A method for evaluating the location confidence of resident users based on spatio-temporal big data

Abstract

The present application discloses a method for evaluating the location confidence of resident users based on spatio-temporal big data, which relates to the field of wireless communication technologies and includes: obtaining measurement report data, and determining each target cell identifier associated with the user number from the data; for any target cell identifier, determining the corresponding cell longitude and latitude and the average time advance from the data, and determining the candidate user residence area according to the cell longitude and latitude and the average time advance; after traversing each target cell identifier, determining the user's permanent residence area based on each candidate user residence area; determining the longitude and latitude of each target user corresponding to the user number from the data, and determining the permanent location among the longitude and latitude of each target user according to the longitude and latitude of each target user and the user's permanent residence area. The present application comprehensively considers multi-dimensional information such as the user's geographical location, communication behavior, and time advance, accurately identifies the user's permanent residence area, and improves the accuracy and reliability of the evaluation of the user's permanent location.

Description

Technical Field

[0001] The present application relates to the field of wireless communication technologies, and in particular, to a method, apparatus, electronic device, and storage medium for evaluating the location confidence of resident users based on spatio-temporal big data. Background Art

[0002] Spatio-temporal big data (also known as geospatial big data) is data with both time and space attributes, including three-dimensional information such as time, space, and thematic attributes. In real life, 80% of the data directly or indirectly has spatio-temporal attributes. When the amount of spatio-temporal data reaches a certain scale, it can be defined as spatio-temporal big data. Spatio-temporal big data exhibits basic characteristics such as massive volume, multi-source heterogeneity, and dynamic variability. All data is generated in a specific time and space context and is directly or indirectly labeled with time and location tags. Therefore, in essence, generalized big data can be considered to have the same attributes as spatio-temporal big data. It is the "sum" of datasets with the characteristics of quantity, quality, and time variation of (phenomena) in the spatial structure and spatial relationships of the real geographical world. Therefore, spatio-temporal big data has information characteristics in three dimensions: time, space, and attributes, and also has the four characteristics of big data: massive data scale, fast data flow, diverse data types, and low value density. Therefore, spatio-temporal data is increasingly becoming the core driving force for the economic operation mechanism, social lifestyle, and the development of various industries. Using data mining techniques, it is possible to find patterns from the "space", "time", and "dynamics" dimensions of things under a unified spatio-temporal benchmark, mine useful information from massive big data, explore potential associations between data, objectively analyze hidden and easily overlooked factors, and provide value-added applications of spatio-temporal big data to decision-makers.

[0003] Based on massive spatio-temporal big data, mining the resident users in a city or region to identify the population distribution characteristics and commuting characteristics of the region is a research hotspot of spatio-temporal big data. At present, many enterprises, including communication operators, have conducted a large number of studies. Based on operator spatio-temporal big data, the mainstream method for mining resident users is as follows: using 4G and 5G signaling data, counting the residence situation of operator users under different base station cells, and based on multi-day data, cumulatively counting the residence days under different base station cells. Then, select the top n base station cells with the most residence days as the resident base station cells of the user, and then based on the MR (Measurement Report) data under the resident base station cells, perform fingerprint positioning and location clustering to determine the accurate resident location of the user, with an average positioning accuracy of 50-100 meters. Due to the complexity of people's living patterns, simply using the residence days cannot accurately identify the resident location of users. For example, a certain user often goes out at 22:00 at night to run around the community. The base station cells where he stays during this period cannot be counted as the resident cells when he is at home, otherwise it will affect the accuracy of the positioning of his home residence (it may be located in the running area). Therefore, using the residence days cannot accurately identify the resident location of users, but only a candidate set of resident cells, and technical means are needed to further distinguish the resident location of users.

[0004] Therefore, how to improve the accuracy of evaluating the resident location of users is an urgent problem to be solved at present. Summary of the Invention

[0005] The main purpose of this application is to provide a method, device, electronic device and storage medium for evaluating the confidence level of the resident user location based on spatio-temporal big data, aiming to solve the technical problem of how to improve the accuracy of evaluating the resident location of users.

[0006] To achieve the above object, this application proposes a method for evaluating the confidence level of the resident user location based on spatio-temporal big data. The method for evaluating the confidence level of the resident user location based on spatio-temporal big data includes:

[0007] Obtain measurement report data, and determine each target cell identifier associated with the user number from the measurement report data;

[0008] For any one target cell identifier, determine the cell longitude and latitude corresponding to the target cell identifier from the measurement report data, and the average time advance amount of the communication between the cell corresponding to the target cell identifier and the device corresponding to the user number, and determine the candidate user residence area corresponding to the user number under the target cell identifier according to the cell longitude and latitude and the average time advance amount;

[0009] After traversing each target cell identifier, determine the user's permanent residence area of the user number based on the residence areas of each candidate user;

[0010] Determine the longitude and latitude of each target user corresponding to the user number from the measurement report data, and determine the permanent location among the longitude and latitude of each target user according to the longitude and latitude of each target user and the user's permanent residence area.

[0011] In one embodiment, the step of determining each target cell identifier associated with the user number from the measurement report data includes:

[0012] Determine each candidate cell identifier having a communication relationship with the user number from the measurement report data, and obtain the number of communication days and the communication duration of the communication relationship between each candidate cell identifier and the user number within a preset time period;

[0013] Determine each target cell identifier among the candidate cell identifiers based on each communication day and each communication duration, where each target cell identifier is a set of candidate cell identifiers that have the most communication days and the longest communication duration in the candidate cell identifiers having a communication relationship with the user number.

[0014] In one embodiment, the step of determining the candidate residence area of the user number corresponding to the target cell identifier according to the cell longitude and latitude and the average time advance amount includes:

[0015] Calculate the candidate residence area range corresponding to the target cell identifier under the user number based on the average time advance amount and the preset error amount;

[0016] Determine the candidate residence area according to the cell longitude and latitude and the candidate residence area range.

