Track data characterization method and device

Abstract

The invention discloses a characterization method and device of trajectory data. The method comprises: acquiring a plurality of pieces of trajectory data, each of the plurality of pieces of trajectory data comprising a plurality of time periods, and a feature signal collected in each of the plurality of time periods (S310); generating a plurality of position points and the attribute of each position point in the plurality of position points based on the plurality of pieces of trajectory data; wherein the plurality of position points comprise a first position point, the first position point corresponds to one or more time periods in the plurality of track data, the combination identifier of each time period in the one or more time periods is the same, and the combination identifier of each time period is generated by the identifier ID of at least one feature signal corresponding to each time period. The attribute of the first position point comprises the number of each type of feature signals and / or the number distribution feature of each type of feature signals in one or more time periods (S320). The storage space of the track data can be effectively saved; meanwhile, the system can be compatible with the format of outdoor data, and indoor and outdoor data integration is achieved.

Description

Trajectory data representation method and device Technical Field

[0001] The present application relates to the field of indoor and outdoor positioning technology, and in particular to a method and device for characterizing trajectory data. Background Art

[0002] The proliferation of mobile devices and the development of mobile communication technologies have opened up new possibilities for positioning and navigation. For example, the Global Navigation Satellite System (GNSS) chips integrated into mobile devices can provide users with precise outdoor positioning services. Satellite-based outdoor positioning and navigation can meet many outdoor travel needs, but due to obstructions such as buildings, satellite-based positioning technology cannot provide usable positioning services indoors.

[0003] Existing indoor positioning technologies can be divided into three types based on data sources and positioning methods: 1) Heavy-deployment indoor positioning: Indoor positioning is achieved by deploying specific positioning base stations and communication servers in indoor environments; 2) Light-deployment indoor positioning: A multi-floor indoor fingerprint database is constructed through manual collection, and positioning is achieved by initiating a positioning request and matching the currently scanned fingerprint with the fingerprint database; 3) Zero-deployment indoor positioning: Sensor, Wi-Fi, Global Positioning System (GPS) and other data collected by users under specific trigger conditions are collected through crowdsourcing and uploaded to the cloud. The cloud uses algorithms to process and obtain an indoor positioning fingerprint library for subsequent indoor positioning. Among them, zero-deployment indoor positioning has gradually become the mainstream indoor positioning solution due to its many advantages such as low cost, high timeliness, and high degree of automation.

[0004] However, in the above-mentioned zero-deployment positioning solution, since most indoor trajectory data does not contain location information such as GNSS, it can only be stored one by one. Therefore, when the data volume is large, it will face the problem of being unable to store it; at the same time, there is also the problem of incompatibility with outdoor data.

[0005] Summary of the Invention

[0006] The embodiments of the present application provide a method and apparatus for characterizing trajectory data, which can effectively save storage space for trajectory data. At the same time, it is compatible with the format of outdoor data, realizing the integration of indoor and outdoor data, thereby improving the practicality of trajectory data in the field of indoor and outdoor positioning.

[0007] In a first aspect, the present application provides a method for characterizing trajectory data, the method comprising: obtaining multiple trajectory data, each of the multiple trajectory data comprising multiple time periods and characteristic signals collected within each of the multiple time periods; generating multiple position points and attributes of each of the multiple position points based on the multiple trajectory data; wherein the multiple position points include a first position point, the first position point corresponds to one or more time periods in the multiple trajectory data, the combination identifier of each time period in the one or more time periods is the same, the combination identifier of each time period is generated by an identifier ID of at least one characteristic signal corresponding to each time period, and the first position point is characterized by the combination identifier; the characteristic signals collected within the one or more time periods comprise at least one type of characteristic signals, and the attributes of the first position point comprise the number of each type of characteristic signals in the at least one type of characteristic signals and / or the quantity distribution characteristics of each type of characteristic signals.

[0008] The first location point is the location where the characteristic signal is collected within the one or more time periods.

[0009] The at least one characteristic signal corresponding to each time period includes the characteristic signal collected during the time period.

[0010] From the perspective of technical effects, due to the uniqueness of the characteristic signal combination identifiers at different location points, for one or more time periods with the same combination identifier in the trajectory data, it can be known that the characteristic signal data in the one or more time periods are collected at the same location point. Furthermore, the characteristic signal data in the one or more time periods can be counted and characterized together to obtain data such as the number and quantity distribution characteristics of each type of characteristic signal in the one or more time periods as attributes of the location points. That is, the present application uses location points and the attributes of location points to characterize multiple trajectory data to replace the method of directly storing each original trajectory data in the prior art, thereby achieving the technical effect of saving trajectory data storage space. Furthermore, when the trajectory data reaches a certain amount, storing the newly collected trajectory data will hardly increase the storage overhead, making it possible to store massive trajectory data in the big data era, thereby effectively improving the value of trajectory data for indoor and outdoor positioning.

[0011] In a feasible embodiment, the one or more time periods include a first time period, the first time period includes M characteristic signals, the M characteristic signals include C-type characteristic signals, and M and C are positive integers; the combined identifier is generated by the IDs of N characteristic signals among the M characteristic signals, the N characteristic signals include D-type characteristic signals, N is a positive integer less than or equal to M, and D is a positive integer less than or equal to C.

[0012] From a technical perspective, since the characteristic signals and corresponding signal strengths collected at different locations are different, at least one of the characteristic signals collected in each time period can be used to generate a combined identifier for each time period to identify the collection position corresponding to each time period, thereby achieving subsequent unified representation and storage of data collected at the same location point, thereby replacing the existing method of storing trajectory data one by one and saving storage space for trajectory data.

[0013] In a feasible embodiment, the C-type characteristic signals include first-type characteristic signals, the M characteristic signals include A first-type characteristic signals, the N characteristic signals include B first-type characteristic signals, the A first-type characteristic signals include the B first-type characteristic signals, and the signal strength of the B first-type characteristic signals is greater than the signal strength of other characteristic signals in the A first-type characteristic signals; wherein B is a positive integer less than or equal to A.

[0014] From a technical perspective, since the signal strengths of characteristic signals collected at different locations are different, the characteristic signal strengths can be used to screen out the characteristic signals used to generate the combination identifier in each type of characteristic signal. In this way, the combination identifier generated by the characteristic signals collected at the same location (that is, the characteristic signal data in one or more time periods are collected at the same location) is unique, and the combination identifiers generated by the characteristic signals collected at different locations are different; furthermore, the similarities and differences in the combination identifiers are used to uniformly represent and store the characteristic signal data of one or more time periods with the same combination identifier, thereby replacing the existing method of storing trajectory data one by one, saving storage space for trajectory data.

[0015] In a feasible embodiment, the attributes of the first location point include indoor and outdoor location identifiers, and the indoor and outdoor location identifiers are used to indicate whether the first location point is an indoor location point or an outdoor location point; when the first location point is an indoor location point, the collection location of the characteristic signal in the one or more time periods is located indoors; when the first location point is an outdoor location point, the collection location of the characteristic signal in the one or more time periods is located outdoors.

[0016] From a technical perspective, since the coordinates of the locations indicated by most outdoor location points are already included in the trajectory data, the locations of different location points are distinguished by indoor and outdoor location identifiers, so that the coordinates of the outdoor location points can be used to calculate the longitude and latitude of the relevant indoor location points. This allows indoor location points to be represented and stored based on coordinates, and achieves compatibility between indoor and outdoor location point data.

