI positioning method according to claim 1, wherein the service set identifiers of several WIFI to be classified in each attribute topology map are input into a private-public binary classification model for classification, and According to the classification result, the attribute label of each WIFI to be classified in each attribute topology map is determined to include:

For each attribute topology map, input the service set identifiers of several WIFIs to be classified in the attribute topology map into the private-public two-classification model for classification to obtain the predicted attribute label of each WIFI to be classified;

Acquiring target attribute tags with the same predicted attribute tags in the predicted attribute tags;

Calculating the number of the target attribute tags;

The maximum number of target attribute labels is determined as the attribute label of each WIFI to be classified in the attribute topology map.
The POI positioning method based on artificial intelligence according to claim 4, wherein, after the calculating the number of the target attribute tags, the method further comprises:

Judge whether the maximum number of target attribute tags matches the corresponding attribute topology map;

When the maximum number of target attribute labels matches the corresponding attribute topology map, determining the maximum number of target attribute labels as the attribute label of each WIFI to be classified in the attribute topology map;

When the maximum number of target attribute labels does not match the corresponding attribute topology map, the attribute matrix of the plurality of WIFIs to be classified is recalculated according to the latitude and longitude data, and multiple attribute topology maps are generated according to the regenerated attribute matrix until The maximum number of target attribute labels matches the corresponding attribute topology map.
The artificial intelligence-based POI positioning method according to any one of claims 1 to 5, wherein the locating the POI according to the service set identifier and latitude and longitude data of the WIFI to be classified includes:

Calling the preset first search POI interface to search for multiple first POIs corresponding to the latitude and longitude data;

Calling a preset second search POI interface to search for multiple second POIs corresponding to the service set identifier and the latitude and longitude data;

Matching the plurality of first POIs with the plurality of second POIs;

Determining the same POI among the plurality of first POIs and the plurality of second POIs as the target POI;

It is determined that the target POI is the POI of the target WIFI to be classified.
The artificial intelligence-based POI positioning method according to claim 6, wherein, after the POI is located according to the service set identifier and latitude and longitude data of the WIFI to be classified for each of the targets, the method further comprises:

Calculate the quantity with the same POI;

Get the name of the POI corresponding to the maximum number;

Recommend commodities corresponding to the name to the user.
A POI positioning device based on artificial intelligence, wherein the device includes:

The obtaining module is used to obtain the service set identifiers and latitude and longitude data of multiple WIFIs to be classified by the user;

A calculation module, configured to calculate attribute matrices of the plurality of WIFIs to be classified according to the latitude and longitude data;

A generating module, configured to generate a plurality of attribute topology maps according to the attribute matrix, wherein each attribute topology map includes several WIFIs to be classified;

The classification module is used to input several WIFI service set identifiers to be classified in each attribute topology map into the private-public binary classification model for classification, and determine each to-be-categorized WIFI service set identifier in each attribute topology map according to the classification result. Attribute label of classified WIFI;

The positioning module is configured to obtain multiple target WIFIs to be classified corresponding to the common attribute with the attribute tag, and locate the POI according to the service set identifier and latitude and longitude data of each target WIFI to be classified.
A computer device, wherein the computer device includes:

The memory is used to store computer-readable instructions;

The processor is configured to implement the following steps when executing the computer-readable instructions:

Obtain the user's multiple service set identifiers and latitude and longitude data of the WIFI to be classified;

Calculating attribute matrices of the plurality of WIFIs to be classified according to the latitude and longitude data;

Generate a plurality of attribute topology maps according to the attribute matrix, wherein each attribute topology map includes several WIFIs to be classified;

Enter the service set identifiers of several WIFIs to be classified in each attribute topology map into the private-public binary classification model for classification, and determine the attributes of each WIFI to be classified in each attribute topology map according to the classification results Label;

