CN116738073B - Residence identification methods, equipment and storage media - Google Patents

Abstract

This application provides a permanent location identification method, equipment and storage medium. This method determines the first stay points included in the second time period and merges multiple identical first stay points into one second stay point based on neighbor clustering, thereby ensuring the stay in each second time period. The points are all unique, giving each stay point actual physical meaning in the clustering process, thereby ensuring that the same second stay point in the first time period is finally clustered into a cluster based on the nearest neighbor clustering method. , for any cluster, each second stay point represents the number of days the user has appeared in the cluster. In this way, according to the needs of different business scenarios, different stay points can be selected by setting different days thresholds. As the resident location in this business scenario, users can be provided with more colorful services based on the identified resident location.

Description

Residence identification methods, equipment and storage media

Technical field

The present application relates to the field of data processing technology, and in particular to a resident identification method, equipment and storage medium.

Background technique

In recent years, with the development of mobile Internet and the continuous improvement of residents' living standards, mobile terminal smart devices such as mobile phones have become an indispensable part of people's lives. In order to provide users with a better user experience, current mobile Internet applications can provide users with richer personalized services by sensing the user's situation. Based on the resident’s behavioral habits, make refined recommendations.

The permanent residence is usually determined based on the user's stay points, so how to process the user's stay points to accurately identify the user's permanent residence is particularly urgent.

Contents of the invention

In order to solve the above technical problems, this application provides a permanent residence identification method, equipment and storage medium, by using the clustering method of nearest neighbor clustering to cluster the user's stay points, and at the same time, the stay points of each day are clustered. The merging process gives each stay point its actual physical meaning in the clustering process, thereby making the resident place identified based on the processed stay points more accurate.

In the first aspect, this application provides a permanent residence identification method. The method includes: obtaining signaling data recorded by an electronic device used by a user in a first time period, where the first time period includes at least one second time period; for each second time period, according to the signaling data of the second time period , determine the user's first stay point in the second time period; for each second time period, based on the clustering method of neighbor clustering, merge the first stay points in the second time period to obtain the second stay point ; Based on the clustering method of nearest neighbor clustering, the same second stay points in the first time period are clustered into a cluster; for each cluster, when the number of second stay points in the cluster satisfies the set When the requirements are determined, the second stay point in the cluster is determined as the first permanent place.

Therefore, by determining the first stay points included in the second time period and merging multiple identical first stay points into one second stay point based on neighbor clustering, it is thus ensured that the first stay points in each second time period are All stay points are unique, giving each stay point actual physical meaning in the clustering process, thereby ensuring that the same second stay point in the first time period is finally clustered into a cluster based on the nearest neighbor clustering method. Finally, for any cluster, each second stay point represents the number of days the user has appeared in the cluster. In this way, according to the needs of different business scenarios, different days thresholds can be set to select different The stay point serves as the resident place in this business scenario, so that users can be provided with more colorful services based on the identified resident place.

According to the first aspect, for each second time period, determining the user's first stay point in the second time period according to the signaling data of the second time period includes: for each second time period, determining the second time The distance between the spatial positions corresponding to each two pieces of signaling data in the segment; for each spatial position, when there is a spatial position whose distance from the spatial position meets the set first distance threshold, it is determined that the electronic device is in the space The position and the distance between the spatial position and the spatial position satisfy the set first distance threshold. The dwell time of the spatial position; when the dwell time satisfies the set time threshold, the spatial position and the distance between the spatial position and the spatial position satisfy the set first distance threshold. The spatial position of the first distance threshold is determined as a first stay point.

Thus, the determination of all stay points of the user using the electronic device in each second time period is achieved.

According to the first aspect, or any implementation of the above first aspect, after determining the distance between the spatial positions corresponding to each two pieces of signaling data in the second time period, the method further includes: for each spatial position, When there is a spatial position whose distance from the spatial position satisfies the set second distance threshold, the spatial position and the spatial position whose distance from the spatial position satisfies the set second distance threshold are merged into one merged spatial position. , the second distance threshold is smaller than the first distance threshold.

As a result, the amount of subsequent data processing is reduced by merging multiple spatial locations that are gathered together into one spatial location.

According to the first aspect, or any implementation of the above first aspect, for each merged spatial position, calculate the average longitude and the average latitude based on the longitude and latitude information of each spatial position included in the merged spatial position; add the average longitude and Average latitude, as the latitude and longitude information of the combined spatial location.

Therefore, by averaging the longitude and latitude of multiple spatial locations included in the merged spatial location, the average longitude and average latitude are used as the longitude and latitude information corresponding to the merged spatial location, thereby facilitating subsequent data processing.

According to the first aspect, or any implementation of the above first aspect, for each second time period, the first stay points in the second time period are merged based on the clustering method of nearest neighbor clustering to obtain the second time period. The second stay point includes: for each second time period, determine the distance between every two first stay points in the second time period; for each first stay point, based on the clustering method of nearest neighbor clustering, The first stay point and the first stay point whose distance from the first stay point meets the set third distance threshold are combined into a second stay point.

Therefore, based on the clustering method of nearest neighbor clustering, according to the above processing logic, multiple identical first stay points included in each second time period can be merged into one second stay point, ensuring the final merging process. The last plurality of second stopping points are all different stopping points.

According to the first aspect, or any implementation of the above first aspect, for each second time period, determining the distance between every two first stay points in the second time period includes: for each second time period For each first stay point in the time period, calculate the average longitude and average latitude based on the longitude and latitude information of each spatial location included in the first stay point; use the average longitude and average latitude as the longitude and latitude information of the first stay point; For each second time period, the distance between each two first stay points is determined based on the latitude and longitude information of each two first stay points.

Therefore, by averaging the longitude and latitude of multiple spatial locations included in the first stay point, the average longitude and average latitude are used as the longitude and latitude information corresponding to the first stay point, thereby facilitating subsequent data processing.

According to the first aspect, or any implementation of the first aspect above, after obtaining the second stay point, the method further includes: for each second stay point, determining the first latitude and longitude information extraction location corresponding to the second stay point. and the second latitude and longitude information extraction bit; arrange the spatial locations included in the second stop point in order, extract the first longitude and first latitude of the spatial location of the first longitude and latitude information extraction bit, and the second longitude and latitude information extraction bit The second longitude and second latitude of the spatial location; determine the longitude retention interval based on the first longitude and the second longitude; determine the latitude retention interval based on the first latitude and the second latitude; eliminate the longitude in the second stay point that is not retained in the longitude interval, and the latitude is not in the spatial position of the latitude-preserved interval.

According to the first aspect, or any implementation of the above first aspect, determining the first longitude and latitude information extraction bit and the second longitude and latitude information extraction bit corresponding to the second stay point includes: determining the spatial position included in the second stay point The number; determine the first middle digit according to the quantity; determine the middle digit between the first middle digit and the first middle digit as the first latitude and longitude information extraction position corresponding to the second stay point; determine the first middle digit and the last digit. The intermediate bit between is determined as the second longitude and latitude information extraction bit corresponding to the second stay point.

According to the first aspect, or any implementation of the first aspect above, the longitude retention interval is [first longitude-1.5*(second longitude-first longitude), second longitude+1.5*(second longitude) - first longitude)]; the latitude retention interval is [first latitude-1.5*(second latitude-first latitude), second latitude+1.5*(second latitude-first latitude)].

According to the first aspect, or any implementation of the above first aspect, for each second time period, the first stay points in the second time period are merged based on the clustering method of nearest neighbor clustering to obtain the second time period. Two stay points include: for each second time period, when there is one first stay point in the second time period, the first stay point is regarded as the corresponding second stay point.

According to the first aspect, or any implementation manner of the first aspect above, clustering the same second stay points in the first time period into a cluster cluster based on the clustering method of neighbor clustering, including: determining the first Within a period of time, the distance between every two second stay points; for each second stay point, based on the clustering method of nearest neighbor clustering, the second stay point and the distance between the second stay point and the second stay point are The second stay points that meet the set fourth distance threshold are clustered into a cluster. The fourth distance threshold is smaller than the third distance threshold. The third distance threshold is used to indicate multiple first points in each second time period. Whether the stop points can be combined into a second stop point.

Therefore, the clustering method based on nearest neighbor clustering clusters all the same second stay points in the first time period into a cluster, and gives each second stay point a physical meaning in the cluster, that is, In the process of determining the resident location, for any cluster, each second stay point represents the number of days the user has appeared in the cluster. In this way, according to the needs of different business scenarios, different days can be set By setting the threshold, different stay points can be selected as permanent residences in this business scenario, thereby providing users with more colorful services based on the identified permanent residences.

According to the first aspect, or any implementation of the first aspect above, determining the distance between every two second stay points within the first time period includes: for each second stay point, according to the second stay point For the longitude and latitude information of each first stay point corresponding to the point, calculate the average longitude and average latitude; use the average longitude and average latitude as the longitude and latitude information of the second stay point; based on the longitude and latitude information of each two second stay points, determine each The distance between two second stop points.

Therefore, by averaging the longitudes and latitudes of multiple first stay points included in the second stay point, the average longitude and average latitude are used as the longitude and latitude information corresponding to the second stay point, thereby facilitating subsequent data processing.

According to the first aspect, or any implementation of the above first aspect, after determining the second stay point in the cluster as the first resident place, the method further includes: A first resident place is assigned a resident tag; after determining the second resident place in the third time period based on the signaling data recorded in the third time period in a distance manner based on neighbor clustering, for each second resident place Resident place, determine the distance between the second permanent place and each first permanent place, the third time period is the same as the first time period; for each second permanent place, when there is a When the distance between the resident places meets the set fifth distance threshold for the first resident place, the second resident place is assigned the same resident place tag as the first resident place.

As a result, the uniqueness of the resident location is determined, so that subsequent service recommendation services based on the resident location can be better suited to users.

In a second aspect, the present application provides an electronic device. The electronic device includes: a memory and a processor, the memory and the processor are coupled; the memory stores program instructions, and when the program instructions are executed by the processor, the electronic device executes the first aspect or any possible implementation of the first aspect. method instructions.

The second aspect and any implementation manner of the second aspect respectively correspond to the first aspect and any implementation manner of the first aspect. The technical effects corresponding to the second aspect and any implementation manner of the second aspect may be referred to the technical effects corresponding to the above-mentioned first aspect and any implementation manner of the first aspect, which will not be described again here.

