CN110012426B

CN110012426B - Method and device for determining casualty POI, computer equipment and storage medium

Info

Publication number: CN110012426B
Application number: CN201910291545.5A
Authority: CN
Inventors: 李岩岩; 段建国; 路新江; 熊辉
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2019-04-11
Filing date: 2019-04-11
Publication date: 2021-01-08
Anticipated expiration: 2039-04-11
Also published as: CN110012426A

Abstract

The embodiment of the invention discloses a method and a device for determining a casualty POI, computer equipment and a storage medium. The method comprises the following steps: the method comprises the steps of obtaining a POI to be verified, and obtaining a target Wi-Fi matched with the POI according to the space-time correlation; performing time distribution statistics on the connection quantity of the target Wi-Fi to obtain a time distribution statistical result; and if the target Wi-Fi is determined to meet the life cycle fading condition according to the time distribution statistical result, determining the POI as a death POI. The embodiment of the invention can improve the efficiency and the accuracy of distinguishing the casual POI, reduce the cost of distinguishing the casual POI and improve the coverage rate of the POI.

Description

Method and device for determining casualty POI, computer equipment and storage medium

Technical Field

The embodiment of the invention relates to a data processing technology, in particular to a method and a device for determining a casualty POI, computer equipment and a storage medium.

Background

With the development of science and technology and the continuous progress of internet technology, the services provided by the mobile terminal are continuously upgraded. Location Based Services (LBS) are currently hot spots in mobile terminal Services.

In LBS, Point of Interest (POI) has become a standard for measuring the value of LBS. The determination of the casualty POI also plays an important role in LBS related application, and particularly can improve the competitiveness of map products. In fact, the disappearance of POIs reflects the competitiveness of an area, for example, the high proportion of POIs in an area indicates that the area is poor in competitiveness and vitality, which also plays an important role in Region (Region) representation.

Currently, the judgment of POI death mainly includes the following three ways: the user uploads User Generated Content (UGC), professional-generated Content (PGC) and a web crawler mode. Among them, the UGC method has the following drawbacks: firstly, the user uploading positivity needs to be called through operation activities, secondly, due to the randomness of user levels, the data quality is uncontrollable, the data quality is poor in a very large probability, and higher manpower is needed to be consumed for auditing; the PGC method has drawbacks: firstly, the cost is high, and high labor cost, equipment cost and traffic cost are required. Meanwhile, the coverage rate of the acquisition is low, and the time efficiency is often low due to high cost; the web crawler method has the defects that: as the information of the new increase or the disappearance of the POI is discretely distributed in the Internet, the network crawling and information processing process is more complicated, and the coverage rate is lower.

Disclosure of Invention

The embodiment of the invention provides a method and a device for determining casualty POI, computer equipment and a storage medium, which can improve the efficiency and the accuracy of distinguishing the casualty POI, reduce the cost of distinguishing the casualty POI and improve the coverage rate of the POI.

In a first aspect, an embodiment of the present invention provides a method for determining a casualty POI, including:

the method comprises the steps of obtaining a POI to be verified, and obtaining a target Wi-Fi matched with the POI according to the space-time correlation;

performing time distribution statistics on the connection quantity of the target Wi-Fi to obtain a time distribution statistical result;

and if the target Wi-Fi is determined to meet the life cycle fading condition according to the time distribution statistical result, determining the POI as a death POI.

In a second aspect, an embodiment of the present invention further provides an apparatus for determining a casualty POI, including:

the target Wi-Fi determining module is used for acquiring a POI to be verified and acquiring a target Wi-Fi matched with the POI according to the space-time correlation;

the connection quantity time distribution counting module is used for carrying out time distribution counting on the connection quantity of the target Wi-Fi to obtain a time distribution counting result;

and the casualty POI determination module is used for determining the POI as an casualty POI if the target Wi-Fi meets the fading condition of the life cycle according to the time distribution statistical result.

In a third aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and operable on the processor, where the processor executes the computer program to implement the method for determining a casual POI according to any one of the embodiments of the present invention.