Acquire multiple target WIFIs to be classified corresponding to the common attribute with the attribute tag, and locate the POI according to the service set identifier and latitude and longitude data of each of the target WIFIs to be classified.
9. The computer device according to claim 9, wherein when the processor executes the computer-readable instructions to calculate the attribute matrix of the plurality of WIFIs to be classified according to the latitude and longitude data, it specifically includes:

Calculate the distance between any two WIFIs to be classified according to the latitude and longitude data;

Generating a distance matrix according to the distance;

Comparing any distance in the distance matrix with a preset distance threshold;

When any distance in the distance matrix is greater than or equal to the preset distance threshold, updating any distance in the distance matrix as the first category identifier;

When any distance in the distance matrix is less than the preset distance threshold, updating any distance in the distance matrix as a second category identifier;

The attribute matrix is obtained according to the updated distance matrix.
10. The computer device according to claim 10, wherein when the processor executes the computer-readable instructions to generate a plurality of attribute topology maps according to the attribute matrix, it specifically comprises:

Acquiring the attribute matrix as the two first WIFIs corresponding to the first category identifier, acquiring the attribute matrix as the two second WIFIs corresponding to the second category identifier;

A first attribute topology diagram is generated according to a plurality of the first WIFIs and a second attribute topology diagram is generated according to a plurality of the second WIFIs, wherein the vertex in the first attribute topology diagram is the first WIFI, and the first attribute topology diagram is The vertices in the two-attribute topological graph are the second WIFI; when the two vertices in the first attribute topological graph correspond to the first category identifier, an edge is established between the two vertices; the second When there is a second category identifier corresponding to two vertices in the attribute topology graph, an edge is established between the two vertices.
The computer device according to claim 9, wherein the processor executes the computer-readable instructions to realize the input of service set identifiers of a plurality of WIFIs to be classified in each attribute topology map into a private-public binary classification When classifying in the model, and determining the attribute label of each WIFI to be classified in each attribute topology map according to the classification result, the details include:

For each attribute topology map, input the service set identifiers of several WIFIs to be classified in the attribute topology map into the private-public two-classification model for classification to obtain the predicted attribute label of each WIFI to be classified;

Acquiring target attribute tags with the same predicted attribute tags in the predicted attribute tags;

Calculating the number of the target attribute tags;

The maximum number of target attribute labels is determined as the attribute label of each WIFI to be classified in the attribute topology map.
The computer device according to claim 12, wherein, after said calculating the number of said target attribute tags, said processor executing said computer-readable instructions is further used to implement the following steps:

Judge whether the maximum number of target attribute tags matches the corresponding attribute topology map;

When the maximum number of target attribute labels matches the corresponding attribute topology map, determining the maximum number of target attribute labels as the attribute label of each WIFI to be classified in the attribute topology map;

When the maximum number of target attribute labels do not match the corresponding attribute topological map, recalculate the attribute matrices of the multiple WIFIs to be classified according to the latitude and longitude data, and generate multiple attribute topological maps according to the regenerated attribute matrix until The maximum number of target attribute labels matches the corresponding attribute topology map.
The computer device according to any one of claims 9 to 13, wherein the processor executes the computer-readable instructions to realize when the POI is located according to the service set identification and latitude and longitude data of the WIFI to be classified by the target , Specifically including:

Calling the preset first search POI interface to search for multiple first POIs corresponding to the latitude and longitude data;

Calling a preset second search POI interface to search for multiple second POIs corresponding to the service set identifier and the latitude and longitude data;

Matching the plurality of first POIs with the plurality of second POIs;

Determining the same POI among the plurality of first POIs and the plurality of second POIs as the target POI;

It is determined that the target POI is the POI of the target WIFI to be classified.
The computer device according to claim 14, wherein, after the POI is located according to the service set identification and latitude and longitude data of the WIFI to be classified for each of the targets, the processor executes the computer-readable instructions and uses To achieve the following steps:

Calculate the quantity with the same POI;

Get the name of the POI corresponding to the maximum number;