[0017] In a feasible embodiment, the multiple position points also include a second position point, and the combined identifier representing the second position point is generated by the ID of E characteristic signals; when the first position point and the second position point meet one or more of the first condition, the second condition or the third condition, the first position point is adjacent to the second position point; wherein, the first condition is: the E characteristic signals and the N characteristic signals contain common G characteristic signals, and the ratio of G to E and the ratio of G to N are both greater than or equal to the first threshold; and the difference between the average signal strength of the first signal in the E characteristic signals and the average signal strength of the first signal in the N characteristic signals is less than or equal to the second threshold, and the first signal is any one of the G characteristic signals; the second condition is: the first position point corresponds to H time periods in the multiple trajectory data, and the The two position points correspond to I time periods in the multiple trajectory data, the H time periods include J time periods, the ratio of J to H is greater than or equal to a third threshold, for the second time period in the J time periods, the I time periods include the third time period, the second time period and the third time period are located on the same trajectory data, and the interval between the second time period and the third time period is less than or equal to a fourth threshold, and the second time period is any time period within the J time periods; the third condition is: the distance between the first position point and the second position point is less than or equal to a fifth threshold, the distance between the first position point and the second position point is calculated by the coordinates of the first position point and the coordinates of the second position point, and the coordinates of the first position point are obtained by summing the position coordinates collected in the one or more time periods and taking the average.

[0018] From a technical perspective, for any two of the aforementioned multiple locations, whether the locations indicated by the two locations are adjacent can be determined based on a spatial relationship (i.e., the first and third conditions) and a temporal relationship (i.e., the second condition). This adjacency relationship can then be used to calculate the first attribute of other locations (whose attributes do not include the first attribute) that have a certain adjacency relationship with these locations, based on the similarity of the same attribute between the adjacent locations. Specifically, the first condition representing the spatial relationship is: for any two locations, when the signal strengths of the characteristic signals generating their combined identifiers are close, the two locations are considered adjacent or close. Specifically, the temporal relationship is: for any of the multiple time periods corresponding to a location, there is a time period with a similar collection time within the multiple time periods corresponding to another location, and these two time periods are located on the same trajectory data. Based on the movement patterns of people or objects indoors, it can be determined that the collection locations corresponding to these two time periods are adjacent.

[0019] In a feasible implementation, the attributes of the first location point include a first attribute, and the method further includes: generating a first graph structure based on the adjacent relationship between the multiple location points; wherein the first graph structure is used to describe the connection relationship between the multiple location points, and when the first location point is adjacent to the second location point, the first location point and the second location point are connected by an edge in the first graph structure, the first graph structure includes a first type of location points and a second type of location points, the attributes of each location point in the first type of location points include the first attribute, and the attributes of each location point in the second type of location points do not include the first attribute; the first graph structure is cut to obtain a second graph structure; wherein the edge between any two of the first type of location points in the first graph structure is cut, and the edge between any two of the second type of location points connected to the first type of location points is cut, and each location point in the second graph structure has a connection relationship with at least one location point.

[0020] The first attribute is any one of the attributes of the first location point.

[0021] From a technical perspective, the first graph structure is used to characterize the adjacent relationship of each location point, and then a second graph structure consisting of the first type of location points and the second type of location points adjacent to the first type of location points is generated. The second graph structure is used to calculate the missing or inaccurate first attributes in the attributes of the second type of location points, so as to remove the influence of the farther first type of location points on the calculation of the first attributes that need to be included in the attributes of the second type of location points.

[0022] In a feasible embodiment, the method also includes: obtaining an adjacency distance matrix based on the connection relationship between each position point in the second graph structure; wherein each element in the adjacency distance matrix is ​​used to represent the number of edges between a second-type position point and a first-type position point in the second graph structure; normalizing the adjacency distance matrix to obtain a weight matrix; multiplying the weight matrix and the first matrix to obtain a second matrix; wherein the elements in the first matrix are used to represent the first attribute contained in the attributes of each first-type position point in the second graph structure, and the elements in the second matrix are used to represent the first attribute contained in the attributes of each second-type position point in the second graph structure.

[0023] From a technical perspective, the distance from the second-category position point to the first-category position point is represented by the number of edges, and then normalized to obtain the weight matrix of all the second-category position points in the second graph structure. This is then multiplied by the first matrix to accurately obtain the first attribute required for each position point in the second category.

[0024] In a feasible implementation manner, the first attribute is the coordinates or indoor or outdoor location identifiers of the first location point, and the indoor or outdoor location identifiers are used to indicate whether the first location point is an indoor location point or an outdoor location point.

[0025] From a technical perspective, by completing the coordinates and storing them in the location point's attributes, the coordinates can be used to replace the combined identifier of each indoor location point for subsequent indexing, achieving format compatibility and uniformity with outdoor data. Furthermore, this attribute completion method effectively compensates for flaws and errors in the data collection process, ensuring that each location point contains complete attributes, effectively improving the practicality of the solution.

[0026] In a feasible implementation, the method further includes: performing location positioning, navigation, big data statistical analysis, or service recommendation based on the coordinates of each of the multiple location points.

[0027] From a technical perspective, after calculating the coordinates of each location point, various upper-level application scenarios can be based on the coordinates of the location point, and the application prospects are broad.

[0028] In a feasible implementation manner, the attributes of the first location point further include L first-category characteristic signals, and the L first-category characteristic signals conform to the quantity distribution characteristics of the first-category characteristic signals.

[0029] From a technical perspective, some original data that conforms to the distribution law can also be stored in the attributes of the location points, so that the true characteristics of the original data can be better preserved when most of the original trajectory data is discarded.

[0030] In a feasible embodiment, the characteristic signal includes one or more of a global navigation satellite system GNSS signal, position coordinates, a radio frequency signal, an optical signal, an acoustic signal, a sensor signal or a geomagnetic signal, wherein the radio frequency signal includes one or more of a WIFI signal, a Bluetooth signal, a cell CELL signal or an ultra-wideband UWB signal.

[0031] In a feasible implementation, the quantity distribution feature includes at least one of normal distribution, Poisson distribution, discrete distribution or interval distribution, and the interval distribution is used to describe the quantity of characteristic signals located in different intervals.

[0032] From a technical perspective, interval distribution and / or normal distribution can greatly save the storage space of trajectory data. By saving distribution-specific (such as the mean and variance of the normal distribution) and partially conforming to the original data of the distribution-specific, it is possible to greatly retain the characteristics of the original data while saving storage space.

[0033] In a second aspect, the present application provides a device for characterizing trajectory data, the device comprising: an acquisition unit for acquiring multiple trajectory data, each of the multiple trajectory data comprising multiple time periods and characteristic signals collected within each of the multiple time periods; a processing unit for generating multiple position points and attributes of each of the multiple position points based on the multiple trajectory data; wherein the multiple position points include a first position point, the first position point corresponds to one or more time periods in the multiple trajectory data, the combination identifier of each time period in the one or more time periods is the same, the combination identifier of each time period is generated by an identifier ID of at least one characteristic signal corresponding to each time period, and the first position point is characterized by the combination identifier; the characteristic signals collected within the one or more time periods include at least one type of characteristic signals, and the attributes of the first position point include the number of each type of characteristic signals in the at least one type of characteristic signals and / or the quantity distribution characteristics of each type of characteristic signals.

[0034] In a feasible embodiment, the one or more time periods include a first time period, the first time period includes M characteristic signals, the M characteristic signals include C-type characteristic signals, and M and C are positive integers; the combined identifier is generated by the IDs of N characteristic signals among the M characteristic signals, the N characteristic signals include D-type characteristic signals, N is a positive integer less than or equal to M, and D is a positive integer less than or equal to C.

[0035] In a feasible embodiment, the C-type characteristic signals include first-type characteristic signals, the M characteristic signals include A first-type characteristic signals, the N characteristic signals include B first-type characteristic signals, the A first-type characteristic signals include the B first-type characteristic signals, and the signal strength of the B first-type characteristic signals is greater than the signal strength of other characteristic signals in the A first-type characteristic signals; wherein B is a positive integer less than or equal to A.

[0036] In a feasible implementation manner, the attributes of the first location point further include L first-category characteristic signals, and the L first-category characteristic signals conform to the quantity distribution characteristics of the first-category characteristic signals.