[0017] In one embodiment, the step of determining the user's permanent residence area of the user number based on each candidate user's residence area includes:

[0018] Perform density clustering on each candidate user's residence area to obtain multiple clustering results;

[0019] Determine the target clustering result among the clustering results based on the number of candidate user residence areas included in each clustering result, and use the target clustering result as the user's permanent residence area of the user number, where the target clustering result is the clustering result with the largest number of candidate user residence areas included in the clustering results.

[0020] In one embodiment, the step of determining the permanent location among the longitude and latitude of each target user according to the longitude and latitude of each target user and the user's permanent residence area includes:

[0021] Determine the valid positions in the longitude and latitude of each target user based on the user's resident area, where the valid positions are the longitude and latitude of the target users within the user's resident area among the longitude and latitude of each target user;

[0022] Screen the valid positions, and use the screened valid positions as the resident positions in the longitude and latitude of each target user.

[0023] In one embodiment, the step of screening the valid positions includes:

[0024] For any one valid position, determine the valid area in the user's resident area that covers the valid position, and obtain the number of such valid areas;

[0025] After traversing each valid position, determine the target valid positions among the valid positions based on the numbers of the valid areas, and use the target valid positions as the screened valid positions, where the target valid positions are the valid positions with the number of valid areas greater than or equal to the index number.

[0026] In one embodiment, before the step of determining the target valid positions among the valid positions based on the numbers of the valid areas, it further includes:

[0027] Determine the maximum number among the numbers of the valid areas, and generate the index number based on the difference between the maximum number and the preset parameter.

[0028] In addition, to achieve the above object, the present application also proposes a device for evaluating the confidence level of the resident user's position. The device for evaluating the confidence level of the resident user's position includes:

[0029] A data acquisition module, configured to acquire measurement report data, and determine each target cell identifier associated with the user number from the measurement report data;

[0030] A first screening module, configured to, for any one target cell identifier, determine the cell longitude and latitude corresponding to the target cell identifier and the average time advance of communication between the cell corresponding to the target cell identifier and the device corresponding to the user number from the measurement report data, and determine the candidate user resident area corresponding to the user number under the target cell identifier according to the cell longitude and latitude and the average time advance;

[0031] A second screening module, configured to, after traversing each target cell identifier, determine the user's resident area of the user number based on each candidate user resident area;

[0032] A third screening module, configured to determine the longitude and latitude of each target user corresponding to the user number from the measurement report data, and determine the resident locations among the longitude and latitude of each target user according to the longitude and latitude of each target user and the user's resident area.

[0033] In addition, to achieve the above object, the present application further provides an electronic device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the method for evaluating the confidence of the resident user location based on spatio-temporal big data as described above.

[0034] In addition, to achieve the above object, the present application further provides a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the method for evaluating the confidence of the resident user location based on spatio-temporal big data as described above are implemented.

[0035] In addition, to achieve the above object, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the method for evaluating the confidence of the resident user location based on spatio-temporal big data as described above are implemented.

[0036] One or more technical solutions proposed by the present application have at least the following technical effects:

[0037] This application first obtains measurement report data and determines each target cell identifier associated with the user number from the measurement report data, thereby collecting communication behavior data through data acquisition and providing effective basic data support for subsequent analysis of the user's resident location. For any target cell identifier, the cell longitude and latitude corresponding to the target cell identifier and the average time advance of communication between the cell corresponding to the target cell identifier and the device corresponding to the user number are determined from the measurement report data. Based on the cell longitude and latitude and the average time advance, the candidate user residence area corresponding to the user number under the target cell identifier is determined, thereby realizing the association between the user's communication behavior and the specific geographical location through data association and spatial analysis, and preliminarily screening out the possible resident areas of the user, improving the accuracy of positioning. After traversing each target cell identifier, the user's resident area corresponding to the user number is determined based on each candidate user residence area, thereby identifying the most likely resident area of the user from multiple candidate residence areas and further improving the accuracy of the user's resident location evaluation. The target user longitudes and latitudes corresponding to the user number are determined from the measurement report data, and the resident location among the target user longitudes and latitudes is determined based on the target user longitudes and latitudes and the user's resident area, thereby realizing the determination of the location point that most conforms to the resident characteristics from the user's location data and providing more accurate resident location information.

[0038] In summary, through data acquisition, correlation analysis, and spatial positioning, this application comprehensively considers multi-dimensional information such as the user's geographical location, communication behavior, and time advance, avoiding the problem of inaccurate positioning caused by relying solely on the residence days and communication duration to determine the user's resident location, realizing the precise identification of the user's resident area from complex spatio-temporal data, thereby improving the accuracy and reliability of the user's resident location evaluation, and further achieving the effect of enhancing the application value of spatio-temporal big data. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0040] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0041] Figure 1 FIG. 15 is a schematic flowchart provided for Embodiment 1 of the method for evaluating the confidence level of the resident user location based on spatio-temporal big data according to the present application;

[0042] Figure 2 It is a schematic diagram of the first scenario of the method for evaluating the confidence level of the location of resident users based on spatio-temporal big data provided in the first embodiment of the present application;

[0043] Figure 3 It is a schematic diagram of the second scenario of the method for evaluating the confidence level of the location of resident users based on spatio-temporal big data provided in the first embodiment of the present application;

[0044] Figure 4 It is a schematic flowchart provided in the second embodiment of the method for evaluating the confidence level of the location of resident users based on spatio-temporal big data of the present application;

[0045] Figure 5 It is a schematic flowchart of the method for evaluating the confidence level of the location of resident users based on spatio-temporal big data provided in the second embodiment of the present application;

[0046] Figure 6 It is a schematic diagram of the module structure of the device for evaluating the confidence level of the location of resident users based on spatio-temporal big data in the embodiment of the present application;

[0047] Figure 7 It is a schematic diagram of the device structure of the hardware operating environment involved in the method for evaluating the confidence level of the location of resident users based on spatio-temporal big data in the embodiment of the present application.