In a third aspect, the present application provides a computer-readable medium for storing a computer program, the computer program comprising instructions for performing a method in the first aspect or any possible implementation of the first aspect.

The third aspect and any implementation manner of the third aspect respectively correspond to the first aspect and any implementation manner of the first aspect. For the technical effects corresponding to the third aspect and any implementation manner of the third aspect, please refer to the technical effects corresponding to the above-mentioned first aspect and any implementation manner of the first aspect, which will not be described again here.

In a fourth aspect, the present application provides a computer program, the computer program comprising instructions for performing a method in the first aspect or any possible implementation of the first aspect.

The fourth aspect and any implementation manner of the fourth aspect respectively correspond to the first aspect and any implementation manner of the first aspect. For the technical effects corresponding to the fourth aspect and any implementation manner of the fourth aspect, please refer to the technical effects corresponding to the above-mentioned first aspect and any implementation manner of the first aspect, which will not be described again here.

In a fifth aspect, this application provides a chip, which includes a processing circuit and transceiver pins. Wherein, the transceiver pin and the processing circuit communicate with each other through an internal connection path, and the processing circuit executes the method in the first aspect or any possible implementation of the first aspect to control the receiving pin to receive the signal, so as to Control the sending pin to send signals.

The fifth aspect and any implementation manner of the fifth aspect respectively correspond to the first aspect and any implementation manner of the first aspect. For the technical effects corresponding to the fifth aspect and any implementation manner of the fifth aspect, please refer to the technical effects corresponding to the above-mentioned first aspect and any implementation manner of the first aspect, which will not be described again here.

Description of drawings

Figure 1a is a schematic diagram illustrating the use of different target applications in a permanent location;

Figure 1b is a schematic diagram illustrating the use of different target applications in another permanent location;

Figure 2a is one of the schematic diagrams illustrating service recommendation based on residence and user behavior habits;

Figure 2b is a second schematic diagram illustrating service recommendation based on residence and user behavior habits;

Figure 3 is a schematic diagram of the hardware structure of an exemplary mobile phone;

Figure 4 is a schematic diagram of the software structure of an exemplary mobile phone;

Figures 5a and 5b are schematic diagrams of the user interface for activating the resident location identification function;

Figures 6a to 6e are schematic diagrams illustrating the generation of stay points on the day;

Figure 7 is an exemplary combined schematic diagram of multiple identical stay points on the day;

Figure 8 is a schematic diagram illustrating the elimination of abnormal points during the merging process of multiple identical stay points on the same day;

Figure 9 is a schematic diagram illustrating a schematic diagram of performing neighbor clustering on N-day stay points to determine a permanent place;

Figure 10 is a schematic flowchart of an exemplary method for identifying a resident place;

Figure 11 is a schematic flow chart of the determination of the first stay point in the method of identifying a resident place;

Figure 12 is a schematic flowchart illustrating the merging of the first stay point into the second stay point in the resident place identification method;

Figure 13 is a schematic flowchart of the elimination of abnormal spatial locations in the resident location identification method;

Figure 14 is a schematic flowchart of determining the resident place based on the second stay point in the exemplary resident place identification method;

FIG. 15 is a schematic flowchart of determining the uniqueness of the resident place in the resident place identification method.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

The term "and/or" in this article is just an association relationship that describes related objects, indicating that three relationships can exist. For example, A and/or B can mean: A exists alone, A and B exist simultaneously, and they exist alone. B these three situations.

The terms “first” and “second” in the description and claims of the embodiments of this application are used to distinguish different objects, rather than to describe a specific order of objects. For example, the first target object, the second target object, etc. are used to distinguish different target objects, rather than to describe a specific order of the target objects.

In the embodiments of this application, words such as "exemplary" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "such as" in the embodiments of the present application is not to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the words "exemplary" or "such as" is intended to present the concept in a concrete manner.

In the description of the embodiments of this application, unless otherwise specified, the meaning of “plurality” refers to two or more. For example, multiple processing units refer to two or more processing units; multiple systems refer to two or more systems.

Before describing the technical solutions of the embodiments of the present application, the application scenarios of the embodiments of the present application are first described with reference to the drawings. For the convenience of description, the following scenario description takes the target applications that need to be recommended as target application 1 and target application 2 as examples. In the station, the usage of each time period within N days is explained.

Referring to Figure 1a, for example, within N days, such as 8 days, the time periods during which a certain user, such as user A, uses the target application 1 installed in the mobile phone at the residence 1 are respectively the t1 time period and the t8~t12 time period. The time periods for using target application 2 are t2 time period, t4 time period, t5 time period and t7 time period respectively.

Continuing to refer to Figure 1a, for example, within these 8 days, user A will use target application 1 during the time period t9 to t11 of each day, and user A will use target application 2 during the time period t5 of each day. Among these 8 days, target application 1 will be used in the t1 time period and t8 time period in 1 day, target application 2 will be used in the t2 time period in 2 days, and target application 2 and t12 will be used in the t7 time period in 3 days. Target application 1 will be used in the time period, and target application 2 will be used in the t4 time period of 5 days.

That is, when user A is at his residence 1, he prefers to use target application 1 in the time period t8 to t12, and uses target application 2 in the time period t4 and t5. Therefore, content related to target application 1 is recommended before and after the t8~t12 time period, or during the t8~t12 time period, which is easier for users to access, while it is easier for users to recommend content before and after the t4 time period, t5 time period, or between the t4 time period and the t5 time period. Recommend content related to target application 2, which is easier for users to access.

Referring to Figure 1b, for example, still taking N days as 8 days as an example, the situation where the same user A uses the above-mentioned target application 1 and target application 2 in the resident place 2 is as follows: in the t2 time period, t4~ Target application 1 is used in the t7 time period, t10 time period, and t11 time period, and target application 2 is used in the t1 time period and t8 time period.

Continuing to refer to Figure 1b, for example, within these 8 days, the user will use target application 1 in the t5 time period on 7 days, use the target application 1 in the t4 time period on 5 days, and use the target application 2 in the t8 time period. There are 4 days when target application 1 will be used in the t10 time period, 2 days when the target application 2 will be used in the t1 time period, target application 1 will be used in the t6 time period and t11 time period, and one day will be used in the t2 time period. 1.

That is, when user A is in his resident place 2, he prefers to use target application 1 in the time period t4~t7 and time period t10~t11, and to use target application 2 in the time period t8. Therefore, content related to target application 1 is recommended before and after the t4~t7 time period, t10~t11 time period, or between the t4~t7 time period, t10~t11 time period, and is easier to be accessed by users, while before and after the t8 time period, Or recommend content related to target application 2 in the t8 time period, which is easier for users to access.

It should be understood that the above description is only an example for a better understanding of the technical solution of this embodiment, and is not the only limitation on this embodiment.

Regarding the above-mentioned implementation method of recommending relevant content corresponding to the target application before and after the time period that user A prefers, or within the time period, as shown in Figure 1a below, user A likes to use the target application in the resident place 1. The time period 1 is the t9~t12 time period as an example, and some feasible recommendation methods will be explained.

For example, assuming that the target application 1 is a game, such as the backgammon game, when user A uses the target application 1 for a long period of time, such as in the time period t9~t2 in Figure 1a, in some implementations In this method, content related to target application 1 can be recommended in advance a few minutes before the t9 time period, such as 1 minute. As shown in Figure 2a, an exemplary scenario is shown in which user A does not use the mobile phone 100 a few minutes before the time period t9. In this case, the mobile phone 100 can be in the interface shown in 10a, for example.

Continuing to refer to Figure 2a, for example, the current time is close to the t9 time period. If the target application 1 has a new game mode online, in order to remind the user A to experience it in time, the notification center 10-a of the interface 10a can display the information related to the target application 1. The relevant content is shown in 10a-11 in Figure 2a. In this way, when user A opens the target application 1 installed in the mobile phone 100, he can view the new game mode in time.

It should be understood that the above description is only an example for a better understanding of the technical solution of this embodiment, and is not the only limitation on this embodiment.

For example, the target application 1 is still used as a game, such as the backgammon game. When user A uses the target application 1 for a long period of time, such as in the time period t9~t2 in Figure 1a, in some implementations In the implementation method, content related to target application 1 can be recommended at any time during the time period t9~t2. As shown in Figure 2b, an exemplary scenario is shown in which user A is using target application 1 to play backgammon during the time period t9~t2. The specific interface may be, for example, the interface 10b in 2b, where the interface 10b may include One or more controls, such as the chessboard 10b-1, the control 10b-2 for exiting the interface 10b, the control 10b-3 for regretting the move, the control 10b-4 for replaying, and the control 10b-4 for entering the settings of sound effects and placement methods. Interface controls 10b-5.

Continuing to refer to Figure 2b, for example, during the time period t9~t2, if the target application 1 has a new game mode online, in order to remind user A to experience it in time, the message notification bar 10b-6 can be popped up directly on the interface 10b, and Content related to target application 1 is displayed in the message notification bar 10-6, such as "Target application 1 has a new game mode online, welcome to experience it~". In this way, user A can directly enter the interface for selecting a game mode or the interface corresponding to a new game mode by clicking on the control 10b-6 while using the target application 1 on the interface 10b, thereby experiencing the game mode for the first time.

It should be understood that the above description is only an example for a better understanding of the technical solution of this embodiment, and is not intended to be the only limitation on this embodiment.

From the above description of the scenarios shown in Figures 1a to 2b, it can be seen that by identifying the different residences where the user is located, and further counting the usage of different target applications by the users in different residences during different time periods, it is possible to Different permanent locations and different time periods recommend content related to different target applications to users, thereby better providing users with richer personalized services.

In addition, it can be understood that in the above scenario description, a mobile phone is used as an example. In practical applications, the resident identification method provided by this application is also applicable to tablet computers, smart wearable devices, etc. that can obtain signaling. Data, and electronic equipment with processing capabilities.

In order to better describe the permanent location identification method provided by the embodiment of the present application, the mobile phone is still used as an example. The hardware structure and software structure of the mobile phone will be described below with reference to Figures 3 and 4, and then with Figures 5a to 5a. 9. Describe the process of implementing the resident location identification method provided by the embodiment of the present application on a mobile phone based on the hardware structure and software structure.

Refer to FIG. 3 , which is a schematic diagram of the hardware structure of a mobile phone 100 that implements the resident location identification method provided by an embodiment of the present application.