[0037] In a feasible embodiment, the multiple position points also include a second position point, and the combined identifier representing the second position point is generated by the ID of E characteristic signals; when the first position point and the second position point meet one or more of the first condition, the second condition or the third condition, the first position point is adjacent to the second position point; wherein, the first condition is: the E characteristic signals and the N characteristic signals include common G characteristic signals, and the ratio of G to E and the ratio of G to N are both greater than or equal to the first threshold; and the difference between the average signal strength of the first signal in the E characteristic signals and the average signal strength of the first signal in the N characteristic signals is less than or equal to the second threshold, and the first signal is any one of the G characteristic signals; the second condition is: the first position point corresponds to H time periods in the multiple trajectory data, the second position point corresponds to I time period in the multiple trajectory data, the H time periods include J time periods, and J is greater than or equal to the second threshold. The ratio of H is greater than or equal to the third threshold value, for the second time period in the J time periods, the third time period is included in the I time period, the second time period and the third time period are located on the same trajectory data, and the interval between the second time period and the third time period is less than or equal to the fourth threshold value, and the second time period is any time period in the J time periods; the third condition is: the distance between the first position point and the second position point is less than or equal to the fifth threshold value, the distance between the first position point and the second position point is calculated by the coordinates of the first position point and the coordinates of the second position point, and the coordinates of the first position point are obtained by summing the position coordinates collected in the one or more time periods and taking the average.

[0038] In a feasible embodiment, the attributes of the first position point include a first attribute, and the processing unit is further used to: generate a first graph structure based on the adjacent relationship between the multiple position points; wherein the first graph structure is used to describe the connection relationship between the multiple position points, and when the first position point is adjacent to the second position point, the first position point and the second position point are connected by an edge in the first graph structure, the first graph structure includes a first type of position points and a second type of position points, the attributes of each position point in the first type of position points include the first attribute, and the attributes of each position point in the second type of position points do not include the first attribute; the first graph structure is cut to obtain a second graph structure; wherein the edge between any two of the first type of position points in the first graph structure is cut, and the edge between any two of the second type of position points connected to the first type of position points is cut, and each position point in the second graph structure has a connection relationship with at least one position point.

[0039] In a feasible embodiment, the processing unit is also used to: obtain an adjacency distance matrix based on the connection relationship between each position point in the second graph structure; wherein each element in the adjacency distance matrix is ​​used to represent the number of edges between a second-type position point and a first-type position point in the second graph structure; normalize the adjacency distance matrix to obtain a weight matrix; multiply the weight matrix and the first matrix to obtain a second matrix; wherein the elements in the first matrix are used to represent the first attribute contained in the attributes of each first-type position point in the second graph structure, and the elements in the second matrix are used to represent the first attribute contained in the attributes of each second-type position point in the second graph structure.

[0040] In a feasible implementation manner, the first attribute is the coordinates or indoor or outdoor location identifiers of the first location point, and the indoor or outdoor location identifiers are used to indicate whether the first location point is an indoor location point or an outdoor location point.

[0041] In a feasible implementation manner, the processing unit is further configured to perform location positioning, navigation, big data statistical analysis, or service recommendation based on the coordinates of each of the multiple location points.

[0042] In a feasible implementation, the quantity distribution feature includes at least one of normal distribution, Poisson distribution, discrete distribution or interval distribution, and the interval distribution is used to describe the quantity of characteristic signals located in different intervals.

[0043] In a feasible embodiment, the characteristic signal includes one or more of a global navigation satellite system GNSS signal, position coordinates, a radio frequency signal, an optical signal, an acoustic signal, a sensor signal or a geomagnetic signal, wherein the radio frequency signal includes one or more of a WIFI signal, a Bluetooth signal, a cell CELL signal or an ultra-wideband UWB signal.

[0044] In a third aspect, an embodiment of the present application provides a chip system, which includes at least one processor, a memory and an interface circuit, wherein the memory, the interface circuit and the at least one processor are interconnected through lines, and instructions are stored in the at least one memory; when the instructions are executed by the processor, the method described in any one of the first aspects above is implemented.

[0045] In a fourth aspect, an embodiment of the present application provides a computer device, comprising at least one processor, a memory and an interface circuit, wherein the memory, the interface circuit and the at least one processor are interconnected via lines, and instructions are stored in the at least one memory; when the instructions are executed by the processor, the method described in any one of the first aspects above is implemented.

[0046] In a feasible implementation manner, the computer device is a server or a terminal device, wherein the terminal device includes a mobile phone, a computer, a car computer or a tablet.

[0047] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed, the method described in any one of the above-mentioned first aspects is implemented.

[0048] In a sixth aspect, an embodiment of the present application provides a computer program product, which includes program instructions. When the program instructions are executed on a computer, the method described in any one of the above-mentioned first aspects is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The following is an introduction to the drawings used in the embodiments of this application.

[0050] FIG1 is a schematic diagram of a system architecture provided by an embodiment of the present application;

[0051] FIG2 is a schematic diagram of a scenario for trajectory data collection provided in an embodiment of the present application;

[0052] FIG3 is a flow chart of a method for characterizing trajectory data provided in an embodiment of the present application;

[0053] FIG4 is a schematic diagram of the structure of trajectory data in an embodiment of the present application;

[0054] 5A-5C are schematic diagrams of a graph structure generation process provided in an embodiment of the present application;

[0055] FIG6 is a schematic diagram of a calculation process of a second matrix provided in an embodiment of the present application;

[0056] 7A-7B are schematic diagrams of indoor and outdoor space topological structures extracted based on the trajectory data characterization method of the present application;

[0057] FIG8 is a schematic diagram of the structure of a trajectory data characterization device provided in an embodiment of the present application;

[0058] FIG9 is a schematic structural diagram of a computer device provided in this application. DETAILED DESCRIPTION

[0059] The following describes the embodiments of the present application in conjunction with the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " represents or, for example, A / B can represent A or B; "and / or" in the text is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" refers to two or more than two.

[0060] The terms "first", "second", "third" and "fourth" in the specification and claims of this application and the accompanying drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices. Reference to "embodiments" herein means that the specific features, structures or characteristics described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0061] First, the relevant terms in this application are explained.

[0062] (1) Crowdsourcing: This refers to collecting available data such as sensors, radio frequency signals, and network signals from users’ smart terminals through certain triggering mechanisms without the users’ awareness. Crowdsourcing is a common method for collecting indoor and outdoor trajectory data.

[0063] (2) Trajectory data: refers to the characteristic signal data collected by the user's smart terminal within a continuous time period. Each trajectory data represents the characteristic signal data collected by the smart terminal at different locations during the user's movement, including indoor trajectory data and outdoor trajectory data.

[0064] (3) Cell: A wireless coverage area identified by a base station identification code or a Cell Global Identifier (CGI). When using an omnidirectional antenna structure, a cell is the base station area.

[0065] (4) Indoor or Outdoor Location Identifier (IOD): This is a location identifier generated by whether a GNSS signal is received, indicating whether the current location is indoors or outdoors. For example, if the signal is received, the IOD is set to 1, indicating that the location is outdoors. If the signal is not received, the IOD is set to 0, indicating that the location is indoors.

[0066] The following describes the system architecture and application scenarios of this application.

[0067] Please refer to Figure 1, which is a schematic diagram of a system architecture provided in an embodiment of the present application. As shown in Figure 1, the system architecture includes user device 101, user device 102, cloud 110, and data storage system 120. Cloud 110 and user devices communicate over a communication network for data transmission. It should be noted that the number of user devices listed in Figure 1 does not limit their number.

[0068] The following describes two specific application scenarios applicable to the present invention based on the system architecture shown in FIG1 .

[0069] In the first scenario, the user device collects data over a period of time to form trajectory data, which is then uploaded to the cloud 110 via a communication network. Optionally, the trajectory data can be collected through crowdsourcing, manual collection, or other collection methods, which are not limited in this application. The trajectory data includes indoor trajectory data and / or outdoor trajectory data.