In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the method for determining a disappearing POI according to any one of the embodiments of the present invention.

According to the embodiment of the invention, the LBS is used for searching the target Wi-Fi matched with the POI to be verified according to the space-time correlation, and when the target Wi-Fi is determined to meet the life cycle fading condition according to the time distribution statistical result of the connection number of the target Wi-Fi, the POI is determined to be the extinction POI, the extinction POI is determined only through the LBS service, the situation that the POI is determined through a UGC uploading mode, a PGC uploading mode and a network crawler updating mode is avoided, the problems of low efficiency, low accuracy, high cost and low coverage rate of POI maintenance in the prior art are solved, the efficiency and the accuracy of the extinction POI determination are improved, the cost of the extinction POI determination is reduced, and the coverage rate of the POI is increased.

Drawings

Fig. 1 is a flowchart of a method for determining a disappearing POI according to a first embodiment of the present invention;

fig. 2a is a flowchart of a method for determining a disappearing POI according to a second embodiment of the present invention;

FIG. 2b is a schematic diagram of a POI functional area in the second embodiment of the present invention;

fig. 3 is a schematic structural diagram of an apparatus for determining a casualty POI according to a third embodiment of the present invention;

fig. 4 is a schematic structural diagram of a computer device in the fourth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

Example one

Fig. 1 is a flowchart of a method for determining a casual POI according to a first embodiment of the present invention, which is applicable to determining whether a POI is a casual POI. The method can be executed by the casual POI determination device provided by the embodiment of the present invention, which can be implemented in software and/or hardware, and can be generally integrated in a server or a terminal device, such as a smart phone, a tablet computer, a vehicle-mounted terminal or a computer device, for providing casual POI determination services. As shown in fig. 1, the method of this embodiment specifically includes:

s110, a POI to be verified is obtained, and a target Wi-Fi matched with the POI is obtained according to the space-time correlation.

The POI may refer to a certain point on the electronic map, and is used to indicate the function represented by the point, for example, locations such as government departments, commercial establishments (gas stations, department stores, supermarkets, restaurants, hotels, or convenience stores, etc.), tourist attractions, infrastructures (parks, public toilets, hospitals, etc.), transportation facilities (stations, parking lots, or speed limit signs), and the like, which may be represented by the point, can be identified. Typically, the POI comprises at least one of: name, category, longitude, latitude, and altitude, etc.

Spatio-temporal correlation is used to evaluate the spatial, or spatial as well as temporal, relationship of POIs to Wi-Fi.

The target Wi-Fi is used to represent Wi-Fi provided where the POI is represented, illustratively, the POI is kentucky, and correspondingly, the target Wi-Fi is Wi-Fi provided by kentucky.

Specifically, determining the target Wi-Fi according to the spatio-temporal correlation may be: and at least one Wi-Fi in a set space area range determined based on the longitude and latitude information of the POI, and screening the Wi-Fi close to the POI name as a target Wi-Fi (such as Pinyin which is an abbreviation of Kendeki and is included in the name of the Wi-Fi). It can be understood that the latitude and longitude information of the POI is mapped to an electronic map provided by the LBS, so as to obtain Wi-Fi near the POI, and further filter out target Wi-Fi matched with the POI. In addition, the temporal judgment can be further performed on the basis of the judgment of the spatial relationship.

Optionally, the obtaining a target Wi-Fi matched with the POI according to the spatio-temporal correlation includes: determining a search range according to the longitude and latitude information of the POI; acquiring at least one alternative Wi-Fi included in the search range; and determining a target Wi-Fi matched with the POI in the at least one candidate Wi-Fi according to the identification information of the candidate Wi-Fi and the correlation between the identification information of the POI.

The search range is used for screening the alternative Wi-Fi, specifically, the POI is mapped to the electronic map according to latitude and longitude information of the POI, and a region matched with the POI is obtained as the search range, for example, the region matched with the POI is a circle center region with the POI as a dot and a preset length as a radius, or a unit region including the POI and divided based on streets, and other situations exist.