Referring to Figure 3, the mobile phone 100 may include: a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, and an antenna. 1. Antenna 2, mobile communication module 150, wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone interface 170D, sensor module 180, button 190, motor 191, indicator 192, camera 193, display Screen 194, and subscriber identification module (subscriber identification module, SIM) card interface 195, etc.

Exemplarily, in some implementations, the sensor module 180 may include a pressure sensor, a gyroscope sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a distance sensor, a proximity light sensor, a fingerprint sensor, a temperature sensor, a touch sensor, and an ambient light sensor. , bone conduction sensors, etc., will not be listed one by one here, and this application does not limit this.

In addition, it should be noted that the processor 110 may include one or more processing units. For example, the processor 110 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), image signal processor (ISP), controller, memory, video codec, digital signal processor (DSP), baseband processor, and/or neural network processor (neural network processor) -network processing unit, NPU), etc. Among them, different processing units can be independent devices or integrated in one or more processors.

It is understandable that the controller can be the nerve center and command center of the mobile phone 100 . In practical applications, the controller can generate operation control signals based on the instruction operation code and timing signals to complete the control of fetching and executing instructions.

In addition, it should be noted that the processor 110 may also be provided with a memory for storing instructions and data. In some implementations, the memory in processor 110 is cache memory. This memory may hold instructions or data that have been recently used or recycled by processor 110 . If the processor 110 needs to use the instructions or data again, it can be called directly from the memory. Repeated access is avoided and the waiting time of the processor 110 is reduced, thus improving the efficiency of the system.

By way of example, in some implementations, processor 110 may include one or more interfaces. Interfaces may include integrated circuit (inter-integrated circuit, I2C) interface, integrated circuit built-in audio (inter-integrated circuit sound, I2S) interface, pulse code modulation (PCM) interface, universal asynchronous receiver and transmitter (universal asynchronous receiver/transmitter (UART) interface, mobile industry processor interface (MIPI), general-purpose input/output (GPIO) interface, subscriber identity module (SIM) interface, and/ Or universal serial bus (USB) interface, etc.

Continuing to refer to FIG. 3 , the charging management module 140 is illustratively configured to receive charging input from a charger. Among them, the charger can be a wireless charger or a wired charger. In some wired charging implementations, the charging management module 140 may receive charging input from the wired charger through the USB interface 130 . In some wireless charging implementations, the charging management module 140 may receive wireless charging input through the wireless charging coil of the mobile phone 100 . While the charging management module 140 charges the battery 142, it can also provide power to the electronic device through the power management module 141.

Continuing to refer to FIG. 3 , as an example, the power management module 141 is used to connect the battery 142 , the charging management module 140 and the processor 110 . The power management module 141 receives input from the battery 142 and/or the charging management module 140, and supplies power to the processor 110, internal memory 121, external memory, display screen 194, camera 193, wireless communication module 160, etc. The power management module 141 can also be used to monitor battery capacity, battery cycle times, battery health status (leakage, impedance) and other parameters. In some other implementations, the power management module 141 may also be provided in the processor 110 . In other implementations, the power management module 141 and the charging management module 140 can also be provided in the same device.

Continuing to refer to FIG. 3 , for example, the wireless communication function of the mobile phone 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor.

It should be noted that antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in mobile phone 100 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example: Antenna 1 can be reused as a diversity antenna for a wireless LAN. In other implementations, the antenna can be used in conjunction with a tuning switch.

Continuing to refer to FIG. 3 , as an example, the mobile communication module 150 can provide a solution for wireless communication including 2G/3G/4G/5G applied on the mobile phone 100 . The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves through the antenna 1, perform filtering, amplification and other processing on the received electromagnetic waves, and transmit them to the modem processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modem processor and convert it into electromagnetic waves through the antenna 1 for radiation. In some implementations, at least part of the functional modules of the mobile communication module 150 may be disposed in the processor 110 . In some implementations, at least part of the functional modules of the mobile communication module 150 and at least part of the modules of the processor 110 may be provided in the same device.

In addition, it should be noted that the modem processor may include a modulator and a demodulator. Among them, the modulator is used to modulate the low-frequency baseband signal to be sent into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After the low-frequency baseband signal is processed by the baseband processor, it is passed to the application processor. The application processor outputs sound signals through audio devices (not limited to speaker 170A, receiver 170B, etc.), or displays images or videos through display screen 194. In some implementations, the modem processor may be a stand-alone device. In other implementations, the modem processor may be independent of the processor 110 and may be provided in the same device as the mobile communication module 150 or other functional modules.

Continuing to refer to FIG. 3 , by way of example, the wireless communication module 160 can provide a wireless local area network (WLAN) (such as a wireless fidelity (Wifi) network), Bluetooth (bluetooth, etc.) applied on the mobile phone 100 . BT), global satellite navigation system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR) and other wireless communication solutions. The wireless communication module 160 may be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2 , frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 110 . The wireless communication module 160 can also receive the signal to be sent from the processor 110, frequency modulate it, amplify it, and convert it into electromagnetic waves through the antenna 2 for radiation.

Specifically, in the technical solutions provided by the embodiments of this application, the mobile phone 100 can communicate with the Global Positioning System (GPS) and/or the accessed base station through the mobile communication module 150 or the wireless communication module 160 to obtain information that can be determined. Signaling data of user movement trajectory. The description of obtaining signaling data and the specific content included in the signaling data is detailed below and will not be described again here.

In addition, it should be noted that the mobile phone 100 implements the display function through the GPU, the display screen 194, and the application processor. The GPU is an image processing microprocessor and is connected to the display screen 194 and the application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. Processor 110 may include one or more GPUs that execute program instructions to generate or alter display information.

Continuing to refer to FIG. 3 , illustratively, the display screen 194 is used to display images, videos, etc. Display 194 includes a display panel. The display panel can use a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active matrix organic light emitting diode or an active matrix organic light emitting diode (active-matrix organic light). emitting diode (AMOLED), flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, quantum dot light emitting diodes (QLED), etc. In some implementations, the mobile phone 100 may include 1 or N display screens 194, where N is a positive integer greater than 1.

In addition, it should be noted that the mobile phone 100 can implement the shooting function through the ISP, camera 193, video codec, GPU, display screen 194 and application processor.

In addition, it should be noted that the ISP is used to process the data fed back by the camera 193 . For example, when taking a photo, the shutter is opened, the light is transmitted to the camera sensor through the lens, the optical signal is converted into an electrical signal, and the camera sensor passes the electrical signal to the ISP for processing, and converts it into an image visible to the naked eye. ISP can also perform algorithm optimization on image noise, brightness, and skin color. ISP can also optimize the exposure, color temperature and other parameters of the shooting scene. In some implementations, the ISP may be located in the camera 193 .

In addition, it should be noted that the camera 193 is used to capture still images or videos. The object passes through the lens to produce an optical image that is projected onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then passes the electrical signal to the ISP to convert it into a digital image signal. ISP outputs digital image signals to DSP for processing. DSP converts digital image signals into standard RGB, YUV and other format image signals. In some implementations, the mobile phone 100 may include 1 or N cameras 193, where N is a positive integer greater than 1.

In addition, it should be noted that the digital signal processor is used to process digital signals. In addition to processing digital image signals, it can also process other digital signals. For example, when the mobile phone 100 selects a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy.

Additionally, it should be noted that video codecs are used to compress or decompress digital video. Mobile phone 100 may support one or more video codecs. In this way, the mobile phone 100 can play or record videos in multiple encoding formats, such as: moving picture experts group (MPEG) 1, MPEG2, MPEG3, MPEG4, etc.

Continuing to refer to FIG. 3 , for example, the external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the mobile phone 100 . The external memory card communicates with the processor 110 through the external memory interface 120 to implement the data storage function. Such as saving music, videos, etc. files in external memory card.

Continuing to refer to FIG. 3 , by way of example, internal memory 121 may be used to store computer executable program code including instructions. The processor 110 executes instructions stored in the internal memory 121 to execute various functional applications and data processing of the mobile phone 100 . The internal memory 121 may include a program storage area and a data storage area. Among them, the stored program area can store the operating system, at least one application program required for a function (such as a sound playback function, an image playback function, etc.), etc. The storage data area can store data created during the use of the mobile phone 100 (such as audio data, phone book, etc.). In addition, the internal memory 121 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

Specifically, in the technical solution provided by the embodiment of this application, after the resident location identification mode is turned on, the acquired signaling data, the stay point data determined based on the signaling data, the resident location data determined based on the stay point data, etc. can be It is stored in the internal memory 121 of the mobile phone 100, so that it can be quickly read, processed and used.

In addition, it should be noted that the mobile phone 100 can implement audio functions through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the headphone interface 170D, and the application processor. Such as music playback, recording, etc.

In addition, it should be noted that the audio module 170 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signals. Audio module 170 may also be used to encode and decode audio signals. In some implementations, the audio module 170 may be provided in the processor 110 , or some functional modules of the audio module 170 may be provided in the processor 110 .

Continuing to refer to FIG. 3 , for example, the keys 190 include a power key, a volume key, etc. Key 190 may be a mechanical key. It can also be a touch button. The mobile phone 100 can receive key input and generate key signal input related to user settings and function control of the mobile phone 100 .

Continuing to refer to FIG. 3 , for example, the motor 191 may generate a vibration prompt. The motor 191 can be used for vibration prompts for incoming calls and can also be used for touch vibration feedback. For example, touch operations for different applications (such as taking pictures, audio playback, etc.) can correspond to different vibration feedback effects. The motor 191 can also respond to different vibration feedback effects for touch operations in different areas of the display screen 194 . Different application scenarios (such as time reminders, receiving information, alarm clocks, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also be customized.

Continuing to refer to FIG. 3 , for example, the indicator 192 may be an indicator light, which may be used to indicate charging status, power changes, or may be used to indicate messages, missed calls, notifications, etc.

This concludes the introduction to the hardware structure of the mobile phone 100. It should be understood that the mobile phone 100 shown in Figure 3 is only an example. In a specific implementation, the mobile phone 100 may have more or fewer components than those shown in the figure. , two or more components may be combined, or may have different component configurations. The various components shown in Figure 3 may be implemented in hardware, software, or a combination of hardware and software including one or more signal processing and/or application specific integrated circuits.