[0048] The realization of the purpose, functional features and advantages of the present application will be further described in conjunction with the embodiments with reference to the accompanying drawings. Specific Embodiments

[0049] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0050] For a better understanding of the technical solutions of the present application, the following will be described in detail in conjunction with the accompanying drawings of the specification and specific embodiments.

[0051] The main solution of the embodiment of the present application is as follows: Obtain measurement report data, and determine each target cell identifier associated with the user number from the measurement report data; for any one target cell identifier, determine the cell longitude and latitude corresponding to the target cell identifier from the measurement report data, and the average time advance of the communication between the cell corresponding to the target cell identifier and the device corresponding to the user number, and determine the candidate user residence area corresponding to the user number under the target cell identifier according to the cell longitude and latitude and the average time advance; after traversing each target cell identifier, determine the user's regular residence area based on each candidate user residence area; determine each target user longitude and latitude corresponding to the user number from the measurement report data, and determine the regular residence position among the target user longitudes and latitudes according to the target user longitudes and latitudes and the user's regular residence area.

[0052] Since the prior art uses 4G and 5G signaling data to count the residence situations of operator users in different base station cells, and based on multi-day data, accumulatively counts the residence days in different base station cells. Then, select the top n base station cells with the most residence days as the user's regular residence base station cells, and then perform fingerprint positioning and location clustering based on the MR (Measurement Report) data under the regular residence base station cells to determine the user's accurate regular residence position, and the average positioning accuracy is 50-100 meters. Due to the complexity of people's living patterns, simply using the residence days cannot accurately identify the user's regular residence position, but only a candidate set of regular residence cells, and technical means are needed to further distinguish the user's regular residence position. Therefore, how to improve the accuracy of evaluating the user's regular residence position is an urgent problem to be solved at present.

[0053] The present application provides a solution. By performing data collection, correlation analysis, and spatial positioning, it comprehensively considers multi-dimensional information such as the user's geographical location, communication behavior, and time advance, avoids the problem of inaccurate positioning caused by relying solely on residence days and communication duration to judge the user's regular residence position, realizes the accurate identification of the user's regular residence area from complex spatio-temporal data, thereby improving the accuracy and reliability of the evaluation of the user's regular residence position, and further achieving the effect of enhancing the application value of spatio-temporal big data.

[0054] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of implementing the above functions. Hereinafter, an electronic device is taken as an example to illustrate this embodiment and the following embodiments.

[0055] Based on this, the embodiment of the present application provides a method for evaluating the confidence level of the position of a regular user based on spatio-temporal big data, referring toFigure 1 , Figure 1 This is a schematic flowchart of the first embodiment of the method for evaluating the location confidence of resident users based on spatio-temporal big data in this application.

[0056] In this embodiment, the method for evaluating the location confidence of resident users based on spatio-temporal big data includes steps S10 to S40:

[0057] Step S10: Obtain measurement report data, and determine each target cell identifier associated with the user number from the measurement report data;

[0058] It should be noted that the measurement report data refers to a series of information collected from the mobile communication network, including the user number, the longitude and latitude of the user's geographical location, the cell identifier, the longitude and latitude of the cell's geographical location, and the statistical indicators of the user's communication behavior in the cell (such as keywords like the average signal strength RSRP, the average signal quality RSRQ, and the average time advance TADV (abbreviated as TA)). Among them, the cell identifier refers to the code used to uniquely identify a wireless coverage area in the mobile communication network. This code can be the evolved universal terrestrial radio access network cell identifier (ECI, E-UTRAN Cell Identifier), or the global cell identifier of the cell (CGI, Cell Global Identifier), or other forms of identifiers. The average time advance TA refers to the amount of time to send a signal in advance to compensate for the signal propagation time in wireless communication. This amount of time is the average value calculated based on the communication behavior between the user and the base station. Since the speed of electromagnetic waves is constant, TA also reflects the distance between the user and the base station. In 4G, the distance represented by a unit TA is approximately 78 meters; in 5G, the distance of a unit TA is related to the subcarrier. Currently, the subcarrier spacing of each operator is mostly 30 kHz, and the distance of a unit TA is about 39 meters. The target cell identifier refers to the cell identifier associated with a specific user number, that is, the cell where the user has activity records.

[0059] It can be understood that due to the complexity of people's living patterns, simply using the number of days of residence cannot accurately identify the resident location of users. It only identifies a candidate set of resident cells. It is necessary to use technical means to further distinguish the resident location of users. Therefore, step S10 is carried out. By collecting the activity information of users in the mobile network (i.e., the measurement report data), the problem of being unable to accurately analyze user behavior due to the lack of detailed user data can be avoided, thus providing a detailed data basis for user behavior and location analysis.

[0060] In a feasible implementation manner, the step of determining each target cell identifier associated with the user number from the measurement report data in step S10 may include steps S11 to S12:

[0061] Step S11: Determine each candidate cell identifier that has a communication relationship with the user number from the measurement report data, and obtain the number of communication days and the communication duration during which each candidate cell identifier has a communication relationship with the user number within a preset time period.

[0062] It should be noted that the candidate cell identifier refers to the identifiers of all cells that have communication records with a specific user number within a preset time period; the number of communication days refers to the total number of days during which a communication behavior occurs between the user number and the candidate cell identifier within a preset time period; the communication duration refers to the total time length of communication between the user number and the candidate cell identifier within a preset time period.

[0063] It can be understood that in order to identify in which cells the user has had communication behaviors, as well as the frequency and duration of these communication behaviors, step S11 is performed, which can avoid the problem of being unable to accurately determine the user's main activity cell, thereby initially screening out the cells where the user may frequently be active.

[0064] Exemplarily, extract all communication records of the user number within a preset time period from the measurement report data in the network-side database; then, through data screening, identify the cell identifiers that have communication behaviors with the user number, and these are the candidate cell identifiers; then, count the number of communication days and the communication duration between each candidate cell identifier and the user number, which can be obtained through database query and calculation.