The alternative Wi-Fi is used to represent Wi-Fi that may be provided for a POI. And based on the longitude and latitude information of each Wi-Fi, taking the Wi-Fi positioned in the searching range as the alternative Wi-Fi.

The Wi-Fi identification information is used to identify Wi-Fi, such as the Wi-Fi name. The identification information of the POI is used to identify the POI, for example, the name of the POI. The correlation is used for evaluating the degree of closeness of correlation between the identification information of Wi-Fi and the identification information of POI. For example, comparing the characters of the identification information of the Wi-Fi with the characters of the identification information of the POI, and evaluating the correlation between the identification information of the Wi-Fi and the identification information of the POI according to whether the same characters exist, the number and the sequence of the same characters, and the like, wherein illustratively, the identification information of the POI is KFC, the identification information of the Wi-Fi is KFC0003, both of which include KFC, and the Wi-Fi is determined as the target Wi-Fi matched with the POI. In addition, there are other situations, for example, a similarity between the identification information of the Wi-Fi and the identification information of the POI is calculated as a correlation, and thus, the embodiment of the present invention is not particularly limited.

In addition, at least one alternative Wi-Fi which meets the existence time condition with the POI and is included in the searching range can be obtained. Wherein the time-to-live condition is mainly used for determining that the setup time of the finally acquired alternative Wi-Fi needs to be after the POI setup time. Indeed, if the Wi-Fi existing before the POI establishment is typically not the Wi-Fi provided by the POI. Therefore, such Wi-Fi does not serve as an alternative POI corresponding to the POI.

The method comprises the steps of determining a search range on a map according to longitude and latitude information of a POI, screening out at least one alternative Wi-Fi, and then determining a target Wi-Fi of the POI according to the correlation between identification information of the at least one alternative Wi-Fi and identification information of the POI, wherein the information can be directly obtained by LBS, so that the process of maintaining the POI is simplified, the POI is prevented from being maintained by adopting other modes such as UGC or PGC and the like, the cost of maintaining the POI is reduced, in addition, the mapping relation between the POI and the target Wi-Fi is constructed according to the space-time correlation and the similarity of the identification information, and the Wi-Fi provided by the POI can be accurately determined, so that the accuracy of judging the extinction and death of the subsequent POI.

And S120, performing time distribution statistics on the connection number of the target Wi-Fi to obtain a time distribution statistical result.

The number of connections may refer to the number of hosts connecting the target Wi-Fi. The time distribution statistics may refer to analyzing a distribution situation of the connection number in time, specifically, if no extinction of the POI occurs, in a process that the connection number changes with time, a probability of a sudden change of the connection number is low, a time interval may be set at each interval, and the connection number of the target Wi-Fi is counted once. The time distribution statistical result is used to indicate a trend of the connection number with time, and specifically may be a graph representing the trend of the connection number with time (a set time interval) as an x-axis and the connection number as a y-axis.

Optionally, the performing time distribution statistics on the connection number of the target Wi-Fi to obtain a time distribution statistical result includes: setting a time interval at intervals, acquiring a current connected host list corresponding to the target Wi-Fi, and establishing a host identification list matched with the time interval; according to the host identification list matched with the time interval and a preset time unit, counting the number of the non-overlapping hosts under each time unit as the number of connections corresponding to the time unit; and acquiring the connection quantity corresponding to at least two time units in a preset time range, and counting to obtain a time distribution statistical result.

The current connection host list is used for describing devices connected with the target Wi-Fi in the current time interval. The host identification list is used for describing the devices connected with the target Wi-Fi in the current time interval and identification information of each device. The time unit may refer to a predetermined time interval. The time lengths of the time units may be the same or different. Illustratively, the duration of a time cell in the peak period (if the POI is a restaurant, the peak period is the time range associated with breakfast, lunch, and dinner) is less than the duration of a time cell in the non-peak period. Wherein, the time unit is equal to n times of the time interval, and n is more than or equal to 1. Illustratively, the time interval is 3 hours, and the time unit may be 3 hours, half a day, or a day, etc. The non-overlapping host number refers to a connected device for which there is no duplicate statistic in the number of connections counted in units of time.