In order to better understand the software structure of the mobile phone 100 shown in Figure 3, the software structure of the mobile phone 100 will be described below. Before describing the software structure of the mobile phone 100, first, the architecture that can be adopted by the software system of the mobile phone 100 is explained.

Specifically, in practical applications, the software system of the mobile phone 100 can adopt a layered architecture, event-driven architecture, microkernel architecture, microservice architecture, or cloud architecture.

In addition, it is understandable that the software systems currently used by mainstream mobile phones 100 include but are not limited to Windows systems, Android systems, and iOS systems. For ease of explanation, this embodiment of the present application takes the Android system with a layered architecture as an example to illustrate the software structure of the mobile phone 100 .

In addition, the subsequent resident location identification scheme provided in the embodiments of this application is also applicable to other systems in specific implementation.

Refer to Figure 4, which is a software structure block diagram of the mobile phone 100 according to the embodiment of the present application.

As shown in Figure 4, the layered architecture of the mobile phone 100 divides the software into several layers, and each layer has clear roles and division of labor. The layers communicate through software interfaces. In some implementations, the Android system is divided into four layers, from top to bottom: application layer, application framework layer, Android runtime and system libraries, and kernel layer.

Among them, the application layer can include a series of application packages. As shown in Figure 4, the application package may include settings, maps, WLAN, Bluetooth, camera, music, smart assistant and other applications, which will not be listed one by one here, and this application does not limit this. .

Regarding the smart assistant application, in this embodiment, it is specifically used for the user to operate to enable or disable the function of realizing the resident location based on the resident location identification method provided by the embodiment of the application.

In addition, it is understandable that in some implementations, the functions implemented by the smart assistant application can also be integrated in the settings application, and this application does not limit this. For ease of explanation, this embodiment of the present application takes as an example the function of turning on or off the resident location based on the resident location identification method provided by the embodiment of the present application by setting an application program. The implementation method is shown in Figures 5a and 5b.

Referring to the interface 10c shown in (1) in Figure 5a, for example, the current interface 10c of the mobile phone may include one or more controls. Controls include but are not limited to: network controls, power controls, application icon controls, etc.

Continuing to refer to the interface 10c shown in (1) in Figure 5a, exemplary application icon controls include but are not limited to: clock application icon control, calendar application icon control, gallery application icon control, memo application icon control, file management application icon Control, email application icon control, music application icon control, calculator application icon control, video application icon control, recorder application icon control, weather application icon control, browser application icon control, settings application icon control 10c-1, etc., this They are not listed one by one, and this application does not limit them.

Continuing to refer to the interface 10c shown in (1) in Figure 5a, for example, after the user clicks the control 10c-1, the mobile phone responds to the user's operation behavior and activates the interface 10d shown in (2) in Figure 5a.

Referring to the interface 10d shown in (2) in Figure 5a, for example, the interface 10d may include one or more controls. The controls include but are not limited to: controls 10d-1 for exiting the interface 10d, controls for setting the sound and vibration mode of the mobile phone, controls for setting notifications, controls 10d-2 for setting the resident identification function, Controls used to view installed applications on the mobile phone, controls used to view the battery information of the mobile phone, controls used to view the current storage space of the mobile phone, controls used to view the security information of the mobile phone, etc. will not be listed here one by one. This application will This is not a restriction.

Continuing to refer to the interface 10d shown in (2) in Figure 5a, for example, after the user clicks the control 10d-2, the mobile phone responds to the user's operation behavior and activates the interface 10e shown in (1) in Figure 5b.

Referring to the interface 10e shown in (1) in Figure 5b, for example, the interface 10e may include one or more controls. The controls include but are not limited to: a control 10e-1 for exiting the interface 10e, and a control 10e-2 for turning on or off the resident identification function.

Exemplarily, in this embodiment, the state of the control 10e-2 in the interface 10e shown in (1) in Figure 5b indicates that the resident place identification function is not turned on, that is, the resident place identification function is in a closed state; as shown in Figure The state of the control 10e-2 in the interface 10e shown in (2) in 5b indicates that the resident identification function is on, that is, the resident identification function is on.

Continuing to refer to the interface 10e shown in (1) in Figure 5b, for example, when the user clicks the control 10e-2, the mobile phone responds to the user's operation behavior, and the control 10e-2 changes from the control 10e-2 shown in (1) in Figure 5b. The state switches to the state shown in (2) in Figure 5b. At this time, the resident location identification function is turned on. Subsequently, when the resident location identification function is turned on, the mobile phone can identify the resident location based on the embodiment of the present application. This method accurately determines the resident place of the user who uses the mobile phone, and then provides users with refined business recommendations based on the determined resident place and the user's behavioral habits in different resident places.

It should be understood that the above description is only an example for a better understanding of the technical solution of this embodiment, and is not the only limitation on this embodiment.

Among them, the application framework layer provides an application programming interface (API) and programming framework for applications in the application layer. In some implementations, these programming interfaces and programming frameworks can be described as functions. As shown in Figure 4, the application framework layer can include functions such as a view system, a content provider, a stay point identification module, a stay point merging module, a resident location identification module, and a resident location uniqueness judgment module. One enumeration is not limited in this application.

Exemplarily, in this embodiment, the stay point identification module is used to identify points in the user's movement trajectory that are continuous in time and space by using the nearest neighbor clustering method based on the signaling data generated during the use of the mobile phone 100. Close stopping points. Regarding the specific details of the stay point identification module determining the stay points within a certain time period, such as one day, based on the signaling data, please see below for details and will not be repeated here.

Exemplarily, in this embodiment, the stay point merging module is used to merge multiple identical stay points in each day identified by the stay point identification module, that is, the stay points processed by the stay point merging module have a unique sex. Regarding the specific details of merging stay points by the stay point merging module, please refer to the following and will not be repeated here.

Illustratively, in this embodiment, the resident place identification module is used to perform neighbor clustering on the unique stay points in each day determined by the stay point merging module within a certain period of time, such as N days, so as to meet the requirements. is determined to be the permanent residence. Regarding the specific details of the permanent residence determined by the permanent residence identification module, please refer to the following and will not be repeated here.

Illustratively, in this embodiment, the resident place uniqueness judgment module is used to uniquely determine the resident place determined by the resident place identification module in two adjacent time periods, such as the first day and the second day. Judgment to avoid duplication of final recorded residence. Regarding the specific details of how the resident location uniqueness judgment module determines the uniqueness of the resident location, see below for details and will not be repeated here.

It should be understood that the above description is only an example for a better understanding of the technical solution of this embodiment, and is not the only limitation on this embodiment.

In addition, it can be understood that the above-mentioned division of functional modules is only an example to better understand the technical solution of this embodiment, and is not the only limitation on this embodiment. In practical applications, the above functions can also be integrated and implemented in one functional module, which is not limited in this embodiment.

In addition, in practical applications, the above functional modules can also be represented as services and frameworks. For example, the stay point identification module can be represented as a stay point identification service, a stay point identification framework, etc. This embodiment is not limited to this.

In addition, it should be noted that the above-mentioned view system located in the application framework layer includes visual controls, such as controls for displaying text, controls for displaying pictures, etc. A view system can be used to build applications. The display interface can be composed of one or more views. For example, a display interface including a text message notification icon may include a view for displaying text and a view for displaying pictures.

In addition, it should be noted that the above-mentioned content provider located in the application framework layer is used to store and obtain data and make the data accessible to the application. The data may include videos, images, audio, calls made and received, browsing history and bookmarks, phone books, etc., which will not be listed one by one here, and this application does not limit this.

In addition, it should be noted that in actual applications, there can also be a phone manager, resource manager, notification manager, etc. in the application framework layer. Among them, the phone manager is used to provide communication functions of the electronic device 100 . For example, the management of call status (including connected, hung up, etc.); the resource manager provides various resources for applications, such as localized strings, icons, pictures, layout files, video files, etc.; the notification manager allows applications to Displaying notification information in the status bar can be used to convey notification-type messages. It can stay for a short time and then disappear automatically without user interaction.

It should be understood that the above description is only an example for a better understanding of the technical solution of this embodiment, and is not the only limitation on this embodiment.

Android Runtime includes core libraries and virtual machines. Android Runtime is responsible for the scheduling and management of the Android system.

The core library contains two parts: one is the functional functions that need to be called by the Java language, and the other is the core library of Android.

The application layer and application framework layer run in virtual machines. The virtual machine executes the java files of the application layer and application framework layer into binary files. The virtual machine is used to perform object life cycle management, stack management, thread management, security and exception management, and garbage collection and other functions.

System libraries can include multiple functional modules. For example: surface manager, media libraries, three-dimensional (3D) image processing library (for example: OpenGL ES), two-dimensional (2D) image engine (for example: SGL), etc.

The surface manager is used to manage the display subsystem and provides the fusion of 2D and 3D layers for multiple applications.

The media library supports playback and recording of a variety of commonly used audio and video formats, as well as static image files, etc. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

The 3D image processing library is used to implement 3D image drawing, image rendering, composition, and layer processing.

It is understandable that the above-mentioned 2D image engine is a drawing engine for 2D drawing.

In addition, it is understandable that the kernel layer in the Android system is the layer between hardware and software. The kernel layer at least includes display driver, Bluetooth driver, microphone driver, sensor driver, GPS driver, etc. For example, the GPS driver can be used to drive the GPS chip to achieve positioning to obtain the latitude and longitude information of different locations during movement and stay, so that the above-mentioned stay point identification module uses the longitude and latitude information as a dimension, combined with the stay time. Determine stopping points.

This concludes the introduction to the software structure of the mobile phone 100 . It can be understood that the layers in the software structure shown in FIG. 4 and the components included in each layer do not constitute specific limitations on the mobile phone 100 . In other embodiments of the present application, the mobile phone 100 may include more or fewer layers than shown in the figure, and each layer may include more or fewer components, which is not limited by this application.

Taking the mobile phone with the hardware structure shown in Figure 3 and the software structure shown in Figure 4 as an example, in order to better adapt to the scenarios shown in Figures 1a to 2b, that is, to accurately identify the user's residence, Then, based on the user's behavioral habits in different residences, detailed business recommendations are implemented. For the above-mentioned stay point determination process implemented by the stay point identification module, the stay point merging process implemented by the stay point merging module, and the stay point merging process implemented by the resident The resident location determination process implemented by the location identification module and the judgment process implemented by the resident location uniqueness judgment module will be described in detail.