[0065] Step S12: Determine each target cell identifier among the candidate cell identifiers based on each communication day and each communication duration, where each target cell identifier is a set of candidate cell identifiers that have the most communication days and the longest communication duration among the candidate cell identifiers that have a communication relationship with the user number.

[0066] It can be understood that since it is necessary to further determine the cell where the user is most likely to reside from the candidate cells, step S12 is performed, which can avoid the problem of ignoring the user's residence time when judging only based on the number of communications, thereby achieving the effect of being able to more accurately identify the user's resident cell.

[0067] Exemplarily, first, sort the communication days and communication durations of each candidate cell identifier. Then, according to a preset threshold or rule, select the cell identifier with the most communication days and the longest communication duration as the target cell identifier. This process can be achieved by writing an algorithm. The algorithm can comprehensively consider the weights of communication days and communication durations, or give priority to communication days. When the communication days are the same, then consider the communication duration. For example, sort the candidate cell identifiers from high to low according to communication days and communication durations. For a given candidate cell quantity threshold n, take the top n candidate cell identifiers as the target cell identifiers, and these identifiers represent the cells where the user is most likely to reside permanently.

[0068] In this embodiment, by deeply analyzing the user's communication records, the communication behavior frequencies and time lengths of the user in each cell are counted, so as to screen out the candidate cell identifier with the most communication days and the longest communication duration as the target cell identifier, avoiding the problem of being unable to accurately judge the main activity cell of the user, improving the accuracy of identifying the user's permanently resident cell, and achieving the effect of accurately identifying the user's permanently resident cell.

[0069] Step S20, for any one target cell identifier, determine the cell longitude and latitude corresponding to the target cell identifier from the measurement report data, and the average time advance of the communication between the cell corresponding to the target cell identifier and the device corresponding to the user number, and determine the candidate user residence area corresponding to the user number under the target cell identifier according to the cell longitude and latitude and the average time advance;

[0070] It should be noted that the candidate user residence area refers to the area where the user may stay for a long time initially judged according to the user's communication behavior and the geographical location information of the cell.

[0071] It can be understood that in order to associate the user behavior with a specific cell, step S20 is performed, which can avoid the problem of inaccurate position judgment caused by the inability to associate the user with a specific cell, and achieve the effect of accurately identifying the user's activities in different cells.

[0072] Exemplarily, first, extract all communication records of a specific user number from the measurement report data; then, through data screening, identify all cell identifiers involved in the communication process of this user number, and these identifiers are the target cell identifiers. Next, for each target cell identifier, search for and extract the corresponding cell longitude and latitude information from the measurement report data, and the average time advance of this user number in this cell. Finally, combine the cell longitude and latitude and the average time advance, and through a certain algorithm model, such as weighted average or clustering analysis, calculate the candidate user residence area of this user number under each target cell identifier.

[0073] In a feasible implementation manner, the step of determining the candidate user residence area corresponding to the user number under the target cell identifier according to the cell longitude and latitude and the average timing advance in step S20 may include steps S21 to S22:

[0074] Step S21, based on the average timing advance and a preset error amount, calculate the candidate residence area range corresponding to the target cell identifier under the user number;

[0075] It should be noted that the candidate residence area range refers to a geographical area calculated according to the communication behavior characteristics of the user in the target cell (such as the average timing advance) and a preset error amount, and this area is used to represent the possible activity range of the user within the target cell.

[0076] It can be understood that in order to estimate the possible physical location residence range of the user, step S21 is performed. By estimating the possible physical location range according to the communication behavior characteristics of the user in the cell, the problem of inaccurate service positioning caused by the inability to accurately determine the user location can be avoided, thereby providing a more accurate estimate of the user activity range.

[0077] Exemplarily, please refer to Figure 2 , the figure shows the candidate residence area ranges corresponding to four different cells. By analyzing the average timing advance TA of the user in the target cell and combining it with the preset error amount Ω, a circular ring area is calculated, and this area is the candidate residence area range. The inner diameter of this circular ring area is (TA - Ω) * unit TA distance, and the outer diameter is (TA + Ω) * unit TA distance, indicating that the candidate residence area range is between the circular range where the outer diameter is located and the circular range where the inner diameter is located.

[0078] Step S22, according to the cell longitude and latitude and the candidate residence area range, determine the candidate residence area.

[0079] It can be understood that since the calculated theoretical range cannot be directly applied to the actual location determination process, step S22 is performed. By combining the calculated theoretical range with the actual geographical information to determine the possible residence area of the user, the problem of ignoring the actual geographical environment by simply relying on theoretical calculations can be avoided, thereby ensuring the actual operability of the candidate residence area.

[0080] Exemplarily, using the longitude and latitude information of the cell, map the calculated candidate residence area range to the actual map, and the regional boundary can be adjusted and optimized through GIS tools to ensure that the area covers the actual locations where the user may be active, such as residences, workplaces, etc.

[0081] In this embodiment, by combining the user's communication behavior data and geographical information, the possible resident areas of the user are calculated and mapped to the actual geographical locations, avoiding the problem of being unable to accurately determine the user's activity range and achieving the effect of accurately depicting the user's resident areas.

[0082] Step S30: After traversing each target cell identifier, determine the user's regular resident area of the user number based on each candidate user resident area;

[0083] It should be noted that the user's regular resident area refers to the area where the user often activities, which is finally determined by analyzing the user's long-term communication behavior and location information.

[0084] It can be understood that in order to determine the area where the user most often activities from multiple possible resident areas, step S30 is performed, which can avoid the problem that the simple statistics fails to reflect the user's true activity area, thus achieving the effect of accurately depicting the user's regular activity area.

[0085] Exemplarily, after traversing all target cell identifiers and their corresponding candidate user resident areas, comprehensive analysis is performed on these areas. For example, by the method of time weighting, considering the length of time the user stays in different cells, or using spatial clustering analysis to merge adjacent candidate areas. Finally, according to the residence frequency and time length of the user in each cell, determine the area where the user most frequently and for a long time stays, that is, the user's regular resident area.