[0070] The cloud 110 characterizes the trajectory data received within a specific area (e.g., an area centered on a shopping mall) over a period of time (e.g., three days or a month) (i.e., the trajectory data characterization method in this application), forms a map of the specific area (including indoors and outdoors), and stores the generated location map and trajectory data characterization data (i.e., the location points and location point attributes described in the embodiments below) in the data storage system 120. When the user device subsequently enters a building in the specific area, it can send a positioning request to the cloud 110.

[0071] The cloud 110 provides users with online positioning services based on the generated map, or sends users a map of the specific area to provide users with offline low-power positioning services. Based on the positioning service, the cloud 110 then provides users with navigation services and personalized recommendation services (for example, recommending businesses in the specific area based on user-specific requests) based on other personalized user needs (for example, navigation requests and service recommendation requests).

[0072] Optionally, the cloud 110 may include at least one server, and the data storage system 120 may be a device independent of the server, or integrated in the server, which is not limited in this application.

[0073] In the second scenario, when the trajectory data is collected from a relatively small area (when the area radius is less than the preset radius, specifically a place such as a subway station or bus stop), the user device in Figure 1 can independently execute the trajectory data characterization method of this application. In this case, the trajectory data can be collected by the user device and / or transmitted to the user device by other devices, which is not limited in this application.

[0074] Optionally, the user device is a terminal device with communication and data collection functions such as a mobile phone, computer, smart watch, bracelet, etc., which is not limited in this application.

[0075] Please refer to Figure 2, which is a schematic diagram of a scenario for trajectory data collection provided in an embodiment of the present application, which is used to describe the collection of trajectory data in a specific area centered on a building. The specific area includes the building and the streets adjacent to the building.

[0076] Figure 2 shows six tracks (i.e., six tracks of data) within this specific area. Tracks 1 and 2 were collected indoors, tracks 3-5 were collected both indoors and outdoors, and track 6 was collected outdoors.

[0077] Please refer to Figure 3, which is a flow chart of a trajectory data characterization method provided by an embodiment of the present application. As shown in Figure 3, the method includes steps S310 and S320.

[0078] Step S310: Acquire multiple pieces of trajectory data, where each piece of trajectory data includes multiple time periods and characteristic signals collected in each of the multiple time periods.

[0079] Each trajectory data is a characteristic signal collected during a continuous period of time. The length of the continuous period of time is not limited, for example, it can be 30 minutes or 1 hour, etc. The characteristic signal collected during the continuous period of time includes at least one type of characteristic signal.

[0080] The characteristic signal includes one or more of a global navigation satellite system GNSS signal, position coordinates, a radio frequency signal, an optical signal, an acoustic signal, a sensor signal or a geomagnetic signal, wherein the radio frequency signal includes one or more of a WIFI signal, a Bluetooth signal, a cell CELL signal or an ultra-wideband UWB signal.

[0081] Optionally, the above-mentioned position coordinates may be coordinates in different coordinate reference systems. The coordinate reference system may be a geodetic coordinate system, a projected coordinate system, or a custom coordinate system, etc., which is not limited in this application. The position coordinates in the geodetic coordinate system may be represented by longitude, latitude, and elevation, etc.

[0082] Ultra Wide Band (UWB) is a wireless carrier signal with a frequency bandwidth above 1 GHz.

[0083] Optionally, the above-mentioned location coordinates can be calculated through the collected GNSS signals, or can be obtained through manual collection or direct acquisition from other terminal devices, etc., which is not limited in this application.

[0084] In the above continuous time, each type of characteristic signal can be collected at a fixed or non-fixed time interval, and the collection time intervals of different types of characteristic signals can be the same or different.

[0085] For characteristic signals with signal strength, the collected content at a collection moment includes at least one identification ID of such characteristic signal and the corresponding signal strength.

[0086] For example, for a WIFI signal, the collected content at each collection moment includes the ID (eg, Media Access Control (MAC) ID) of the WIFI signal identified by the smart terminal and the corresponding signal strength.

[0087] For another example, for CELL signals, the collected content at each collection moment includes the ID of the CELL signal recognized by the smart terminal (such as the Cell Global Identifier (CGI) and / or the Physical Cell Identifier (PCI)) and the corresponding signal strength.

[0088] The relationship between the multiple time periods contained in each piece of trajectory data and the continuous time during which each piece of trajectory data was collected is as follows: the multiple time periods contained in each piece of trajectory data are obtained by dividing the continuous time according to fixed time intervals or non-fixed time intervals, and no two of the multiple time periods obtained by division overlap.

[0089] Optionally, the manner of dividing the continuous time for collecting data for each trajectory data may be determined according to a specific scenario, which is not limited in this application.

[0090] Optionally, for each type of characteristic signal, each divided time period only includes one collection moment of the characteristic signal of that type.

[0091] Figure 4 is a schematic diagram of the structure of trajectory data in an embodiment of the present application. An example of the collection of two types of characteristic signals on a piece of trajectory data is listed. As shown in Figure 4, the collection time of the trajectory data (i.e., the above-mentioned continuous time) is from 12:30 to 12:45, which includes three time periods: 12:30-12:35, 12:35-12:40, and 12:40-12:45, that is, the continuous time (15 minutes) is divided according to a fixed time interval (5 minutes). The collected characteristic signals include cell CELL signals and WIFI signals. Among them, the collection time of the cell signal is: 12:32, 12:37 and 12:43; the collection time of the WIFI signal is 12:34, 12:39 and 12:44. That is, the collection time interval of the cell signal and the WIFI signal is 5 minutes.

[0092] Optionally, the cell signal collected at each moment includes a primary station signal and at least one neighboring station signal. The Wi-Fi signal collected at each moment includes all Wi-Fi signals recognized by the smart terminal. That is, at each collection moment within the collection time, the number of characteristic signals collected is at least one.

[0093] It should be understood that FIG4 shows only an example of trajectory data collection, which does not constitute a limitation on the types of characteristic signals collected, the collection time interval of each type of characteristic signal, etc.

[0094] Step S320: Generate multiple location points and attributes of each of the multiple location points based on the multiple trajectory data; wherein the multiple location points include a first location point, the first location point corresponds to one or more time periods in the multiple trajectory data, the combination identifier of each time period in the one or more time periods is the same, the combination identifier of each time period is generated by the identification ID of at least one characteristic signal corresponding to each time period, and the first location point is represented by the combination identifier; the characteristic signals collected in the one or more time periods include at least one type of characteristic signals, and the attributes of the first location point include the number of each type of characteristic signals in the at least one type of characteristic signals and / or the quantity distribution characteristics of each type of characteristic signals.

[0095] It should be understood that the present application describes the first location point among multiple location points to represent the generation of each location point and its attributes, that is, the first location point is any one of the multiple location points.

[0096] After obtaining multiple time periods of each trajectory data according to the above method, a combination identifier for each time period is constructed. Time periods with the same combination identifier correspond to the same location point, and the same location point is represented by the combination identifier.

[0097] The at least one characteristic signal corresponding to each time period includes the characteristic signal collected during the time period.

[0098] Specifically, the combination identifier for each time period is derived from the combination of the identifiers of at least one characteristic signal collected during that time period. Technically, because the types and signal strengths of characteristic signals collected at different locations vary, the combination identifier can be used to indicate differences in collection locations. That is, time periods with the same combination identifier correspond to the same collection location, while time periods with different combination identifiers correspond to different collection locations.

[0099] The following describes the process of constructing the combined identifier of each time period by taking one or more time periods corresponding to the first location point as an object.

[0100] Optionally, the one or more time periods include a first time period, the first time period includes M characteristic signals, the M characteristic signals include C-type characteristic signals, and M and C are positive integers; the combined identifier is generated by the IDs of N characteristic signals among the M characteristic signals, the N characteristic signals include D-type characteristic signals, N is a positive integer less than or equal to M, and D is a positive integer less than or equal to C.

[0101] The first time period is any one of the one or more time periods. That is, for each time period, its combined identifier is generated by combining the IDs of at least one characteristic signal collected during the time period. The at least one characteristic signal includes at least one type of characteristic signal.