Stopping point confirmed

For the convenience of explanation, this embodiment uses days as units and combines the partial signaling data corresponding to the mobile phones in one day shown in Table 1 to explain the determination of the stay point.

It should be understood that the so-called signaling data can also be called Mobile Signal Data. Specifically, it refers to determining the spatial location of the user through the exchange of information between mobile phone users between base stations, that is, it can record the flow of people relatively accurately. space-time trajectory. As long as mobile phone users turn on and off, make calls, text messages, location updates, and switch base stations, the corresponding signaling data will be recorded. Therefore, based on the signaling data within the set time, the mobile phone user's stay point within that time can be determined.

Table 1 Mobile phone signaling data

Refer to Table 1, for example, the content corresponding to the "User_id" field is used to identify the mobile phone corresponding to the signaling data. Regarding the specific value of the content corresponding to "User_id", in some implementations, it can be the SIM card number inserted in the mobile phone, the serial number of the mobile phone, or the identification number generated according to the set rules, etc., this implementation The example does not limit this. In practical applications, anything that can identify its uniqueness can be used. Table 1 takes the identification number "User_138" generated according to the set rules as an example.

In addition, it should be noted that for the scenario where the determination of the stay point is completed locally on the mobile phone, since the signaling data obtained is the mobile phone's own and there is no signaling data from other mobile phones, it is displayed in the form shown in Table 1 For signaling data, the "User_id" field does not need to be set.

Correspondingly, for the scenario where the determination of the stay point is completed by the cloud server, in order to distinguish the signaling data of different mobile phones, the "User_id" field needs to be set for the signaling data displayed in the form shown in Table 1.

It should be understood that the above description is only an example for a better understanding of the technical solution of this embodiment, and is not the only limitation on this embodiment.

Continuing to refer to Table 1, for example, the content corresponding to the "Happen_time" field is used to identify the recording time of the signaling data. Table 1 takes the 10 pieces of signaling data corresponding to the 10 times "T_1" to "T_10" as an example.

Continuing to refer to Table 1, for example, the content corresponding to the "longitude" field is used to identify the longitude corresponding to the piece of signaling data, and the content corresponding to the "latitude" field is used to identify the latitude corresponding to the piece of signaling data. Table 1 takes as an example that the longitude and latitude of the 10 pieces of signaling data corresponding to the 10 times from "T_1" to "T_10" are different.

Continue to refer to Table 1. For example, the content corresponding to the "Cell_id" field is used to identify the identity document (Identity document, id) of the base station that the mobile phone accesses at different times, and the content corresponding to the "Wifi_bssid" field is used to identify The number of the router that the mobile phone accesses when using Wifi for communication services.

It should be noted that in actual applications, if the user does not use Wifi but directly uses the cellular network when using the mobile phone for communication services, the content corresponding to the "Wifi_bssid" field in the corresponding signaling data can be empty, or set to A certain "null" or other contents are not limited in this embodiment.

Based on the 10 pieces of signaling data shown in Table 1 above, 10 spatial locations of users using the mobile phone can be determined, and their distribution is, for example, P1 to P10 in Figure 6a.

Referring to Figure 6a, for example, the distribution of the six spatial locations P4 to P9 is relatively concentrated. In order to reduce the amount of data processing, one of the spatial locations can be used as a reference point, and then the reference point and other locations can be determined based on the longitude and latitude information of each spatial location. The distance between 5 spatial locations.

Referring to Figure 6b, for example, taking P4 as the reference point, it is assumed that the distance between P4 and P5 is D (P4, P5), the distance between P4 and P6 is D (P4, P6), and the distance between P4 and P7 D(P4,P7), the distance D(P4,P8) between P4 and P8, and the distance D(P4,P9) between P4 and P9 are all less than the set distance D1, then the 6 distances from P4 to P9 can be A spatial position is regarded as a spatial position, such as P11 shown in Figure 6b. In this way, when subsequently determining the stay point based on these 10 spatial positions, P11 can be directly processed with P1, P2, P3, and P10. There is no need to process the 6 spatial positions P4 to P9 with P1, P2, P3, and P10 respectively. processing, thereby simplifying the processing process.

In addition, it should be noted that in some implementations, the average longitude and latitude information of the six spatial locations P4 to P9 can be used as the longitude and latitude information of the spatial location P11, that is, the longitude of the six spatial locations P4 to P9 is calculated. The average longitude is used as the longitude of the spatial location P11, and the average latitude calculated from the latitudes of the six spatial locations P4 to P9 is used as the latitude of the spatial location P11.

For example, in other implementations, if the difference in the longitude and latitude information of the six spatial locations P4 to P9 is small, the selected reference point, such as the longitude and latitude information of P4 mentioned above, can also be directly used as the longitude and latitude information of P11. .

It should be understood that the above description is only an example for a better understanding of the technical solution of this embodiment, and is not the only limitation on this embodiment.

In addition, it should be noted that the value of D1 mentioned above can be set according to actual business scenario requirements. For example, corresponding to business scenarios with high accuracy requirements, the value of D1 can be set to a relatively small value, such as 1 to 5 meters; On the contrary, the value of D1 can be set to a relatively large value, such as 5 to 10 meters, or even larger. This embodiment does not limit this.

For example, after the processing shown in Figure 6b, the distribution diagram shown in Figure 6a will be changed to that shown in Figure 6c.

Based on the clustering method of nearest neighbor clustering, as shown in Table 1 and Figure 6c, the distance information between P1 and P2, P3, P11 and P10 is determined in sequence, assuming 20 meters, 50 meters, 175 meters and 205 meters. If the distance between any two spatial locations in the same stay point set according to business scenario requirements is not greater than D2, such as 125 meters, and the stay time at the stay point is determined based on the time corresponding to all spatial locations in the stay point, it is not less than the set A certain time threshold, such as 10 minutes. Based on the above-determined distance information between P1 and P2, P3, P11 and P10, it can be seen that the distance between P1 and P2, P3 is not greater than D2, which satisfies one of the conditions for belonging to the same stay point. For this situation, the dwell time of the mobile phone user at the three spatial locations P1 to P3 can be further determined.

Regarding the determination of the residence time, the content corresponding to the "Happen_time" field in each piece of signaling data in Table 1 identifies the time point when the mobile phone user moves to the spatial position corresponding to the signaling data. When the mobile phone user moves from P1 to P3 For the residence time of these three spatial locations, for example, "T_1" corresponding to P1 can be used as the starting time, "T_3" corresponding to P3, or "T_4" corresponding to P4 can be used as the ending time, and then the mobile phone user can be determined from P1 to P3 The residence time of these three spatial locations.

For example, in other implementations, if the content corresponding to the "Happen_time" field in each piece of signaling data in Table 1 identifies the dwell time of the mobile phone user at the spatial location corresponding to the piece of signaling data, then directly By summing "T_1", "T_2" and "T_3", you can get the dwell time of the mobile phone user at the three spatial locations from P1 to P3.

It should be understood that the above description is only an example for a better understanding of the technical solution of this embodiment, and is not the only limitation on this embodiment. In this embodiment, it is taken as an example that the mobile phone user's stay time in the three spatial locations P1 to P3 is 2 minutes.

Since the mobile phone user's stay time (2 minutes) at the three spatial locations from P1 to P3 is less than the above-mentioned time threshold (10 minutes), P1, P2, and P3 do not belong to the same stay point.

According to the above processing logic, combined with Table 1 and Figure 6d, continue to determine the distance information between P2 and P3, P11 and P10, assuming they are 30 meters, 155 meters, and 185 meters. Still taking the above two conditions for determining that they belong to the same stay point as an example, it can be determined that P2 and P3 meet the distance requirements for belonging to the same stay point. If the mobile phone user stays at the two spatial locations P2 and P3 for 5 minutes, Then P2 and P3 do not belong to the same stop point.

According to the above processing logic, combined with Table 1 and Figure 6e, continue to determine the distance information between P3 and P11 and P10, assuming 125 meters and 155 meters. Still taking the above two conditions for determining that they belong to the same stay point as an example, it can be determined that P3 and P1 meet the distance requirements for belonging to the same stay point. If the mobile phone user stays at the two spatial locations P3 and P11 for 30 minutes, That is, if it is greater than the set time threshold (10 minutes), it is determined that P3 and P11 also meet the above time requirements for belonging to the same stay point, so P3 and P11 belong to the same stay point. That is, according to the signaling data corresponding to P3 and the signaling data corresponding to P11, a stay point can be determined, such as stay point 1 in Figure 6e.

It can be understood that the longitude and latitude information about the stay point 1 may be, for example, the average longitude and latitude information determined based on the longitude and latitude information of P3 and P11.

Therefore, based on the clustering method based on neighbor clustering and according to the above processing logic, all the stay points that meet the above requirements can be determined based on all signaling data recorded during the day.

Stop point merge

After the above-mentioned stay points are determined, all the stay points determined for the day can be clustered based on the clustering method of neighbor clustering, and then multiple stay points at the same location can be merged into one, so that the merged The stop point is unique.

Referring to Figure 7, for example, the staying points that the mobile phone user appears sequentially throughout the day are determined to be stay point 1, stay point 2 and stay point 1 using the above stay point determination method, that is, the mobile phone user stays at stay point 1 throughout the day. Passed twice and stopped at stopping point 2 once.

In order to ensure that different stay points only appear once, the stay points are merged based on the clustering method of nearest neighbor clustering. For example, a stay point in a day is randomly selected, such as stay point 1 in Figure 7, and then stay point 1 is used as Starting from the clustering center point, traverse backward to the next stop point that appears on the timeline, such as stop point 2. Next, it is judged whether the distance between stay point 1 and stay point 2 is not greater than the set distance D3. If it is greater than D3, then stay point 2 is used as the second cluster center point, that is, stay point 1 and stay point 2. are two different stay points, for example, one indicates the residence location of the mobile phone user, and the other indicates the work location of the mobile phone user; otherwise, the stay point 1 and the stay point 2 will be merged into one stay point, and the stay point 1 and the stay point 2 will be combined according to the stay point 1 and the stay point 2. The average longitude and latitude information determined by the longitude and latitude information of point 2 is used as the longitude and latitude information of the merged stay point.

Based on the above processing logic, repeat the above steps until all the stay points on the timeline have been traversed, and then all the merged stay points in the day can be obtained. As shown in Figure 7, this embodiment takes the stay point 1 and the stay point 2 as two different stay points as an example. According to the above processing logic, the finally obtained stay points include the stay point 1' and the stay point 2.