[0086] In a feasible embodiment, the step of determining the user's regular resident area of the user number based on each candidate user resident area in step S30 may include steps S31 to S32:

[0087] Step S31: Perform density clustering on each candidate user resident area to obtain multiple clustering results;

[0088] It should be noted that the clustering result refers to the grouping obtained by performing density clustering analysis on the candidate user resident area, and each grouping contains a set of candidate user resident areas that are geographically close to each other.

[0089] It can be understood that in order to identify the main activity area of the user from a large number of candidate resident areas, step S31 is performed, which can avoid the problem that it is impossible to effectively identify the user's regular resident area due to the dispersion of candidate resident areas, and achieves the effect of making the user's activity range more focused and specific through clustering analysis.

[0090] Exemplarily, a density clustering algorithm (such as DBSCAN) can be used to perform clustering analysis on the candidate user residence areas. The algorithm will automatically divide the clusters according to the density and distance between the areas without the need to preset the number of clusters in advance; alternatively, the candidate user residence areas with intersections can be clustered.

[0091] Step S32: Based on the number of candidate user residence areas included in each clustering result, determine the target clustering result among the various clustering results, and use the target clustering result as the user's permanent residence area corresponding to the user number. Among them, the target clustering result is the clustering result with the largest number of candidate user residence areas included in the various clustering results.

[0092] It should be noted that the target clustering result refers to the clustering result with the largest number of candidate user residence areas among each group of clustering results, and this clustering result represents the area where the user is most active.

[0093] It can be understood that in order to select the clustering that best represents the user's permanent behavior from multiple clustering results, step S32 is performed, which can avoid the problem of being unable to accurately describe the user's permanent residence area due to selecting the wrong clustering result, thereby ensuring that the selected user's permanent residence area is the residence area that most conforms to the user's actual activity pattern.

[0094] Exemplarily, count the number of candidate user residence areas included in each clustering result, and select the clustering result with the largest number as the target clustering result. This clustering result is the user's permanent residence area because it represents the area where the user is most frequently and intensively active.

[0095] In this embodiment, by performing density clustering analysis and combining quantity statistics, the problem of being unable to accurately identify the user's main activity area due to the dispersion of user residence area data is avoided, and the effect of accurately determining the user's permanent residence area from a large number of candidate residence areas is achieved. This method performs density clustering on the candidate residence areas, identifies the area where the user's activities are most intensive, and selects the clustering result containing the largest number of candidate residence areas as the target clustering result, thereby ensuring that the identification of the user's permanent residence area is more in line with the user's actual behavior pattern, laying a foundation for providing personalized services and optimizing network resources.

[0096] Step S40: Determine the respective target user latitudes and longitudes corresponding to the user number from the measurement report data, and determine the permanent location among the respective target user latitudes and longitudes based on the respective target user latitudes and longitudes and the user's permanent residence area.

[0097] It should be noted that the target user's longitude and latitude refer to the longitude and latitude information extracted from the measurement report data associated with a specific user number; the resident location refers to the specific location point within the user's resident area, and this location point is determined by the user's longitude and latitude data.

[0098] It can be understood that in order to find the true specific location of the user from the longitude and latitude data within the large number of user resident areas, step S40 is carried out, which can avoid the problem of being unable to provide personalized services due to the lack of accurate information, thus providing effective basic data support for providing more accurate location-related services to users.

[0099] Exemplarily, all the user longitude and latitude data associated with a specific user number are screened out from the measurement report data, and these data points are the target user's longitude and latitude; then, through data analysis, the part that overlaps with the user's resident area among these data points is identified as the specific resident location of the user within the resident area.

[0100] In a feasible implementation manner, the step of determining the resident location in the respective target user longitudes and latitudes according to the respective target user longitudes and latitudes and the user's resident area in step S40 may include steps S41 to S42:

[0101] Step S41, determining the valid locations in the respective target user longitudes and latitudes based on the user's resident area, where the valid locations are the target user longitudes and latitudes within the user's resident area among the respective target user longitudes and latitudes;

[0102] It should be noted that the valid location refers to the specific longitude and latitude location of the user within the resident area, and these locations reflect the user's activities within the resident area.

[0103] It can be understood that since it is necessary to screen out those locations from the target user longitudes and latitudes that truly represent the user's resident activities, step S41 is carried out, which can avoid the problem of misidentifying the longitudes and latitudes where the user occasionally appears as the resident location, thus ensuring that the determined location information conforms to the user's actual resident behavior.

[0104] Exemplarily, the target user longitude and latitude data are compared with the boundaries of the user's resident area, and the longitude and latitude points located within the user's resident area are screened out, and these points are the valid locations. Please refer to Figure 3 , Figure 3 Points 1, 2, 3, 4, 5 in are the respective target user longitudes and latitudes. Among them, the area of cell 4 where user longitude and latitude 5 is located is not the user's resident area, so user longitude and latitude 5 is not a valid location, and user longitude and latitude 1 is not within the user's resident area, so user longitude and latitude 1 is also not a valid location. Therefore, only user longitudes and latitudes 2, 3, 4 are within the user area and are valid locations.

[0105] Step S42, screen the valid locations, and use the screened valid locations as the resident locations in the longitude and latitude of each target user.

[0106] It can be understood that since it is necessary to further exclude noise and abnormal data from the valid locations to obtain a more accurate user resident location, performing step S41 can avoid the problem of inaccurate resident locations caused by abnormal values in the valid location data, thereby improving the accuracy and reliability of user resident location recognition.

[0107] Exemplarily, perform statistical analysis on the screened valid locations, such as removing abnormal values that deviate from most data points, or using time series analysis to identify the locations where the user appears most frequently. The finally determined location where the user appears most frequently is the user's resident location.

[0108] In this embodiment, by first determining the valid locations within the user's resident area and then further screening and optimizing these locations, it is ensured that the finally determined resident location can truly reflect the user's daily activity pattern, avoiding the problem of inaccurate resident location judgment due to including the user's occasional activities or abnormal data, ensuring that the finally determined resident location can truly reflect the user's daily activity pattern, and achieving the effect of accurately identifying the user's main activity area and determining its resident location.