[0102] For example, the combined identifier of each time period can be generated by the ID combination of multiple CELL signals (such as a master station signal + multiple neighbor station signals); or generated by the MAC ID combination of multiple WIFI signals; or generated by the ID combination of at least one CELL signal, at least one WIFI signal and at least one Bluetooth signal; or generated by the ID combination of at least one WIFI signal, at least one geomagnetic signal and at least one sensor signal. This application is not limited to this.

[0103] The method of generating the combined identifier by combining the IDs of at least one characteristic signal may be to directly use the ID series combination or to calculate it using a specific algorithm (such as a hash algorithm, etc.).

[0104] It should be understood that the more types of characteristic signals used to generate a combination identifier, the more unique the combination identifier is, that is, the time periods of different combination identifiers correspond to different collection locations.

[0105] Furthermore, when multiple characteristic signals of the same type of characteristic signals are used to generate a combined identifier, the method for screening the multiple characteristic signals of the same type of characteristic signals is as follows:

[0106] For characteristic signals with signal strength, the characteristic signals of the same type in the first time period are sorted from high to low according to the signal strength, and then a preset number of characteristic signals are filtered out from high to low according to the signal strength. The filtered characteristic signals are subsequently used to generate a combination identifier for the first time period.

[0107] Specifically, the C-type characteristic signals include a first-type characteristic signal. The M characteristic signals include A first-type characteristic signals, the N characteristic signals include B first-type characteristic signals, the A first-type characteristic signals include the B first-type characteristic signals, and the signal strength of the B first-type characteristic signals is greater than the signal strength of other characteristic signals in the A first-type characteristic signals; wherein B is a positive integer less than or equal to A.

[0108] The A first-category characteristic signals include the B first-category characteristic signals. The B first-category characteristic signals are selected from the A first-category characteristic signals based on the signal strength of the characteristic signals. Specifically, the signal strength of the B first-category characteristic signals is greater than the signal strength of other characteristic signals in the A first-category characteristic signals.

[0109] For example, assume that the combined identifier for each time period is generated by combining the master station ID and three neighbor station IDs. If the CELL signals collected in the first time period include one master station signal and 10 neighbor station signals, the top three neighbor station signals with the highest signal strength are first filtered out based on the neighbor station signal strength. Then, the master station ID (such as CGI) and the three filtered neighbor station IDs (such as PCI) are combined to generate the combined identifier for the first time period.

[0110] For example, assume that the combination identifier for each time period is generated by combining five Wi-Fi signals. If the Wi-Fi signals collected in the first time period include 10 Wi-Fi signals, the top five Wi-Fi signals with the highest signal strength are selected based on the signal strength of the Wi-Fi signals. The combination identifier for the first time period is then generated using the combination of the IDs of the top five Wi-Fi signals.

[0111] Optionally, the attributes of the first location point include indoor and outdoor location identifiers, and the indoor and outdoor location identifiers are used to indicate that the first location point is an indoor location point or an outdoor location point; when the first location point is an indoor location point, the collection location of the characteristic signal in the one or more time periods is located indoors; when the first location point is an outdoor location point, the collection location of the characteristic signal in the one or more time periods is located outdoors.

[0112] Specifically, the indoor and outdoor identification of the first location point can be determined by counting the number of time periods corresponding to the first location point and whether the characteristic signal collected in each time period includes a GNSS signal. When the number of time periods in which satellite positioning signals are collected is greater than or equal to a preset ratio, the indoor and outdoor location identification of the first location point can be set to 1 to indicate that the collection location of the characteristic signal in one or more time periods corresponding to the first location point is outdoors; when the number of time periods in which satellite positioning signals are collected is less than the preset ratio, the indoor and outdoor location identification of the first location point can be set to 0 to indicate that the collection location of the characteristic signal in one or more time periods corresponding to the first location point is indoors.

[0113] After a plurality of position points are generated using the acquired plurality of trajectory data, it is started to determine the adjacent relationship between the plurality of position points.

[0114] The multiple position points further include a second position point, and the combined identifier representing the second position point is generated by the IDs of E characteristic signals.

[0115] The following takes the first and second position points among the above multiple position points as an example to describe how to determine the adjacent relationship between any two position points among the multiple position points, that is, the first and second position points are any two of the multiple position points.

[0116] Specifically, when the first position point and the second position point satisfy one or more of the first condition, the second condition, or the third condition, the first position point is adjacent to the second position point.

[0117] That is, different rules can be selected according to specific application scenarios to determine whether the first location point and the second location point are adjacent (or have an adjacent relationship). The first location point and the second location point being adjacent means that the distance between the first location point and the second location point is less than or equal to a preset distance.

[0118] From the above description, it can be seen that there are 7 rules for determining whether the first position point and the second position point are adjacent: 1) satisfying the first condition; 2) satisfying the second condition; 3) satisfying the third condition; 4) satisfying the first condition and the second condition at the same time; 5) satisfying the first condition and the third condition at the same time; 6) satisfying the first condition and the third condition at the same time; 7) satisfying the first condition, the second condition and the third condition at the same time.

[0119] The first, second and third conditions mentioned above are described in detail below.

[0120] (1)First condition

[0121] The first condition is: the E characteristic signals and the N characteristic signals contain common G characteristic signals, the ratio of G to E and the ratio of G to N are both greater than or equal to the first threshold; and the difference between the average signal strength of the first signal in the E characteristic signals and the average signal strength of the first signal in the N characteristic signals is less than or equal to the second threshold, and the first signal is any one of the G characteristic signals.

[0122] Specifically, for the first position point, first calculate the average signal strength of each characteristic signal in the N characteristic signals used to generate the combined identifier. Specifically, for each characteristic signal in the N characteristic signals, sum the signal strengths of the characteristic signal in each time period corresponding to the first position point, and then take the average to obtain the average signal strength of each characteristic signal. Similarly, the average signal strength of each characteristic signal in the E characteristic signals can also be obtained by referring to the above method. Finally, calculate the difference between the average signal strength of the first characteristic signal in the E characteristic signals and the average signal strength in the N characteristic signals. When the difference is less than or equal to the second threshold, and each characteristic signal in the G characteristic signals meets the above conditions of the first characteristic signal, and the ratio of G to E and the ratio of G to N are both greater than or equal to the first threshold, then it is determined that the first vertex and the second vertex meet the first condition.

[0123] The first and second thresholds are set based on specific scenarios. The first threshold is used to ensure that the E characteristic signals and the N characteristic signals contain a certain proportion of identical characteristic signals, thereby proving that the first and second locations are close to each other. E, G, and N are positive integers.

[0124] (2) Second Condition

[0125] The second condition is: the first position point corresponds to H time periods in the multiple trajectory data, the second position point corresponds to I time periods in the multiple trajectory data, the H time periods include J time periods, the ratio of J to H is greater than or equal to a third threshold, for the second time period in the J time periods, the third time period is included in the I time periods, the second time period and the third time period are located on the same trajectory data, and the interval between the second time period and the third time period is less than or equal to a fourth threshold, and the second time period is any time period within the J time periods.

[0126] Specifically, the second condition is also called the timing condition. For J time periods out of the H time periods corresponding to the first location point (the ratio of J to H is greater than or equal to the third threshold), for any time period in the J time periods (i.e., the aforementioned second time period), if there is a third time period in the I time periods corresponding to the second location point, this third time period and the second time period are located on the same trajectory data, and the time interval between the second and third time periods is less than or equal to the fourth threshold, then the first location point and the second location point are deemed to meet the aforementioned second condition.

[0127] For example, if the collection time for the second time period is 3:35 PM to 3:45 PM, and the collection time for the third time period is 3:45 PM to 3:55 PM, the time interval between the two time periods can be calculated using the end time of the first time period (i.e., the second time period) and the start time of the second time period (i.e., the third time period). Therefore, the time interval between the second and third time periods is 0. Of course, other methods can also be used to calculate the time interval between the two time periods, and this application is not limited thereto.

[0128] The third threshold and the fourth threshold are set based on specific scenarios. H, I and J are positive integers.