The method comprises the steps of obtaining a current connection host list corresponding to a target Wi-Fi, establishing a host identification list matched with a time interval, flexibly setting time to count the connection number of the target Wi-Fi, and meanwhile counting the number of non-overlapped hosts under each preset time unit to serve as the connection number, so that the connection number of the target Wi-Fi is accurately obtained.

S130, if the target Wi-Fi is determined to meet the life cycle fading condition according to the time distribution statistical result, determining the POI as a death POI.

The life cycle fading condition is used to evaluate whether the target Wi-Fi fades, i.e., whether the number of users using the target Wi-Fi decreases.

It can be understood that as Wi-Fi is popularized, more and more POIs are internally distributed with the Wi-Fi, wherein the number of devices connected with the Wi-Fi is used for directly depicting the vitality of the Wi-Fi and indirectly expressing the vitality of the Wi-Fi, and the vitality of the Wi-Fi is used for representing the vitality of the POIs, so that the death and death of the POIs can be depicted through the number of the Wi-Fi connections. Therefore, a mapping relation between the POI and the target Wi-Fi can be constructed according to the space-time correlation, and the extinction condition of the POI is represented by the life cycle fading condition of the target Wi-Fi.

Optionally, if it is determined that the target Wi-Fi satisfies the life cycle fading condition according to the time distribution statistical result, the method includes: if the connection number of the target Wi-Fi is smaller than a set number threshold value in at least one nearest time unit in a preset time range determined by the current system time according to the time distribution statistical result, determining that the target Wi-Fi meets a life cycle fading condition; and/or if the number average value of the connection number of the target Wi-Fi in one time unit in the at least one nearest time unit and the ratio of the maximum connection number of the target Wi-Fi in the at least one nearest time unit is smaller than a set ratio threshold value according to the time distribution statistical result, determining that the target Wi-Fi meets the life cycle fading condition.

It is understood that the number of connections of the target Wi-Fi in the latest one or more time units is less than the set number threshold; or the ratio of the number average of the connection number of the target Wi-Fi in the latest one or more time units to the maximum connection number of the target Wi-Fi is smaller than a set ratio threshold value, which indicates that the number of users connected with the target Wi-Fi is reduced, and also indicates that the vitality of the target Wi-Fi is reduced, so that the target Wi-Fi fading can be determined.

The connection number of the target Wi-Fi or the ratio of the number average value of the connection number to the maximum connection number in a time unit is counted under at least one nearest time unit in a preset time range and compared with a preset threshold value, whether the target Wi-Fi meets a life cycle fading condition or not is judged according to the utilization rate of the target Wi-Fi, and the vitality of the target Wi-Fi is accurately judged.

The disappearing POI is used to indicate that the POI disappears, and may also be understood as the function corresponding to the POI disappears. For example, if the POI is kentucky, when the kentucky, the kentucky decoration and the kentucky cannot be opened or the kentucky move, the kentucky death can be determined, that is, the POI is determined to be a death POI.

Typically, the user usage of Wi-Fi provided by the casual POI drops, i.e., the number of Wi-Fi connections decreases. Therefore, whether the POI is a death POI or not can be judged according to whether the target Wi-Fi meets the life cycle fading condition or not.

In addition, if the target Wi-Fi is determined not to meet the life cycle fading condition, that is, the POI is determined not to be a death POI, the next POI to be verified can be obtained for death judgment.

Example two

Fig. 2a is a flowchart of a car service request method in the second embodiment of the present invention, and in this embodiment, optimization is performed based on the above embodiment, and after a POI to be verified is obtained, optimization is performed as: if the target Wi-Fi matched with the POI is not successfully acquired, acquiring at least one POI description feature corresponding to the POI; inputting the at least one POI description characteristic into a pre-trained casualty POI verification model, and acquiring casualty probability output by the casualty POI verification model; and if the casualty probability meets a preset casualty threshold condition, determining the POI as a casualty POI. The method specifically comprises the following steps:

s201, POI to be verified is obtained.