It can be understood that each stay point includes signaling data corresponding to each spatial location that constitutes the stay point. In actual applications, a stay point may include many spatial locations, such as dozens, hundreds, or even more. Therefore, often because the conditions set in the stay point determination process are not reasonable enough, in the stay point merging process, the merged stay points include abnormal spatial positions.

It should be noted that the abnormal spatial position mentioned in this embodiment is, for example, an edge spatial position far away from the spatial positions where most of the objects are gathered together. In order to avoid the impact of these edge space positions on the final result, after merging the stay points according to the above processing logic, the spatial position information included in each stay point can be filtered, and then the abnormal edge space positions are eliminated, and finally based on After eliminating abnormal spatial locations, the remaining spatial location longitude and latitude information is used to recalculate the central longitude and latitude of the stay point, that is, the average longitude and average latitude.

Regarding the elimination method of edge space position, for example, the following method can be used:

(1) For each stay point, obtain the longitude and latitude information corresponding to all spatial locations within the stay point;

(2) Sort according to latitude and longitude information;

(3) Obtain the sorted longitude and latitude of Q1 respectively, remember Q1_long and Q1_lat respectively, and the longitude and latitude of Q3, remember Q3_long and Q3_lat respectively;

(4) Keep the longitude in [Q1_long-1.5*(Q3_long-Q1_long), Q3_long+1.5*(Q3_long-Q1_long)] and the latitude in [Q1_lat-1.5*(Q3_lat-Q1_lat), Q3_lat+1.5*(Q3_lat-Q1_lat) ] spatial position, others are regarded as edge spatial positions and eliminated.

For example, regarding the selection of Q1 and Q3, the sorted spatial positions can be divided into two averages, and the middle position is represented as Q2, then the Q1 position is the middle between the 1st position and the Q2th position. bit, the Q3 bit is the middle bit between the Q2 bit and the last bit. For example, when there are 100 spatial locations after sorting, the longitude and latitude information of the Q1 bit is the longitude and latitude information corresponding to the 25th bit of spatial location. The longitude and latitude information at the Q3 position is the longitude and latitude information corresponding to the spatial position at the 75th position.

In addition, it should be noted that if in actual applications, the above two middle bits are not integer values, the Q1th bit is taken to be the smallest integer bit close to the middle bit determined based on the 1st and Q2th bits, and the Q3th bit is taken to be close to The maximum integer number of intermediate bits determined based on the Q2 and last bits.

For example, in the case where the spatial position distribution included in the merged stay points is as shown in (1) in Figure 8, after the edge spatial position is eliminated based on the above edge spatial position elimination method, the spatial position that is finally retained is The distribution is shown in (2) in Figure 8.

It should be understood that the above description is merely an example listed for a better understanding of the technical solution of this embodiment, and is not intended to be the sole limitation to this embodiment.

Therefore, based on the clustering method of nearest neighbor clustering, according to the above processing logic, it is possible to obtain all the unique stay points in a day based on the stay points determined by the stay point determination link, that is, after the stay point merging link, the final retained points Multiple stop points are different stop points.

Residential location determined

It should be noted that the resident place mentioned in this embodiment refers to the stay point where the mobile phone user's stay time at the same stay point meets the set requirements within the preset time. Since the determination of the above stay points is described in units of days, this embodiment takes the stay points where the number of days that the mobile phone user stays at the same stay point within N days meets the setting requirements, such as not less than (α% * N), as the permanent residence. .

It is understandable that the value of α can be set according to the requirements of the business scenario, for example, it can be 50, that is, a stay point with a stay period of not less than N/2 days is regarded as a permanent residence.

Regarding the determination of the number of days to stay at the same stay point, specifically based on the clustering method of nearest neighbor clustering, all the same stay points that appear within N days are clustered. In Figure 9, N=3 is used as an example, where Day 1 stays according to the above The stay points determined after the point determination process and stay point merging process include stay point 1' and stay point 2. On Day 2, the stay points determined after the stay point determination process and stay point merging process are processed according to the above stay point determination process and stay point merging process include stay point 1', stay point 2. Point 2 and stay point 3. On Day 3, the stay points determined after processing according to the above stay point determination process and stay point merging process include stay point 1' and stay point 4. Based on the clustering method of nearest neighbor clustering, after clustering the stay points that appeared in these three days, we will finally get 4 clusters of different stay points, such as the cluster cluster and stay point of stay point 1' in Figure 9 The cluster of 2, the cluster of stop point 3 and the cluster of stop point 4.

It should be noted that, in order to improve the accuracy of the final determined resident place as much as possible, in the process of determining the resident place, when clustering based on the clustering method of nearest neighbor clustering, the distance between any two stay points can be set. Less than D4, where the value of D4 can be smaller than D3 mentioned above.

After processing according to the above processing logic, the number of stay points included in the cluster corresponding to each stay point represents the number of days that the mobile phone user has appeared in the cluster of the stay point. Continuing to refer to Figure 9, for example, in these three days, the mobile phone user appeared at stay point 1' every day, appeared at stay point 2 on two days, and appeared at stay point 3 and stay point 4 on one day. Pass.

Based on the above-mentioned requirements for determination of permanent residence, if the value of α is 50, then the stay points that have occurred on at least 1.5 of these 3 days will be determined as permanent residences. It can be seen from the above description that there are two stay points that meet this requirement, namely stay point 1' and stay point 2. That is, in the example shown in Figure 9, according to the above stay point determination link, stay point merging link and permanent residence determination During the processing of this link, the final determined permanent locations are stay point 1' and stay point 2.

It should be understood that the above description is only an example for a better understanding of the technical solution of this embodiment, and is not the only limitation on this embodiment.

Therefore, the clustering method based on nearest neighbor clustering clusters the spatial positions of mobile phone users in each day, and then obtains the stay points included in each day. At the same time, by merging the stay points in each day, each user is given The actual physical meaning of stay points in the clustering process is that in the process of determining the resident location, for any cluster, each stay point represents the number of days that the mobile phone user has appeared in the cluster. In this way, according to Different business scenarios require that by setting different day thresholds, different staying points can be selected as permanent residences in the business scenario, so that users can be provided with more colorful services based on the identified permanent residences.

Judgment of uniqueness of permanent residence

It should be noted that in practical applications, the resident location determination process can be executed according to a set period, for example, in days, that is, the longitude and latitude information corresponding to the resident location generated each day can be based on the results of the previous day. Adjustment. Although this method can reduce the amount of data processing each day, in actual applications, due to the difference in the user's stay location, the longitude and latitude information of the permanent residence of the previous day may not be exactly the same, which will result in the correspondence of each day. There are many different longitude and latitude information for the same permanent place in the resident place statistics table. In order to ensure that the permanent place can be accurately determined based on the previous permanent place statistics table and the latest day's permanent place statistics table in the above permanent place determination process, instead of identifying the same permanent place as multiple different places. The resident place can be judged whether the resident place recorded in the resident place statistics table of the previous day is the same as the resident place recorded in the resident place statistics table of the next day. If so, the same label will be assigned to it. .

Table 2Day 9-day resident statistics table

Table 3 Day 10 resident place statistics Table 1

It should be noted that the "Num" field appearing in the above table is the sequence number corresponding to each piece of data when generating the resident place statistics table, the "longitude" field corresponds to the longitude of the resident place, and the "latitude" field corresponds to The content of is the latitude of the resident place, and the content corresponding to the "label" field is the label corresponding to the resident place.

In addition, it should be noted that the resident place statistics table 1 on Day 10 shown in Table 3 is specifically the resident place determined based on the signaling data on Day 10.

By calculating the distance between the longitude and latitude of each piece of data in Table 3 and the longitude and latitude of each piece of data in Table 2, the distance between the resident place corresponding to each serial number in Table 3 and each resident place in Table 2 is determined. Is the distance no greater than the set distance D5? The value of D5 can be set according to the actual business scenario requirements, for example, 5 meters.

Correspondingly, if it is determined through judgment that the distance between the resident place where Num is 1 in Table 3 and the resident place where Num is 1 in Table 2 is not greater than D5, it is different from the resident place where Num is 2 and 3 in Table 2. If the distance between them is greater than D5, it is considered that the permanent residence with Num of 1 in Table 3 and the permanent residence with Num of 1 in Table 2 are the same permanent residence, and the permanent residence with Num of 2 and 3 in Table 2 is considered to be the same permanent residence. The land is not the same permanent place.

According to the above processing logic, the other remaining permanent residences in Table 3 are judged against the permanent residences in Table 2. Since the permanent residence with Num in Table 3 is 2 and the longitude and latitude of the permanent residence with Num at 2 in Table 2 The same, it can be directly determined that it is the same permanent residence. It is not the same permanent residence as the permanent residence where Num is 1 and 3 in Table 2. The permanent residence where Num is 3 in Table 3 is different from the permanent residence where Num is 3 in Table 2. The distances between the permanent residences of 1, 2 and 3 are all greater than D5, that is, the permanent residence with Num of 3 in Table 3 and the permanent residence with Num of 1, 2 and 3 in Table 2 are different permanent residences. , assuming that the resident place with Num of 3 in Table 3 appears for the first time and does not appear in the resident place statistics table from Day 1 to Day 8, then a new resident place with Num of 3 in Table 3 can be assigned Labels, such as Fence_4, and other identical resident locations, reuse the labels corresponding to the resident locations in Table 2. Based on this, after assigning labels to the resident places with Num of 1, 2, and 3 in Table 3, the obtained resident place statistics table for Day 10 is as shown in Table 4 below.

Table 4 Day 10-day resident statistics Table 2

It should be understood that the above description is only an example for a better understanding of the technical solution of this embodiment, and is not the only limitation on this embodiment.

Therefore, through the processing logic of the above-mentioned permanent residence uniqueness judgment, the same permanent residence can be recognized as the same permanent residence even if the longitude and latitude are not exactly the same.

Regarding the specific implementation process of the permanent residence identification method mentioned in the above embodiments of this application, as well as the first stay point determination process involved in the permanent residence identification method, and the first stay point merging into the second stay point. The process, the process of eliminating abnormal spatial locations, the process of determining the resident location based on the second stay point, and the process of determining the uniqueness of the resident location are detailed in the embodiments shown in Figures 10 to 15.