[0129] (3) The third condition

[0130] The third condition is: the distance between the first position point and the second position point is less than or equal to the fifth threshold, the distance between the first position point and the second position point is calculated by the coordinates of the first position point and the coordinates of the second position point, and the coordinates of the first position point are obtained by summing the position coordinates collected in the one or more time periods and taking the average.

[0131] Specifically, for location points with coordinates, the distance between two location points can be directly calculated using the coordinates. The coordinates of each location point are obtained by summing and averaging the location coordinates collected in one or more corresponding time periods.

[0132] For example, if a first location point corresponds to 100 time periods, and location coordinates are collected in 89 of the 100 time periods, the coordinates of the first location point can be obtained by calculating the average of the 89 location coordinates collected in each of the 89 time periods. The process of collecting location coordinates in each time period can be described in the previous embodiment.

[0133] Among them, the fifth threshold is set according to the specific scenario, and this application does not limit it.

[0134] After determining the neighbor relationships between multiple location points according to the above embodiment, the location point attributes can be completed based on the neighbor relationships. The attributes of the first location point include a first attribute, which is any attribute that needs to be completed. Attribute completion of the first attribute means calculating the first attributes of location points for which the first attribute is missing or inaccurate. The process is as follows:

[0135] Optionally, the method further includes: generating a first graph structure based on the adjacent relationship between the multiple position points; wherein the first graph structure is used to describe the connection relationship between the multiple position points, and when the first position point is adjacent to the second position point, the first position point and the second position point are connected by an edge in the first graph structure, the first graph structure contains first-type position points and second-type position points, the attributes of each position point in the first type of position points contain the first attribute, and the attributes of each position point in the second type of position points do not contain the first attribute; cutting the first graph structure to obtain a second graph structure; wherein the edge between any two first-type position points in the first graph structure is cut, the edge between any two second-type position points connected to the first-type position points is cut, and each position point in the second graph structure has a connection relationship with at least one position point.

[0136] The first category of location points includes the first attribute in their attributes, while the second category of location points does not include the first attribute in their attributes. The absence of the first attribute should be understood as meaning that the first attribute does not exist in the attributes or that the first attribute is inaccurate. The accuracy of the first attribute depends on the specific scenario and is not discussed in detail in this application.

[0137] Specifically, for the plurality of position points, two adjacent position points (having an adjacent relationship) are connected by an edge, generating a first graph structure representing the connection relationship between the plurality of position points. The edges between all first-category position points in the first graph structure are then cut, and the edges between any two second-category position points that have an edge relationship with the first-category position points (are connected by an edge) are cut, generating a second graph structure.

[0138] It can be seen that the second graph structure is used to represent the connection relationship between the second type of location points, and between the second type of location points and adjacent first type of location points.

[0139] Please refer to Figures 5A-5C, which are schematic diagrams of a generation process of a graph structure provided in an embodiment of the present application.

[0140] Figure 5A is a specific example of a first graph structure, which is used to describe the adjacent relationship between multiple location points generated from trajectory data collected within a specific area. As shown in Figure 5A, a total of 14 location points are included (i.e., location points 0-13). Among them, the dotted circles represent the first type of location points (i.e., location points 4-6, location points 8-13), and the solid circles represent the second type of location points (i.e., location points 0-3 and location point 7). Two location points with an adjacent relationship are connected by an edge.

[0141] FIG5B is a schematic diagram for describing the process of cutting the first graph structure shown in FIG5A. As shown in FIG5B , according to the description of the aforementioned cutting method, the dotted line segments indicate the edges to be cut. The process of cutting the edges between all first-category position points in FIG5B includes cutting the edges between position points 6 and 8, between position points 6 and 9, between position points 5 and 10, between position points 5 and 11, between position points 4 and 12, between position points 4 and 13, and between position points 12 and 13. The process of cutting the edges between any two second-category position points that have an edge relationship with the first-category position points includes cutting the edge between position points 7 and 3.

[0142] Figure 5C is used to describe an example of the second graph structure obtained after cutting. As shown in Figure 5C, it contains 4 second-category position points (i.e., position points 0-3) and 3 first-category position points (i.e., position points 4-6).

[0143] After obtaining the second graph structure, the first attribute required to be included in the attributes of each location point in the second category can be calculated based on the first attribute included in the attributes of each location point in the first category in the second graph structure and the connection relationship between the location points. The specific process is as follows:

[0144] Optionally, the method also includes: obtaining an adjacency distance matrix based on the connection relationship between each position point in the second graph structure; wherein each element in the adjacency distance matrix is ​​used to represent the number of edges between a second-class position point and a first-class position point in the second graph structure; normalizing the adjacency distance matrix to obtain a weight matrix; multiplying the weight matrix and the first matrix to obtain a second matrix; wherein the elements in the first matrix are used to represent the first attribute contained in the attributes of each first-class position point in the second graph structure, and the elements in the second matrix are used to represent the first attribute contained in the attributes of each second-class position point in the second graph structure.

[0145] Specifically, in the adjacency distance matrix, the elements in each row represent the number of edges contained in the path from a second-class position point to each first-class position point (or between a second-class position point and a first-class position point). For example, if the second feature graph contains 3 first-class position points, then the number of edges contained in the path between a second-class position point and these 3 first-class position points (such as 2, 3, and 4) is a row element in the adjacency distance matrix. Similarly, each column element in the adjacency distance matrix can also be used to represent the number of edges contained in the path from a second-class position point to each first-class position point, and this application does not limit this. That is, each element in the adjacency distance matrix is ​​used to represent the number of edges contained in the path from a second-class position point to a first-class position point.

[0146] Furthermore, optionally, the normalization processing mentioned above refers to normalization processing performed on the basis of each row or column element in the adjacency distance matrix. When each row element in the adjacency distance matrix represents the number of edges included in the path from a second-category location point to each first-category location point, the normalization processing is performed on the basis of each row element; when each column element in the adjacency distance matrix represents the number of edges included in the path from a second-category location point to each first-category location point, the normalization processing is performed on the basis of each column element.

[0147] For example, when normalization is performed on elements in each row, if the elements in one row are 2, 3, and 3, then after normalization, the elements in the row are 1 / 4, 3 / 8, and 3 / 8, respectively.

[0148] Each row or column of the first matrix represents a first attribute included in the attributes of each first-category location point. Each row or column of the second matrix represents a first attribute required to be included in the attributes of each second-category location point. Specifically, after calculating the required first attribute for each second-category location point, the calculated first attribute is added to the location point's attributes and stored.

[0149] The following, based on Figure 6, uses the first attribute as an example to explain the calculation process of the second matrix in detail. In this case, the first type of location points are those whose attributes contain coordinates, and the second type of location points are those whose attributes do not contain coordinates or whose coordinates are inaccurate.

[0150] As shown in Figure 6, the adjacency distance matrix is ​​obtained based on the second graph structure in the embodiment shown in Figures 5A-5C, which is a 4*3 matrix, in which each row element is used to represent the number of edges contained in the path from a second-class position point to each first-class position point. 0, 1, 2, and 3 on the left side of the adjacency distance matrix represent the second-class position points corresponding to each row element, and 4, 5, and 6 above the adjacency distance matrix represent the first-class position points corresponding to each column element. Each element is used to represent the number of edges contained in the path from a second-class position point to a first-class position point. For example, in the adjacency distance matrix, the element in the first row and first column represents the number of edges contained in the path from second-class position point 0 to first-class position point 4, that is, 1, and the element in the third row and second column represents the number of edges contained in the path from second-class position point 2 to first-class position point 5, that is, 2.

[0151] Then, each row element in the adjacency distance matrix is ​​normalized as a unit to obtain the weight matrix shown in Figure 6.

[0152] Each row of the first matrix represents the coordinates contained in the attributes of each first-category location point (in this example, expressed as longitude and latitude in a geodetic coordinate system; elevation is omitted). For example, in this example, the coordinates contained in the attributes of the three first-category location points are (21, 28), (42, 56), and (21, 14), respectively.