[0109] This embodiment provides a method for evaluating the confidence level of the location of resident users based on spatio-temporal big data. By performing data collection, association analysis, and spatial positioning, it comprehensively considers multi-dimensional information such as the user's geographical location, communication behavior, and time lead, avoiding the problem of inaccurate positioning caused by relying solely on the number of days of residence and communication duration to determine the user's resident location, achieving the accurate identification of the user's resident area from complex spatio-temporal data, thereby improving the accuracy and reliability of user resident location evaluation, and further achieving the effect of enhancing the application value of spatio-temporal big data.

[0110] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar content as in the above-mentioned embodiment one can be referred to the above introduction and will not be repeated hereinafter. On this basis, please refer to Figure 4 , step S42 may further include steps S421 to S422:

[0111] Step S421, for any one valid location, determine the valid area in the user's resident area that covers the valid location, and obtain the number of the valid areas;

[0112] It should be noted that the valid area refers to a sub-area in the user's resident area that covers a specific valid location, and this sub-area represents the activity range of the user near this location.

[0113] It is understandable that since it is necessary to evaluate the representativeness of each valid position within the user's resident area, step S421 is carried out, which can avoid the problem of judging the user's activity pattern based on a single position point, thereby more comprehensively understanding the activity distribution of the user within the resident area.

[0114] Exemplarily, for each valid position, calculate how many valid areas in the user's resident area cover this position, so as to obtain the number of valid areas. For example, please refer to Figure 3 , the following Table 1 can be obtained:

[0115] Table 1

[0116]

[0117] In Table 1, it is shown that the valid areas covering the valid position 2 are the user's resident areas corresponding to Community 1 and Community 2, and the number of valid areas is 2; the valid areas covering the valid position 3 are the user's resident areas corresponding to Community 1, Community 2, and Community 3, and the number of valid areas is 3; the valid area covering the valid position 4 is the user's resident area corresponding to Community 1, and the number of valid areas is 1.

[0118] Step S422, after traversing each valid position, determine the target valid position among each valid position based on the number of each valid area, and use the target valid position as the filtered valid position, where the target valid position is a valid position whose number of valid areas is greater than or equal to the index number.

[0119] It should be noted that the target valid position refers to those valid positions that are covered by multiple valid areas and the coverage quantity reaches or exceeds the preset index number. These positions are considered the most frequent and stable activity points of the user.

[0120] It is understandable that since it is necessary to identify the most representative positions from multiple valid positions, step S422 is carried out, which can avoid the problem that invalid positions caused by random or accidental activities are misjudged as resident positions, thereby improving the accuracy and stability of the user's resident positions.

[0121] Exemplarily, after traversing all valid positions and calculating the number of their respective valid areas, set an index number as the threshold. Only when the number of valid areas is greater than or equal to this threshold, the corresponding valid position is determined as the target valid position. These target valid positions are then used as the filtered valid positions to represent the user's resident positions.

[0122] In this embodiment, by ensuring that only the positions covered by multiple valid regions can become target valid positions, the problem of inaccurate determination of the resident position caused by the inability of a single position point to accurately reflect the user's activity pattern is avoided. The effect of accurately identifying the resident position where the user is most frequently and stably active from multiple potential valid positions is achieved, thereby improving the reliability and accuracy of user resident position identification.

[0123] In a feasible implementation manner, before the step of determining the target valid position among the valid positions based on the number of each valid region in step S422, the method for evaluating the confidence level of the resident user position based on spatio-temporal big data may further include step S100:

[0124] Step S100: Determine the maximum number among the numbers of each of the valid regions, and generate the index number based on the difference between the maximum number and a preset parameter.

[0125] It can be understood that since a reasonable threshold needs to be set to distinguish the important positions where the user is frequently active from other positions where the user is occasionally active, step S100 is performed. Setting a reasonable threshold according to the data of the actual valid regions can avoid the problems of missing important positions or misjudging invalid positions caused by too strict or too loose threshold settings, thereby achieving the effect of accurately identifying the user's resident position.

[0126] Exemplarily, first, count the number of valid positions covered by all valid regions and find the maximum value among them; then, subtract a preset parameter (such as the average coverage number or a fixed threshold) from this maximum number to obtain the difference; finally, use this difference as the index number for subsequent screening of the target valid position. For example, if the maximum number is 3 and the preset parameter is 1, then the index number is 2. Only when the number of valid regions is greater than or equal to 2, the corresponding valid position will be selected as the target valid position. For example, referring to Table 1, only the numbers of the valid regions corresponding to valid position 2 and valid position 3 are greater than or equal to 2. Therefore, valid position 2 and valid position 3 can be used as the final resident positions.

[0127] In this implementation manner, by adopting the scheme of dynamic threshold setting, the problem of inaccurate identification of important positions caused by the inability of a fixed threshold to adapt to different user activity pattern differences is avoided, and the effect of flexibly determining the resident position according to the specific activity characteristics of the user is achieved.

[0128] Exemplarily, to help understand the implementation process of the method for evaluating the confidence level of the resident user position based on spatio-temporal big data obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 5 , Figure 5A brief process schematic diagram of a method for evaluating the location confidence of resident users based on spatio-temporal big data is provided. Specifically:

[0129] First, calculate the candidate set of resident cells according to the MR data, that is, determine each target cell identifier associated with the user number among each cell identifier; then perform validity screening on the calculated candidate set of resident cells, that is, screen and determine the user's resident area corresponding to the user number; finally, perform optimization of the location of the resident user, that is, screen the longitude and latitude of each target user according to the user's resident area to obtain the resident location among the longitude and latitude of each target user.

[0130] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the method for evaluating the location confidence of resident users based on spatio-temporal big data in this application. Any simple transformation in more forms based on this technical concept is within the protection scope of this application.