Referring to Figure 10, the resident location identification method provided by this embodiment specifically includes:

S101. Obtain signaling data recorded by the electronic device used by the user in a first time period. The first time period includes at least one second time period.

For example, in some implementations, the electronic device is, for example, the above-mentioned mobile phone, tablet computer, smart wearable device, such as smart watch, etc., which is not limited in this embodiment.

For example, in some implementations, the first period of time in this embodiment is, for example, the N days mentioned above, such as 3 days.

Correspondingly, when the first time period is N days, the second time period is, for example, 24 hours, that is, 1 day.

In addition, it can be understood that the signaling data in this embodiment is the same as the above embodiment, and may include longitude, latitude, accessed base station ID, accessed router number, specific recording time, and ID identifying the electronic device. etc. The description of the specific parameters in the signaling data is detailed above and will not be described again here.

S102: For each second time period, determine the user's first stay point in the second time period based on the signaling data of the second time period.

For example, in some implementations, there may be multiple determined first stay points, such as stay point 1, stay point 2, etc. mentioned above.

Regarding the determination process of the first stopping point, reference can be made to the embodiment shown in Fig. 11 and will not be described again here.

S103. For each second time period, based on the clustering method of neighbor clustering, merge the first stay points in the second time period to obtain the second stay point.

For example, in some implementations, based on the distance method of nearest neighbor clustering, the first stay point is merged into a second stay point, for example, two or even more stay points 1 are merged as mentioned above. It is the stay point 1'. For specific implementation details, please refer to the embodiment shown in Figure 12 and will not be described again here.

S104. Based on the clustering method of neighbor clustering, the same second stay points in the first time period are clustered into a cluster.

As mentioned above, all stay points 1' within 3 days are clustered into one cluster, all stay points 2 within 3 days are clustered into one cluster, and all stay points 3 within 3 days are clustered into one. Clustering clusters all the stay points 4 within 3 days into one clustering cluster. For specific implementation details, please refer to the embodiment shown in Figure 14, which will not be described again here.

S105. For each clustering cluster, when the number of second staying points in the clustering cluster meets the set requirements, determine the second staying point in the clustering cluster as the first resident place.

For example, as mentioned above, the second stay point in the cluster whose number of second stay points is not less than (α% * N) is determined as the first resident place. For specific implementation details, please refer to the above , which will not be described again here.

Therefore, the identification method of the permanent residence provided by this embodiment determines the first stay points included in the second time period and merges multiple identical first stay points into one second stay based on the neighbor clustering method. points, thereby ensuring that each stay point in the second time period is unique, giving each stay point actual physical meaning in the clustering process, thereby ensuring that the same stay points in the first time period are finally classified based on the nearest neighbor clustering method. After the second stay points are clustered into a cluster, for any cluster, each second stay point represents the number of days the user has appeared in the cluster. In this way, according to different business scenario needs, By setting different day thresholds, different staying points can be selected as permanent residences in this business scenario, so that users can be provided with more colorful services based on the identified permanent residences.

Referring to Figure 11, the determination process of the first stay point in the resident place identification method provided by this embodiment specifically includes:

S201: For each second time period, determine the distance between the spatial positions corresponding to each two pieces of signaling data in the second time period.

It is understandable that the spatial location is determined based on the latitude and longitude information in the corresponding signaling data. Therefore, based on the latitude and longitude information in each two pieces of signaling data, the distance between the two corresponding spatial locations can be determined.

In addition, in order to reduce the amount of data processing, in some implementations, after determining the distance between the spatial locations corresponding to each two pieces of signaling data in the second time period, for each spatial location, when there is a distance between When the spatial position whose distance satisfies the set second distance threshold, the spatial position and the spatial position whose distance from the spatial position satisfies the set second distance threshold can be merged into one merged spatial position.

Further, in order to facilitate the subsequent determination of the first stop point based on the merged spatial position, for each merged spatial position, the average longitude and average latitude can be calculated based on the longitude and latitude information of each spatial position included in the merged spatial position, and then The average longitude and average latitude obtained are calculated as the latitude and longitude information of the combined spatial location.

Regarding the method of determining the latitude and longitude information of the combined spatial location, please refer to the above and will not be described again here.

Illustratively, the first distance threshold in this embodiment is, for example, the distance D1 mentioned above. Regarding the implementation details of merging multiple adjacent spatial positions into one merged spatial position, please refer to the above. The process of merging P4 to P9 into P11 will not be described again here.

S202. For each spatial position, when there is a spatial position whose distance from the spatial position satisfies the set first distance threshold, determine the spatial position of the electronic device and the distance between the electronic device and the spatial position that satisfies the set first distance threshold. The dwell time at a spatial location away from the threshold.

For example, the first distance threshold in this embodiment is, for example, the distance D2 mentioned above, such as 125 meters.

Correspondingly, regarding the implementation details of whether the distance between each two spatial positions satisfies the distance D2 determined as the first stay point, please refer to the description of the stay point determination environment implemented by the stay point determination module above, which will not be discussed here. Again.

S203: When the stay time satisfies a set time threshold, the spatial position and the spatial position whose distance to the spatial position satisfies a set first distance threshold are determined as a first stay point.

For example, the residence time threshold mentioned in this embodiment can be set according to business scenario requirements, such as the 10 minutes mentioned above.

Correspondingly, regarding the implementation details of whether the stay time meets the stay time threshold, please refer to the description of the stay point determination environment implemented by the stay point determination module above, which will not be described again here.

Therefore, based on the clustering method based on neighbor clustering and according to the above processing logic, all first stay points that meet the above requirements can be determined based on all signaling data recorded during the day.

Referring to Figure 12, the process of merging the first stay point into the second stay point in the resident place identification method provided by this embodiment specifically includes:

S301: For each second time period, determine the distance between every two first stay points in the second time period.

For example, regarding determining the distance between every two first stay points in the second time period, for example: for each first stay point in each second time period, first based on the first stay point Include the longitude and latitude information of each spatial location, calculate the average longitude and average latitude; then, use the calculated average longitude and average latitude as the longitude and latitude information of the first stay point; finally, based on the longitude and latitude of each two first stay points information to determine the distance between each two first stop points.

It should be understood that the above description is only an example for a better understanding of the technical solution of this embodiment, and is not the only limitation on this embodiment.

S302: For each first stay point, based on the clustering method of nearest neighbor clustering, merge the first stay point and the first stay point whose distance from the first stay point satisfies the set third distance threshold into A second stop.

For example, in this embodiment, the third distance threshold is, for example, the distance D3 mentioned above.

Correspondingly, the implementation details of using the third distance threshold as a judgment condition and merging multiple first stay points into one second stay point based on the clustering method of neighbor clustering can be found above, and will not be described again here.

In addition, it should be noted that in some implementations, there may be only one first stay point. For example, stay point 2 above appears only once in a day. Corresponding to this scenario, the first stay point can be as the corresponding second stop point.

Therefore, based on the clustering method of nearest neighbor clustering, according to the above processing logic, it is possible to obtain all the unique stay points in a day based on the stay points determined by the stay point determination link, that is, after the stay point merging link, the final retained points Multiple stop points are different stop points.

Referring to Figure 13, the process of eliminating abnormal spatial locations in the resident location identification method provided by this embodiment specifically includes:

S401. For each second stay point, determine the first longitude and latitude information extraction bit and the second longitude and latitude information extraction bit corresponding to the second stay point.

Regarding the determination method of the first longitude and latitude information extraction bit and the second longitude and latitude information extraction bit corresponding to the second stay point, for example, first determine the number of spatial positions included in the second stay point; then determine the first intermediate bit according to the number; and then The middle bit between the first bit and the first middle bit is determined as the first longitude and latitude information extraction bit corresponding to the second stay point, and the middle bit between the first middle bit and the last bit is determined as the second stay point corresponding to The second latitude and longitude information extraction bit.

For example, the first latitude and longitude information extraction bit in this embodiment is, for example, Q1 as mentioned above, the second latitude and longitude information extraction bit is, for example, Q3 as mentioned above, and the first middle bit is, for example, the above Said Q2.

S402, arrange the spatial positions included in the second stay point in order, extract the first longitude and first latitude of the spatial position of the first longitude and latitude information extraction bit, and the second longitude of the spatial position of the second longitude and latitude information extraction bit. and second latitude.

For example, the first longitude of the spatial position of the first latitude and longitude information extraction bit is, for example, the above Q1_long, and the first latitude is, for example, the above Q1_lat.

For example, the second longitude of the spatial position of the second latitude and longitude information extraction bit is, for example, the above Q3_long, and the second latitude is, for example, the above Q3_lat.

S403: Determine the longitude retention interval based on the first longitude and the second longitude.

For example, regarding the first longitude and the second longitude, the determined longitude retention interval satisfies [first longitude-1.5*(second longitude-first longitude), second longitude+1.5*(second longitude) longitude - first longitude)].

S404: Determine the latitude retention interval based on the first latitude and the second latitude.

For example, regarding the first latitude and the second latitude, the determined latitude retention interval satisfies [first latitude - 1.5* (second latitude - first latitude), second latitude + 1.5* (second latitude - first latitude), for example one latitude)].

S405: Eliminate the spatial positions in the second stay point whose longitude is not in the longitude retention interval and whose latitude is not in the latitude retention interval.

Regarding the specific selection of Q1 and Q3, as well as the details of eliminating abnormal spatial positions, please refer to the above and will not be repeated here.

This ensures that the interference of abnormal spatial location longitude and latitude information on the final determined permanent location is avoided, and the accuracy of the determined permanent location is ensured.

Referring to Figure 14, the process of determining the permanent residence based on the second stay point in the permanent residence identification method provided by this embodiment specifically includes:

S501, determining the distance between every two second stop points in a first time period.

Exemplarily, regarding the method of determining the distance between every two second stay points in the first time period, for example: for each second stay point, first based on each first stay point corresponding to the second stay point Based on the longitude and latitude information of the point, calculate the average longitude and average latitude; then use the average longitude and average latitude as the longitude and latitude information of the second stay point; finally, determine each two second stay points based on the longitude and latitude information of each two second stay points. the distance between.

It should be understood that the above description is only an example for a better understanding of the technical solution of this embodiment, and is not the only limitation on this embodiment.

S502, for each second stay point, based on the clustering method of neighbor clustering, cluster the second stay point and the second stay point whose distance from the second stay point satisfies the set fourth distance threshold. is a cluster.