[0153] Finally, the weight matrix is ​​multiplied by the first matrix to obtain the second matrix. Each row of the second matrix represents the coordinates (i.e., longitude and latitude) to be included in the attributes of each location point in the second category. The coordinates that need to be included in the attributes of the four second-category location points are calculated to be (30, 34), (24, 26), (28, 33), and (30, 42).

[0154] Typically, a location point with coordinates is an outdoor location point, and a location point without coordinates is an indoor location point. Therefore, the trajectory data characterization method described in this application can generate indoor and outdoor location maps to provide users with indoor and outdoor positioning and other services based on indoor and outdoor positioning.

[0155] Similarly, you can refer to the above coordinate completion process to complete other attributes, which will not be repeated here.

[0156] Optionally, the first attribute is the coordinates or indoor or outdoor location identifiers of the first location point, and the indoor or outdoor location identifiers are used to indicate whether the first location point is an indoor location point or an outdoor location point.

[0157] Specifically, the attributes that can be completed include, but are not limited to, the coordinates of the location point, indoor and outdoor location identifiers, and collected characteristic signals.

[0158] Optionally, the above method further includes: performing position positioning, navigation, big data statistical analysis or service recommendation based on the coordinates of each location point in the multiple location points.

[0159] Specifically, after obtaining the coordinates of each of the multiple location points, a map of the specific area (representing indoor and outdoor locations) where the multiple trajectory data are located can be generated based on the coordinates of each location point. Then, after the user enters this specific area, they can send a positioning request to the server, and the server can provide positioning services to the user based on the generated map of the specific area.

[0160] Furthermore, on the basis of providing positioning services, navigation and service recommendations (for example, recommending businesses closest to the user) can also be provided to the user based on user requests.

[0161] Among them, the above-mentioned big data statistical analysis can be based on the characterized regional or city trajectory data to construct a city-level or regional-level heat map to analyze the flow of people in the region or city, etc., which is not limited in this application.

[0162] Optionally, the quantity distribution feature includes at least one of normal distribution, Poisson distribution, discrete distribution or interval distribution, and the interval distribution is used to describe the quantity of characteristic signals located in different intervals.

[0163] Further, optionally, the indicator used when counting the quantity distribution characteristics of each type of characteristic signal may be the signal strength of each type of characteristic signal, etc., which is not limited in this application.

[0164] Specifically, when using interval distribution to characterize the quantitative distribution characteristics of a type of characteristic signal, the number of characteristic signals of this type within different signal strength intervals can be counted, and then the range of the signal strength interval and the corresponding number can be added to the location point attributes for storage. When using normal distribution to characterize the quantitative distribution characteristics of a type of characteristic signal, the mean and variance of the normal distribution obtained based on signal strength statistics can be added to the location point attributes for storage.

[0165] It should be understood that other mathematical distribution laws (such as Poisson distribution, discrete distribution, Bernoulli distribution, etc.) can also be used to describe / characterize the quantitative distribution characteristics of each type of characteristic signal, and this application is not limited to this.

[0166] Optionally, the attribute of the first location point further includes L first-category characteristic signals, and the L first-category characteristic signals conform to the quantity distribution characteristics of the first-category characteristic signals. L is a positive integer.

[0167] The first type of characteristic signal is any one type of characteristic signal among the at least one type of characteristic signals mentioned above.

[0168] Specifically, for each type of characteristic signal, the location point attributes also include a portion of the original data for each type of characteristic signal, and this portion of original data conforms to the quantitative distribution characteristics of that type of characteristic signal. This allows the location point and attribute-based storage method to maximize the preservation of the original data characteristics of multiple trajectory data.

[0169] For example, the first type of characteristic signal is a WiFi signal, and the number of WiFi signals collected during one or more time periods corresponding to the first location point is 5000. The quantitative distribution characteristics of these 5000 WiFi signals are represented by a normal distribution, that is, the normal distribution characteristics of the 5000 signal strengths corresponding to the 5000 signals are represented by a normal distribution. In this case, based on the specific scenario requirements, 100 WiFi signals can be selected from the 5000 WiFi signals, and the signal strength distribution of these 100 WiFi signals conforms to the normal distribution of the signal strength of the 5000 WiFi signals. These 100 WiFi signals are then stored together as attributes of the first location point.

[0170] For another example, when using interval distribution to describe the distribution characteristics of the number of 5,000 Wi-Fi signals, we first count the number of Wi-Fi signals within different signal strength ranges. Assume that the proportions of signals with signal strengths in [-10, 0]dBm, [0, 10]dBm, [10, 20]dBm, and [20, 30]dBm are 10%, 20%, 40%, and 30%, respectively. Then, we filter out 100 raw data points from the 5,000 Wi-Fi signals and store them with the location attributes. The distribution of these 100 data points also conforms to the distribution patterns within the four signal strength ranges.

[0171] Similarly, when the first type of characteristic signal is also represented by other quantitative distribution characteristics, the first type of characteristic signal selected and stored as the attribute of the first position point must also conform to the corresponding other quantitative distribution characteristics.

[0172] In summary, the attributes of the first location point may include at least one of the following three types.

[0173] (1) The number of each type of characteristic signals in the at least one type of characteristic signals mentioned above.

[0174] (2) The quantity distribution characteristics of each type of characteristic signal in the at least one type of characteristic signal mentioned above.

[0175] (3) Part of the characteristic signals in each category of the at least one category of characteristic signals, wherein the part of the characteristic signals conforms to the quantity distribution characteristics of the characteristic signals of the category to which it belongs.

[0176] The following describes the technical effects of using the trajectory data characterization method of this application for data characterization and storage based on Table 1. Table 1 is used to show the compression ratio of trajectory data in a certain area of ​​Nanjing after using the trajectory data characterization method of this application within one week and one month.

[0177] The number of trajectory points in Table 1 is the number of time periods obtained by dividing the collected trajectory data. The compression ratio is calculated by dividing the number of trajectory points by the number of location points, where M represents the unit of measurement—millions.

[0178] As shown in Table 1, for trajectory data collected within a week, the number of trajectory points for mobile operators is 113.59M. After using the trajectory data representation method of this application, only 0.94M location points need to be stored, with a compression ratio of 120.29 times. Similarly, for China Unicom and China Telecom operators, the compression ratios after trajectory data representation within a week also reached 79.55 times and 128.44 times, respectively.

[0179] Table 1 also shows that the compression ratio increases with increasing collection time. Within a month, the trajectory data collected by China Mobile, China Unicom, and China Telecom achieved compression ratios of 238.64, 142.44, and 215.02, respectively, after trajectory data characterization.

[0180] The main reasons for using the trajectory data representation method in this application to achieve data compression technology are:

[0181] (1) Position point-attribute representation method. Trajectory data is prone to over-accumulation, especially for trajectory data collected by crowdsourcing. The amount of crowdsourcing data itself is large. When the data accumulates to a certain extent, the accumulated data has completely reflected all the data features that the crowdsourcing data itself can express. At this time, increasing the amount of data has no effect on the data distribution and features. This is the limit of crowdsourcing data accumulation. At this time, the continuously accumulated data is redundant. The characterization method of this application uses attributes (quantity distribution characteristics and quantity, etc.) to characterize multiple types of feature signals within a local range, and stores part of the original data in a limited manner. It not only balances the crowdsourcing data, but also avoids the excessive accumulation of local crowdsourcing data and signal categories. Thus, a compression effect is achieved.

[0182] (2) The finite number of locations. The number of locations within an area is limited. As the acquisition time increases, the data will also increase linearly. The linearly increasing data will be converted into quantitative distribution characteristics and attributes such as quantity, and compressed and stored in a limited number of locations, so the compression ratio will continue to increase.