[0131] This application also provides a device for evaluating the location confidence of resident users. Please refer to Figure 6 The device for evaluating the location confidence of resident users includes:

[0132] A data acquisition module 10, configured to acquire measurement report data and determine each target cell identifier associated with the user number from the measurement report data;

[0133] A first screening module 20, configured to, for any one target cell identifier, determine the longitude and latitude of the cell corresponding to the target cell identifier and the average time advance of communication between the cell corresponding to the target cell identifier and the device corresponding to the user number from the measurement report data, and determine the candidate user residence area corresponding to the user number under the target cell identifier according to the longitude and latitude of the cell and the average time advance;

[0134] A second screening module 30, configured to, after traversing each target cell identifier, determine the user's resident area corresponding to the user number based on each candidate user residence area;

[0135] A third screening module 40, configured to determine the longitude and latitude of each target user corresponding to the user number from the measurement report data, and determine the resident location among the longitude and latitude of each target user according to the longitude and latitude of each target user and the user's resident area.

[0136] Optionally, the first screening module 20 is further configured to:

[0137] Determine each candidate cell identifier having a communication relationship with the user number from the measurement report data, and obtain the number of communication days and the communication duration of each candidate cell identifier having a communication relationship with the user number within a preset time period;

[0138] Determine each target cell identifier among the candidate cell identifiers based on each communication day count and each communication duration, where each target cell identifier is a set of candidate cell identifiers that have the most communication days with the user number and the longest communication duration among the candidate cell identifiers.

[0139] Optionally, the first screening module 20 is further configured to:

[0140] Calculate a candidate residence area range corresponding to the target cell identifier under the user number based on the average time advance and a preset error amount;

[0141] Determine the candidate residence area according to the cell longitude and latitude and the candidate residence area range.

[0142] Optionally, the second screening module 30 is further configured to:

[0143] Perform density clustering on each candidate user residence area to obtain multiple clustering results;

[0144] Determine a target clustering result among the clustering results based on the number of candidate user residence areas included in each clustering result, and use the target clustering result as the user's permanent residence area of the user number, where the target clustering result is the clustering result with the largest number of candidate user residence areas included among the clustering results.

[0145] Optionally, the third screening module 40 is further configured to:

[0146] Determine valid positions among the target user longitudes and latitudes based on the user's permanent residence area, where the valid positions are the target user longitudes and latitudes within the user's permanent residence area among the target user longitudes and latitudes;

[0147] Screen the valid positions and use the screened valid positions as the permanent residence positions among the target user longitudes and latitudes.

[0148] Optionally, the third screening module 40 is further configured to:

[0149] For any one valid position, determine a valid area in the user's permanent residence area that covers the valid position, and obtain the number of the valid areas;

[0150] After traversing each valid position, determine a target valid position among the valid positions based on the number of valid areas, and use the target valid position as the screened valid position, where the target valid position is a valid position with the number of valid areas greater than or equal to the index number.

[0151] Optionally, the third screening module 40 is further configured to:

[0152] Determine the maximum number among the quantities of the effective regions, and generate the index quantity based on the difference between the maximum number and a preset parameter.

[0153] The resident user location confidence evaluation device provided by this application adopts the resident user location confidence evaluation method based on spatio-temporal big data in the above embodiment, and can solve the technical problem of how to improve the accuracy of evaluating the resident location of a user. Compared with the prior art, the beneficial effects of the resident user location confidence evaluation device provided by this application are the same as those of the resident user location confidence evaluation method based on spatio-temporal big data provided by the above embodiment, and other technical features in the resident user location confidence evaluation device are the same as the features disclosed in the method of the above embodiment, and will not be elaborated here.

[0154] This application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the resident user location confidence evaluation method based on spatio-temporal big data in the first embodiment above.

[0155] Next, refer to Figure 7 , which shows a schematic structural diagram of an electronic device suitable for implementing the embodiments of this application. The electronic device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The electronic device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of this application.

[0156] As Figure 7As shown, the electronic device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the electronic device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the electronic device to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows an electronic device with various systems, it should be understood that it is not required to implement or have all the shown systems. Instead, more or fewer systems may be implemented or had.

[0157] Specifically, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are executed.

[0158] The electronic device provided by the present application adopts the method for evaluating the confidence of a resident user's location based on spatio-temporal big data in the above embodiments, and can solve the technical problem of how to improve the accuracy of evaluating the resident location of a user. Compared with the prior art, the beneficial effects of the electronic device provided by the present application are the same as those of the method for evaluating the confidence of a resident user's location based on spatio-temporal big data provided in the above embodiments, and other technical features in the electronic device are the same as those disclosed in the method of the previous embodiment, and will not be elaborated here.

[0159] It should be understood that each part disclosed in this application can be implemented by hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0160] As described above, the above are only specific embodiments of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all of them should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0161] This application provides a computer-readable storage medium with computer-readable program instructions (i.e., computer programs) stored thereon. The computer-readable program instructions are used to execute the method for evaluating the confidence level of the location of resident users based on spatio-temporal big data in the above embodiments.

[0162] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or combined with an instruction execution system or device. The program code contained on the computer-readable storage medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0163] The above computer-readable storage medium can be included in an electronic device; or it can exist separately without being assembled into the electronic device.

[0164] The above computer-readable storage medium carries one or more programs, which, when executed by an electronic device, cause the electronic device to: obtain measurement report data, and determine, from the measurement report data, each target cell identifier associated with a user number; for any one target cell identifier, determine, from the measurement report data, the longitude and latitude of the cell corresponding to the target cell identifier, and the average time advance of communication between the cell corresponding to the target cell identifier and the device corresponding to the user number, and determine, based on the longitude and latitude of the cell and the average time advance, a candidate user residence area corresponding to the user number under the target cell identifier; after traversing each target cell identifier, determine a user's regular residence area of the user number based on each candidate user residence area; determine, from the measurement report data, the longitude and latitude of each target user corresponding to the user number, and determine a regular residence position among the longitude and latitude of each target user based on the longitude and latitude of each target user and the user's regular residence area.