In the present embodiment, the POI to be verified, the spatial-temporal correlation, the target Wi-Fi, the time distribution statistics, the life cycle fading condition, and the death POI may refer to the description of the above embodiments.

S202, judging whether the target Wi-Fi matched with the POI is successfully acquired or not according to the space-time correlation, and if so, executing S203; otherwise, S207 is executed.

S203, performing time distribution statistics on the connection number of the target Wi-Fi to obtain a time distribution statistical result.

S204, judging whether the target Wi-Fi meets a life cycle fading condition according to the time distribution statistical result, and if so, executing S205; otherwise, S206 is executed.

S205, determining the POI as a death POI.

S206, determining that the POI is not a death POI.

S207, acquiring at least one POI description characteristic corresponding to the POI.

Wherein the POI description feature is used to describe the vitality of the POI.

Optionally, the POI description features include at least one of: the method comprises the following steps of POI function area characteristics, POI surrounding people stream density and variation characteristics based on a block, POI surrounding people stream density and variation characteristics based on a grid index, POI surrounding Wi-Fi density, statistical characteristics of the number of Wi-Fi connections around the POI, POI categories, POI density around the POI, statistical characteristics of POI in a set category in a corresponding function area, and statistical characteristics of POI in the set category based on the block or the grid index.

In fact, the POI may also be used to represent a functional area, such as a business district, a square, a college, a residential district, or a technology park, which has a large area, and the POI functional area generally includes a plurality of sites, for example, as shown in fig. 2b, and a technology park includes an office building, a company enterprise, a parking lot, transportation facilities, and the like. The POI function region feature is used to describe places included in the function region, category features of the function region, and category features of each included place. The category feature is used to describe a feature that a place is distinguished from other places, and specifically may refer to a feature determined based on a Term Frequency-Inverse text Frequency index (TF-IDF) technique, where exemplary values shown in fig. 2b respectively represent category features of places, for example, a category feature value determined by an office building based on TF-IDF is 112811.586.

On an electronic map, area division is required, and the method specifically comprises the following steps: the dividing method based on the block comprises the following steps: dividing the area by taking the road as a boundary; and a partitioning method based on grid indexes: and carrying out region division by adopting a preset grid structure.

And the crowd density and the variation characteristics around the POI based on the block are used for representing the crowd density and the variation characteristics in the block unit area to which the POI belongs or in the block unit area near the POI (such as in a set distance range). The crowd density is used to indicate the number of people in a certain area, and the change characteristic is used to indicate that the number of people in a certain area changes.

And the density of people around the POI and the change characteristics based on the grid index are used for representing the density of people and the change characteristics in the grid cell area to which the POI belongs or the grid cell area near the POI.

The POI ambient Wi-Fi density is used to represent the number of Wi-Fi in the vicinity of the POI.

Statistical characterization of the number of Wi-Fi connections around the POI is used to characterize the number (e.g., mean of the number of connections) and attributes (e.g., whether Wi-Fi satisfies life cycle fading) of the number of connections for each Wi-Fi in the vicinity of the POI.

The POI category is used to represent a function of the POI, such as a restaurant, a clothing store, or a gym.

The POI density around the POI is used to indicate the number of POIs near the POI.

The statistical characteristics of the set category POI in the corresponding functional area are used to indicate the number of set category POIs in the functional area.

The statistical characteristics of the set category POI based on the block or the grid index are used to represent the quantity characteristics (such as the mean value) and the attribute characteristics (such as whether the POI is a death POI) of the set category POI in at least one unit area formed based on the block or the grid index.

By presetting a plurality of description characteristics, the characteristics of the POI can be accurately described, and the representativeness of the description characteristics can be improved, so that the identification accuracy of the casualty POI verification model is improved.

S208, inputting the at least one POI description characteristic into a pre-trained casualty POI verification model, and acquiring casualty probability output by the casualty POI verification model.