Regarding the implementation details of clustering multiple identical second stay points into one cluster, please refer to the description of the resident location determination link implemented by the resident location determination module above, which will not be described again here.

Therefore, the clustering method based on nearest neighbor clustering clusters all the same second stay points in the first time period into a cluster, and gives each second stay point a physical meaning in the cluster, that is, In the process of determining the resident location, for any cluster, each second stay point represents the number of days the user has appeared in the cluster. In this way, according to the needs of different business scenarios, different days can be set By setting the threshold, different stay points can be selected as permanent residences in this business scenario, thereby providing users with more colorful services based on the identified permanent residences.

Referring to Figure 15, the process for determining the uniqueness of the resident location in the resident location identification method provided by this embodiment specifically includes:

S601: Allocate a permanent location label to each first permanent location determined in a first time period.

S602. After determining the second resident place in the third time period based on the signaling data recorded in the third time period in the distance mode based on neighbor clustering, determine the second resident place for each second resident place. Distance from each first permanent residence.

S603: For each second resident place, when there is a first resident place whose distance from the second resident place meets the set fifth distance threshold, assign the second resident place to the first resident place. The resident label of the same resident.

Regarding the determination of the uniqueness of the permanent location, please refer to the description of the permanent location uniqueness judgment step implemented by the permanent location uniqueness judgment module above, and will not be described again here.

As a result, the uniqueness of the resident location is determined, so that subsequent service recommendation services based on the resident location can be better suited to users.

Further, in practical applications, after the permanent residence is determined according to the above permanent residence identification method, in order to facilitate providing users with rich and colorful services, the labels of the permanent residences where the user resides in different cities can be added, and The longitude and latitude information of each permanent residence, the ID of the base station accessed in different permanent residences, and the number of days of access, the numbers of routers connected in different permanent residences, and the number of days of accessed routers, permanent residence The trajectory index of the spatial location of the user's movement process and the number of days the user appears in different residences within the preset time period are stored in the form of Table 5 below.

Table 5 Resident location information table

It should be understood that the above description is only an example for a better understanding of the technical solution of this embodiment, and is not the only limitation on this embodiment. Based on the above resident location information table, when it is determined that the user is in a different resident location, appropriate services can be pushed to the user through the corresponding base station and router.

In addition, it can be understood that in order to implement the above functions, the electronic device includes corresponding hardware and/or software modules that perform each function. In conjunction with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is performed by hardware or computer software driving the hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions in conjunction with the embodiments for each specific application, but such implementations should not be considered to be beyond the scope of this application.

In addition, it should be noted that in actual application scenarios, the resident identification method provided by the above embodiments implemented by electronic equipment can also be performed by a chip system included in the electronic equipment, where the chip The system may include a processor. The chip system can be coupled with a memory, so that when the chip system is running, it calls the computer program stored in the memory to implement the steps performed by the electronic device. The processor in the chip system may be an application processor or a non-application processor.

In addition, embodiments of the present application also provide a computer-readable storage medium. Computer instructions are stored in the computer storage medium. When the computer instructions are run on an electronic device, the electronic device causes the electronic device to execute the above-mentioned related method steps to implement the above-mentioned embodiments. identification method of permanent residence.

In addition, embodiments of the present application also provide a computer program product. When the computer program product is run on an electronic device, it causes the electronic device to perform the above related steps to implement the resident location identification method in the above embodiment.

In addition, embodiments of the present application also provide a chip (which may also be a component or module), which may include one or more processing circuits and one or more transceiver pins; wherein the transceiver pins and the The processing circuits communicate with each other through internal connection paths. The processing circuits execute the above related method steps to implement the resident identification method in the above embodiment to control the receiving pin to receive signals and to control the sending pin to send signals.

In addition, it can be seen from the above description that the electronic devices, computer-readable storage media, computer program products or chips provided by the embodiments of the present application are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be Refer to the beneficial effects of the corresponding methods provided above, which will not be described again here.

As mentioned above, the above embodiments are only used to illustrate the technical solution of the present application, but not to limit it. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still make the foregoing technical solutions. The technical solutions described in each embodiment may be modified, or some of the technical features may be equivalently replaced; however, these modifications or substitutions do not cause the essence of the corresponding technical solutions to depart from the scope of the technical solutions in each embodiment of the present application.

Claims (14)

1. A method of identifying a premises, the method comprising:

acquiring signaling data recorded by electronic equipment used by a user in a first time period, wherein the first time period comprises at least one second time period;

for each second time period, determining a first stay point of a user in the second time period according to signaling data of the second time period;

for each second time period, merging the first stay points in the second time period based on a clustering mode of neighbor clustering to obtain second stay points;

clustering the same second stay points in the first time period into a cluster based on a clustering mode of neighbor clustering;

For each cluster, determining the second stay point in the cluster as a first residence when the second stay point number in the cluster meets a set requirement;

wherein for each second time period, determining a first dwell point of the user in the second time period according to the signaling data of the second time period includes:

for each second time period, determining the distance between the spatial positions corresponding to every two pieces of signaling data in the second time period;

for each of the spatial locations, determining a dwell time for the electronic device to stay at the spatial location and at a spatial location having a distance from the spatial location that is not greater than a set first distance threshold when there is a spatial location having a distance from the spatial location that is not greater than the set first distance threshold;

and determining the space position and the space position with the distance from the space position not larger than a set first distance threshold value as one first stopping point when the stopping time is not smaller than a set time threshold value.

2. The method of claim 1, wherein after said determining a distance between spatial locations corresponding to every two pieces of signaling data within said second time period, said method further comprises:

For each of the spatial positions, when there is a spatial position whose distance from the spatial position satisfies a set second distance threshold, merging the spatial position and the spatial position whose distance from the spatial position satisfies the set second distance threshold, which is smaller than the first distance threshold, into one merged spatial position.

3. The method according to claim 2, wherein the method further comprises:

for each merging spatial position, calculating average longitude and average latitude according to longitude and latitude information of each spatial position included in the merging spatial position;

and taking the average longitude and the average latitude as longitude and latitude information of the combined spatial position.

4. The method of claim 1, wherein for each of the second time periods, merging the first stay points in the second time period based on the clustering manner of the neighbor clusters to obtain second stay points, includes:

for each second time period, determining a distance between every two first stay points in the second time period;

And merging the first stopping points and the first stopping points, of which the distance with the first stopping points meets a set third distance threshold, into a second stopping point based on a clustering mode of neighbor clustering for each first stopping point.

5. The method of claim 4, wherein said determining, for each of said second time periods, a distance between each two first dwell points within said second time period comprises:

for each first stopping point in each second time period, calculating average longitude and average latitude according to longitude and latitude information of each spatial position included in the first stopping point;

taking the average longitude and the average latitude as longitude and latitude information of the first stay point;

and for each second time period, determining the distance between every two first stay points according to the longitude and latitude information of every two first stay points.

6. The method of claim 4, wherein after the second dwell point is obtained, the method further comprises:

for each second stopping point, determining a first longitude and latitude information extraction bit and a second longitude and latitude information extraction bit corresponding to the second stopping point;

Sequentially arranging the spatial positions included in the second dwell point, and extracting a first longitude and a first latitude of the spatial position of the first longitude and latitude information extraction bit, and a second longitude and a second latitude of the spatial position of the second longitude and latitude information extraction bit;

determining a longitude reserved interval according to the first longitude and the second longitude;

determining a latitude reservation interval according to the first latitude and the second latitude;

and eliminating the spatial position of the second stopping point, in which the longitude is not in the longitude reserved interval and the latitude is not in the latitude reserved interval.

7. The method of claim 6, wherein the determining the first and second latitude and longitude information extraction bits corresponding to the second dwell point comprises:

determining a number of spatial positions included in the second dwell point;

determining a first intermediate bit based on the number;

determining a middle bit between a first bit and the first middle bit as a first longitude and latitude information extraction bit corresponding to the second stay point;

and determining the middle bit between the first middle bit and the last bit as a second longitude and latitude information extraction bit corresponding to the second stay point.

8. The method of claim 6, wherein the reserved longitude interval is [ first longitude-1.5 (second longitude-first longitude), second longitude +1.5 (second longitude-first longitude) ];

the latitude reservation interval is [ first latitude-1.5 (second latitude-first latitude), second latitude+1.5 (second latitude-first latitude) ].

9. The method of claim 1, wherein for each of the second time periods, merging the first stay points in the second time period based on the clustering manner of the neighbor clusters to obtain second stay points, includes:

and for each second time period, when the first stopping point in the second time period is one, taking the first stopping point as the corresponding second stopping point.

10. The method of claim 1, wherein the clustering the same second stay points in the first period into a cluster based on the clustering method of the neighbor clusters comprises:

determining a distance between every two second stay points in the first time period;

for each second stopping point, clustering the second stopping points and the second stopping points, the distance between which meets a set fourth distance threshold value, into a cluster based on a clustering mode of neighbor clustering, wherein the fourth distance threshold value is smaller than a third distance threshold value, and the third distance threshold value is used for indicating whether a plurality of first stopping points in each second time period can be combined into one second stopping point.

11. The method of claim 10, wherein the determining the distance between each two second dwell points during the first period of time comprises:

for each second stopping point, calculating average longitude and average latitude according to longitude and latitude information of each first stopping point corresponding to the second stopping point;

taking the average longitude and the average latitude as longitude and latitude information of the second stay point;

and determining the distance between every two second stay points according to the longitude and latitude information of every two second stay points.

12. The method according to any one of claims 1 to 11, wherein after said determining said second point of stay in said cluster as a first residence, the method further comprises:

assigning a residence label to each of the first residents determined in the first time period;

after determining a second resident in a third time period according to signaling data recorded in the third time period based on a distance mode of neighbor clustering, determining a distance between the second resident and each first resident for each second resident, wherein the third time period is the same as the first time period in duration;

For each of the second residents, assigning the second residents the same resident tag as the first residents when there is the first residents whose distance from the second residents meets a set fifth distance threshold.

13. An electronic device, the electronic device comprising: a memory and a processor, the memory and the processor coupled; the memory stores program instructions that, when executed by the processor, cause the electronic device to perform the method of identifying a premises according to any of claims 1 to 12.

14. A computer readable storage medium comprising a computer program which, when run on an electronic device, causes the electronic device to perform the method of identifying a premises according to any of claims 1 to 12.