[0165] Computer program code for performing the operations of the present application may be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partially on the user's computer, execute as a stand-alone software package, execute partially on the user's computer and partially on a remote computer, or execute entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, by connecting through the Internet using an Internet service provider).

[0166] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0167] The modules involved in the embodiments described in the present application can be implemented in software or in hardware. In this case, the name of the module does not constitute a limitation on the unit itself in some cases.

[0168] The readable storage medium provided in the present application is a computer-readable storage medium, and the computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned method for evaluating the confidence level of a user's resident location based on spatio-temporal big data, which can solve the technical problem of how to improve the accuracy of evaluating the user's resident location. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as those of the method for evaluating the confidence level of a user's resident location based on spatio-temporal big data provided in the above embodiments, and will not be elaborated here.

[0169] The present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the steps of the method for evaluating the confidence level of a user's resident location based on spatio-temporal big data as described above.

[0170] The computer program product provided in the present application can solve the technical problem of how to improve the accuracy of evaluating the user's resident location. Compared with the prior art, the beneficial effects of the computer program product provided in the present application are the same as those of the method for evaluating the confidence level of a user's resident location based on spatio-temporal big data provided in the above embodiments, and will not be elaborated here.

[0171] The above are only some embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. A resident user location confidence assessment method based on spatiotemporal big data, characterized in that: The resident user location confidence assessment method based on spatiotemporal big data includes: Obtaining measurement report data, and determining each target cell identifier associated with the user number from the measurement report data; For any target cell identifier, determine the longitude and latitude of the cell corresponding to the target cell identifier, and the average time advance of communication between the cell corresponding to the target cell identifier and the device corresponding to the user number from the measurement report data, and calculate the candidate resident area range corresponding to the target cell identifier under the user number based on the average time advance and a preset error amount; Determine a candidate user residence area according to the cell longitude and latitude and the candidate residence area range, wherein the candidate user residence area is a circular area with the cell longitude and latitude as the center, the inner diameter of the circular area is the product of the difference between the average time advance and the preset error and the unit average time advance distance, and the outer diameter of the circular area is the product of the sum of the average time advance and the preset error and the unit average time advance distance; After traversing each target cell identifier, density clustering is performed on each candidate user residence area to obtain multiple clustering results; Based on the number of candidate user residence areas included in each clustering result, determine a target clustering result in each clustering result, and use the target clustering result as the user residence area of ​​the user number, wherein the target clustering result is the clustering result with the largest number of candidate user residence areas included in each clustering result; Determine the longitude and latitude of each target user corresponding to the user number from the measurement report data, and determine a valid position among the longitude and latitude of each target user based on the user's permanent area, wherein the valid position is the longitude and latitude of the target user in the user's permanent area among the longitude and latitude of each target user; For any valid location, determine the valid area covering the valid location in the user's permanent area, and obtain the number of the valid areas; Determining a maximum number among the numbers of the valid areas, and generating an indicator number based on a difference between the maximum number and a preset parameter; After traversing each valid position, a target valid position in each valid position is determined based on the number of each valid area, and the target valid position is used as the permanent position in the longitude and latitude of each target user, wherein the target valid position is a valid position where the number of valid areas is greater than or equal to the number of indicators.

2. The resident user location confidence assessment method based on spatiotemporal big data as claimed in claim 1, characterized in that: The step of determining each target cell identifier associated with the user number from the measurement report data comprises: Determine each candidate cell identifier having a communication relationship with the user number from the measurement report data, and obtain the number of communication days and communication duration during which each candidate cell identifier has a communication relationship with the user number within a preset time period; The target cell identifiers among the candidate cell identifiers are determined based on the communication days and the communication durations, wherein the target cell identifiers are a collection of candidate cell identifiers among the candidate cell identifiers, which have the most communication days and the longest communication duration with the user number.

3. A resident user location confidence assessment device, characterized in that: The resident user position confidence assessment device comprises: A data acquisition module, used to acquire measurement report data and determine each target cell identifier associated with the user number from the measurement report data; A first screening module is used to determine, for any target cell identifier, the longitude and latitude of the cell corresponding to the target cell identifier and the average time advance of communication between the cell corresponding to the target cell identifier and the device corresponding to the user number from the measurement report data, and calculate the candidate resident area range corresponding to the target cell identifier under the user number based on the average time advance and the preset error amount; determine the candidate user resident area according to the longitude and latitude of the cell and the candidate resident area range, wherein the candidate user resident area is a circular area with the longitude and latitude of the cell as the center, the inner diameter of the circular area is the product of the difference between the average time advance and the preset error amount and the unit average time advance distance, and the outer diameter of the circular area is the sum of the average time advance and the preset error amount and the unit average time advance distance. A second screening module is used to perform density clustering on each candidate user residence area after traversing each target cell identifier to obtain multiple clustering results; based on the number of candidate user residence areas included in each clustering result, determine a target clustering result in each clustering result, and use the target clustering result as the user residence area of ​​the user number, wherein the target clustering result is the clustering result with the largest number of candidate user residence areas included in each clustering result; The third screening module is used to determine the longitude and latitude of each target user corresponding to the user number from the measurement report data, and determine the valid position in the longitude and latitude of each target user based on the user's permanent area, wherein the valid position is the longitude and latitude of the target user in the user's permanent area; for any valid position, determine the valid area covering the valid position in the user's permanent area, and obtain the number of the valid areas; determine the maximum number of the numbers of each valid area, and generate an index number based on the difference between the maximum number and a preset parameter; after traversing each valid position, determine the target valid position in each valid position based on the number of each valid area, and use the target valid position as the permanent position in the longitude and latitude of each target user, wherein the target valid position is a valid position whose number of valid areas is greater than or equal to the index number.

4. An electronic device, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for assessing the confidence of resident user locations based on spatiotemporal big data as described in any one of claims 1 to 2.

5. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for assessing the confidence of resident user locations based on spatiotemporal big data as described in any one of claims 1 to 2 are implemented.

Images