The casualty POI verification model is a machine learning model trained in advance and used for calculating casualty probability of the POI. The probability of death is used to represent the probability that a POI is a death POI. Specifically, the machine learning model may include a support vector machine, a decision tree, a Gradient boosting decision tree (Gradient boosting trees), or a neural network.

S209, judging whether the death probability meets a preset death threshold condition, if so, executing S205; otherwise, S206 is executed.

The death threshold condition is used to determine whether the POI is a specific probability value of the death POI, for example, 80% or 90%.

Optionally, before the inputting the at least one POI description feature into the pre-trained extinction POI verification model, the method further includes: acquiring at least one disappeared POI; acquiring at least one POI description characteristic respectively corresponding to each disappeared POI; inputting the disappeared POI and the corresponding at least one POI description characteristic into a standard machine learning model to train the standard machine learning model, and obtaining the disappeared POI verification model.

Specifically, the disappeared POI and the corresponding at least one POI description feature are used as training samples, and the standard machine learning model is trained to obtain the disappeared POI verification model. The deleted POI may refer to a POI to which a deleted tag is attached, and tag data of the POI may be acquired by a PGC or UGC method. Specifically, the method based on PGC or UGC may acquire the change data of the POI by day, and the change data of the POI is referred to as POI snapshot for short. Generating tag data for POI death may be implemented based on the POI snapshot. And training to obtain a casualty POI verification model by taking the casualty POI and the corresponding at least one POI description characteristic as training samples, so that the calculation accuracy of the casualty POI verification model is improved.

According to the embodiment of the invention, when the target Wi-Fi provided by the POI is determined not to be searched, the casualty judgment of the POI is realized by adopting the casualty POI verification model, so that the accuracy of POI casualty judgment is improved, the labor cost is reduced, and the efficiency of POI casualty judgment is improved.

EXAMPLE III

Fig. 3 is a schematic structural diagram of an apparatus for determining a casualty POI according to a third embodiment of the present invention, and as shown in fig. 3, the apparatus specifically includes:

the target Wi-Fi determining module 310 is used for acquiring a POI to be verified and acquiring a target Wi-Fi matched with the POI according to the time-space correlation;

the connection quantity time distribution statistics module 320 is configured to perform time distribution statistics on the connection quantity of the target Wi-Fi to obtain a time distribution statistical result;

a casualty POI determining module 330, configured to determine the POI as a casualty POI if it is determined that the target Wi-Fi satisfies a life cycle fading condition according to the time distribution statistical result.

Further, the target Wi-Fi determining module 310 may be specifically configured to: determining a search range according to the longitude and latitude information of the POI; acquiring at least one alternative Wi-Fi included in the search range; and determining a target Wi-Fi matched with the POI in the at least one candidate Wi-Fi according to the identification information of the candidate Wi-Fi and the correlation between the identification information of the POI.

Further, the connection quantity time distribution statistical module 320 may be specifically configured to: setting a time interval at intervals, acquiring a current connected host list corresponding to the target Wi-Fi, and establishing a host identification list matched with the time interval; according to the host identification list matched with the time interval and a preset time unit, counting the number of the non-overlapping hosts under each time unit as the number of connections corresponding to the time unit; and acquiring the connection quantity corresponding to at least two time units in a preset time range, and counting to obtain a time distribution statistical result.

Further, the casual POI determination module 330 may be specifically configured to: if the connection number of the target Wi-Fi is smaller than a set number threshold value in at least one nearest time unit in a preset time range determined by the current system time according to the time distribution statistical result, determining that the target Wi-Fi meets a life cycle fading condition; and/or if the ratio of the number average of the connection number of the target Wi-Fi in the at least one nearest time unit to the maximum connection number of the target Wi-Fi in one time unit is smaller than a set ratio threshold according to the time distribution statistical result, determining that the target Wi-Fi meets the life cycle fading condition.

Further, the apparatus for determining a casualty POI may further include: the POI description feature acquisition unit is used for acquiring at least one POI description feature corresponding to the POI if the target Wi-Fi matched with the POI is not successfully acquired after the POI to be verified is acquired; the casualty POI verification model input unit is used for inputting the at least one POI description characteristic into a pre-trained casualty POI verification model and acquiring casualty probability output by the casualty POI verification model; and the casualty POI determination unit is used for determining the POI as an casualty POI if the casualty probability meets a preset casualty threshold value condition.