Recommend commodities corresponding to the name to the user.
A computer-readable storage medium having computer-readable instructions stored thereon, wherein the computer-readable instructions implement the following steps when executed by a processor:

Obtain the user's multiple service set identifiers and latitude and longitude data of the WIFI to be classified;

Calculating attribute matrices of the plurality of WIFIs to be classified according to the latitude and longitude data;

Generate a plurality of attribute topology maps according to the attribute matrix, wherein each attribute topology map includes several WIFIs to be classified;

Enter the service set identifiers of several WIFIs to be classified in each attribute topology map into the private-public binary classification model for classification, and determine the attributes of each WIFI to be classified in each attribute topology map according to the classification results Label;

Acquire multiple target WIFIs to be classified corresponding to the common attribute with the attribute tag, and locate the POI according to the service set identifier and latitude and longitude data of each of the target WIFIs to be classified.
The computer-readable storage medium according to claim 16, wherein, when the computer-readable instructions are executed by the processor to calculate the attribute matrix of the plurality of WIFIs to be classified according to the latitude and longitude data, it specifically includes :

Calculate the distance between any two WIFIs to be classified according to the latitude and longitude data;

Generating a distance matrix according to the distance;

Comparing any distance in the distance matrix with a preset distance threshold;

When any distance in the distance matrix is greater than or equal to the preset distance threshold, updating any distance in the distance matrix as the first category identifier;

When any distance in the distance matrix is less than the preset distance threshold, updating any distance in the distance matrix as a second category identifier;

The attribute matrix is obtained according to the updated distance matrix.
17. The computer-readable storage medium according to claim 17, wherein when the computer-readable instructions are executed by the processor to generate a plurality of attribute topological maps according to the attribute matrix, it specifically comprises:

Acquiring the attribute matrix as the two first WIFIs corresponding to the first category identifier, acquiring the attribute matrix as the two second WIFIs corresponding to the second category identifier;

A first attribute topology diagram is generated according to a plurality of the first WIFIs and a second attribute topology diagram is generated according to a plurality of the second WIFIs, wherein the vertex in the first attribute topology diagram is the first WIFI, and the first attribute topology diagram is The vertices in the two-attribute topological graph are the second WIFI; when the two vertices in the first attribute topological graph correspond to the first category identifier, an edge is established between the two vertices; the second When there is a second category identifier corresponding to two vertices in the attribute topology graph, an edge is established between the two vertices.
The computer-readable storage medium according to claim 16, wherein the computer-readable instructions are executed by the processor to realize the input of service set identifiers of a plurality of WIFIs to be classified in each attribute topology map for private use -When performing classification in a public two-class classification model, and determining the attribute label of each WIFI to be classified in each attribute topology map according to the classification result, it specifically includes:

For each attribute topology map, input the service set identifiers of several WIFIs to be classified in the attribute topology map into the private-public two-classification model for classification to obtain the predicted attribute label of each WIFI to be classified;

Acquiring target attribute tags with the same predicted attribute tags in the predicted attribute tags;

Calculating the number of the target attribute tags;

The maximum number of target attribute labels is determined as the attribute label of each WIFI to be classified in the attribute topology map.
19. The computer-readable storage medium of claim 19, wherein, after the calculation of the number of the target attribute tags, the computer-readable instructions are executed by the processor to further implement the following steps:

Judge whether the maximum number of target attribute tags matches the corresponding attribute topology map;

When the maximum number of target attribute labels matches the corresponding attribute topology map, determining the maximum number of target attribute labels as the attribute label of each WIFI to be classified in the attribute topology map;

When the maximum number of target attribute labels do not match the corresponding attribute topological map, recalculate the attribute matrices of the multiple WIFIs to be classified according to the latitude and longitude data, and generate multiple attribute topological maps according to the regenerated attribute matrix until The maximum number of target attribute labels matches the corresponding attribute topology map.