Further, the apparatus for determining a casualty POI may further include: the casualty POI verification model training unit is used for acquiring at least one casualty POI before the at least one POI description characteristic is input into a pre-trained casualty POI verification model; acquiring at least one POI description characteristic respectively corresponding to each disappeared POI; inputting the disappeared POI and the corresponding at least one POI description characteristic into a standard machine learning model to train the standard machine learning model, and obtaining the disappeared POI verification model.

Further, the POI description feature may include at least one of: the method comprises the following steps of POI function area characteristics, POI surrounding people stream density and variation characteristics based on a block, POI surrounding people stream density and variation characteristics based on a grid index, POI surrounding Wi-Fi density, statistical characteristics of the number of Wi-Fi connections around the POI, POI categories, POI density around the POI, statistical characteristics of POI in a set category in a corresponding function area, and statistical characteristics of POI in the set category based on the block or the grid index.

The device for determining the death POI can execute the method for determining the death POI provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executed method for determining the death POI.

Example four

Fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention. FIG. 4 illustrates a block diagram of an exemplary computer device 412 suitable for use in implementing embodiments of the present invention. The computer device 412 shown in FIG. 4 is only one example and should not impose any limitations on the functionality or scope of use of embodiments of the present invention.

As shown in FIG. 4, computer device 412 is in the form of a general purpose computing device. Components of computer device 412 may include, but are not limited to: one or more processors or processing units 416, a system memory 428, and a bus 418 that couples the various system components including the system memory 428 and the processing unit 416. The computer device 412 may be an in-vehicle device.

Bus 418 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

Computer device 412 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computer device 412 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 428 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)430 and/or cache memory 432. The computer device 412 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 434 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, commonly referred to as a "hard drive"). Although not shown in FIG. 4, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk Read-Only Memory (CD-ROM), Digital Video disk (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 418 by one or more data media interfaces. Memory 428 can include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.

A program/utility 440 having a set (at least one) of program modules 442 may be stored, for instance, in memory 428, such program modules 442 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. The program modules 442 generally perform the functions and/or methodologies of the described embodiments of the invention.

The computer device 412 may also communicate with one or more external devices 414 (e.g., keyboard, pointing device, display 424, etc.), with one or more devices that enable a user to interact with the computer device 412, and/or with any devices (e.g., network card, modem, etc.) that enable the computer device 412 to communicate with one or more other computing devices. Such communication may be through an Input/Output (I/O) interface 422. Further, computer device 412 may also communicate with one or more networks (e.g., Local Area Network (LAN), Wide Area Network (WAN)) through Network adapter 420 As shown, Network adapter 420 communicates with other modules of computer device 412 through bus 418, it should be understood that although not shown in FIG. 4, other hardware and/or software modules may be used in conjunction with computer device 412, including without limitation, microcode, device drivers, Redundant processing units, external disk drive Arrays, Redundant Arrays of Inesponsive Disks, RAID systems, tape drives, data backup storage systems, and the like.

The processing unit 416 executes programs stored in the system memory 428 to perform various functional applications and data processing, such as implementing a method for determining a disappearing POI provided by embodiments of the present invention.

That is, the processing unit implements, when executing the program: the method comprises the steps of obtaining a POI to be verified, and obtaining a target Wi-Fi matched with the POI according to the space-time correlation; performing time distribution statistics on the connection quantity of the target Wi-Fi to obtain a time distribution statistical result; and if the target Wi-Fi is determined to meet the life cycle fading condition according to the time distribution statistical result, determining the POI as a death POI.

EXAMPLE five

The fifth embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for determining a casualty POI provided in all the embodiments of the present invention: the method comprises the steps of obtaining a POI to be verified, and obtaining a target Wi-Fi matched with the POI according to the space-time correlation; performing time distribution statistics on the connection quantity of the target Wi-Fi to obtain a time distribution statistical result; and if the target Wi-Fi is determined to meet the life cycle fading condition according to the time distribution statistical result, determining the POI as a death POI.

Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a RAM, a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), a flash Memory, an optical fiber, a portable CD-ROM, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, Radio Frequency (RF), etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a LAN or a WAN, or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining a casual POI, comprising:

if the target Wi-Fi is determined to meet the life cycle fading condition according to the time distribution statistical result, determining the POI as a death POI; the life cycle fading condition is used to evaluate whether the number of users using the target Wi-Fi is reduced.

2. The method of claim 1, wherein obtaining a target Wi-Fi matching the POI according to the spatiotemporal correlation comprises:

determining a search range according to the longitude and latitude information of the POI;

acquiring at least one alternative Wi-Fi included in the search range;

and determining a target Wi-Fi matched with the POI in the at least one candidate Wi-Fi according to the identification information of the candidate Wi-Fi and the correlation between the identification information of the POI.

3. The method of claim 1, wherein the performing time distribution statistics of the number of connections to the target Wi-Fi to obtain time distribution statistics comprises:

setting a time interval at intervals, acquiring a current connected host list corresponding to the target Wi-Fi, and establishing a host identification list matched with the time interval;

according to the host identification list matched with the time interval and a preset time unit, counting the number of the non-overlapping hosts under each time unit as the number of connections corresponding to the time unit;

and acquiring the connection quantity corresponding to at least two time units in a preset time range, and counting to obtain a time distribution statistical result.

4. The method of claim 1, wherein if it is determined from the time distribution statistics that the target Wi-Fi satisfies a life cycle fading condition, comprising:

if the connection number of the target Wi-Fi is smaller than a set number threshold value in at least one nearest time unit in a preset time range determined by the current system time according to the time distribution statistical result, determining that the target Wi-Fi meets a life cycle fading condition; and/or

And if the ratio of the number average of the connection number of the target Wi-Fi in the at least one nearest time unit to the maximum connection number of the target Wi-Fi in one time unit is smaller than a set ratio threshold according to the time distribution statistical result, determining that the target Wi-Fi meets the life cycle fading condition.

5. The method of claim 1, after obtaining the POI to be verified, further comprising:

if the target Wi-Fi matched with the POI is not successfully acquired, acquiring at least one POI description feature corresponding to the POI;

inputting the at least one POI description characteristic into a pre-trained casualty POI verification model, and acquiring casualty probability output by the casualty POI verification model;

and if the casualty probability meets a preset casualty threshold condition, determining the POI as a casualty POI.

6. The method of claim 5, further comprising, prior to inputting the at least one POI description feature into a pre-trained extinction POI verification model:

acquiring at least one disappeared POI;

acquiring at least one POI description characteristic respectively corresponding to each disappeared POI;

inputting the disappeared POI and the corresponding at least one POI description characteristic into a standard machine learning model to train the standard machine learning model, and obtaining the disappeared POI verification model.

7. The method of claim 6, wherein the POI description features comprise at least one of:

the method comprises the following steps of POI function area characteristics, POI surrounding people stream density and variation characteristics based on a block, POI surrounding people stream density and variation characteristics based on a grid index, POI surrounding Wi-Fi density, statistical characteristics of the number of Wi-Fi connections around the POI, POI categories, POI density around the POI, statistical characteristics of POI in a set category in a corresponding function area, and statistical characteristics of POI in the set category based on the block or the grid index.

8. An apparatus for determining a casual POI, comprising:

the casualty POI determination module is used for determining the POI as an casualty POI if the target Wi-Fi meets the life cycle fading condition according to the time distribution statistical result; the life cycle fading condition is used to evaluate whether the number of users using the target Wi-Fi is reduced.

9. A computer device, characterized in that the computer device comprises:

one or more processors;

storage means for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement a method of determining a casual POI as defined in any one of claims 1-7.

10. A storage medium on which a computer program is stored which, when being executed by a processor, carries out a method of determining a casual POI according to any one of claims 1 to 7.