[0183] Table 1: Compression ratio of trajectory data in different acquisition time periods

[0184] 4G Operators Cumulative Days Number of Location Points (M) Number of Track Points (M) Compression Ratio Mobile 7944292113592680120.29 Unicom 73190972538551079.55 Telecom 758724375426828128.44 Mobile 302363136508115826215.02 Unicom 30835072118943509142.44 Telecom 301414625337584951238.64

[0185] Please refer to Figures 7A-7B. Figures 7A-7B are schematic diagrams of indoor and outdoor space topological structures extracted based on the trajectory data representation method of the present application.

[0186] As shown in Figure 7A, Figure 7A is the extracted outdoor spatial topology. The left side of Figure 7A shows the distribution of all trajectory points contained in the collected trajectory data (that is, the location points corresponding to each time period contained in the trajectory data) on the map. The denser the trajectory points, the higher the density of human traffic. Usually, the road has the highest human traffic density, and the entire outdoor trajectory data will actually tend to represent the road network. The left picture in Figure 7A is a display of the location information of the outdoor trajectory points, which is consistent with the road network as a whole, and the right side of Figure 7A is an outdoor heat statistics map after the left picture is rasterized, showing the overall road network situation.

[0187] Figure 7B shows the extracted indoor spatial topology. Based on the distribution of indoor trajectory points in each area, we can identify hotspots with high traffic volume. These hotspots provide the basis for subsequent indoor positioning and floor recognition.

[0188] Please refer to Figure 8, which is a schematic diagram of the structure of a trajectory data representation device provided in an embodiment of the present application, which can be used to perform each step in the above method embodiment. As shown in Figure 8, the device includes an acquisition unit 810 and a processing unit 820.

[0189] The acquiring unit 810 is configured to acquire a plurality of trajectory data, where each of the plurality of trajectory data includes a plurality of time periods and a characteristic signal collected in each of the plurality of time periods.

[0190] The processing unit 820 is configured to generate a plurality of location points and an attribute of each of the plurality of location points based on the plurality of trajectory data.

[0191] Among them, the multiple position points include a first position point, the first position point corresponds to one or more time periods in the multiple trajectory data, the combination identifier of each time period in the one or more time periods is the same, the combination identifier of each time period is generated by the identification ID of at least one characteristic signal corresponding to each time period, and the first position point is represented by the combination identifier; the characteristic signals collected in the one or more time periods include at least one type of characteristic signals, and the attributes of the first position point include the number of each type of characteristic signals in the at least one type of characteristic signals and / or the quantity distribution characteristics of each type of characteristic signals.

[0192] In a feasible embodiment, the one or more time periods include a first time period, the first time period includes M characteristic signals, the M characteristic signals include C-type characteristic signals, and M and C are positive integers; the combined identifier is generated by the IDs of N characteristic signals among the M characteristic signals, the N characteristic signals include D-type characteristic signals, N is a positive integer less than or equal to M, and D is a positive integer less than or equal to C.

[0193] In a feasible embodiment, the C-type characteristic signals include the first-type characteristic signals; the M characteristic signals include A first-type characteristic signals, the N characteristic signals include B first-type characteristic signals, the A first-type characteristic signals include the B first-type characteristic signals, and the signal strength of the B first-type characteristic signals is greater than the signal strength of other characteristic signals in the A first-type characteristic signals; wherein B is a positive integer less than or equal to A.

[0194] In a feasible implementation manner, the attributes of the first location point further include L first-category characteristic signals, and the L first-category characteristic signals conform to the quantity distribution characteristics of the first-category characteristic signals.

[0195] In a feasible embodiment, the multiple position points also include a second position point, and the combined identifier representing the second position point is generated by the ID of E characteristic signals; when the first position point and the second position point meet one or more of the first condition, the second condition or the third condition, the first position point is adjacent to the second position point; wherein, the first condition is: the E characteristic signals and the N characteristic signals contain common G characteristic signals, and the ratio of G to E and the ratio of G to N are both greater than or equal to the first threshold; and the difference between the average signal strength of the first signal in the E characteristic signals and the average signal strength of the first signal in the N characteristic signals is less than or equal to the second threshold, and the first signal is any one of the G characteristic signals; the second condition is: the first position point corresponds to H time periods in the multiple trajectory data, and the The two position points correspond to I time periods in the multiple trajectory data, the H time periods include J time periods, the ratio of J to H is greater than or equal to a third threshold, for the second time period in the J time periods, the I time periods include the third time period, the second time period and the third time period are located on the same trajectory data, and the interval between the second time period and the third time period is less than or equal to a fourth threshold, and the second time period is any time period within the J time periods; the third condition is: the distance between the first position point and the second position point is less than or equal to a fifth threshold, the distance between the first position point and the second position point is calculated by the coordinates of the first position point and the coordinates of the second position point, and the coordinates of the first position point are obtained by summing the position coordinates collected in the one or more time periods and taking the average.

[0196] In a feasible embodiment, the attributes of the first position point include a first attribute, and the processing unit 820 is further used to: generate a first graph structure based on the adjacent relationship between the multiple position points; wherein the first graph structure is used to describe the connection relationship between the multiple position points, and when the first position point is adjacent to the second position point, the first position point and the second position point are connected by an edge in the first graph structure, the first graph structure includes a first type of position points and a second type of position points, the attributes of each position point in the first type of position points include the first attribute, and the attributes of each position point in the second type of position points do not include the first attribute; the first graph structure is cut to obtain a second graph structure; wherein the edge between any two of the first type of position points in the first graph structure is cut, the edge between any two of the second type of position points connected to the first type of position points is cut, and each position point in the second graph structure has a connection relationship with at least one position point.

[0197] In a feasible embodiment, the processing unit 820 is also used to: obtain an adjacency distance matrix based on the connection relationship between each position point in the second graph structure; wherein each element in the adjacency distance matrix is ​​used to represent the number of edges between a second-type position point and a first-type position point in the second graph structure; normalize the adjacency distance matrix to obtain a weight matrix; multiply the weight matrix and the first matrix to obtain a second matrix; wherein the elements in the first matrix are used to represent the first attribute contained in the attributes of each first-type position point in the second graph structure, and the elements in the second matrix are used to represent the first attribute contained in the attributes of each second-type position point in the second graph structure.

[0198] In a feasible implementation manner, the first attribute is the coordinates or indoor or outdoor location identifiers of the first location point, and the indoor or outdoor location identifiers are used to indicate whether the first location point is an indoor location point or an outdoor location point.

[0199] In a feasible implementation manner, the processing unit 820 is further configured to perform location positioning, navigation, big data statistical analysis, or service recommendation based on the coordinates of each of the multiple location points.

[0200] In a feasible implementation, the quantity distribution feature includes at least one of normal distribution, Poisson distribution, discrete distribution or interval distribution, and the interval distribution is used to describe the quantity of characteristic signals located in different intervals.

[0201] In a feasible embodiment, the characteristic signal includes one or more of a global navigation satellite system GNSS signal, position coordinates, a radio frequency signal, an optical signal, an acoustic signal, a sensor signal or a geomagnetic signal, wherein the radio frequency signal includes one or more of a WIFI signal, a Bluetooth signal, a cell CELL signal or an ultra-wideband UWB signal.

[0202] Specifically, the specific execution process of each unit in the trajectory data representation device can refer to the specific steps in the method embodiment of Figure 3 above, and will not be repeated here.

[0203] Please refer to Figure 9, which is a schematic diagram of the structure of a computer device provided in this application, which can be a server or user device in the cloud 110 in the embodiment of Figure 1. The computer device includes a memory 901, one or more (only one is shown in the figure) processors 902, an interface circuit 903, and a bus 904. The memory 901, processor 902, and interface circuit 903 are connected to each other via the bus 904.

[0204] The processor 902 is configured to obtain, through the interface circuit 903, a plurality of trajectory data, each of the plurality of trajectory data including a plurality of time periods and a characteristic signal collected within each of the plurality of time periods. The processor 902 is configured to generate, based on the plurality of trajectory data, a plurality of location points and attributes of each of the plurality of location points; wherein the plurality of location points includes a first location point, the first location point corresponding to one or more time periods in the plurality of trajectory data, the combination identifier of each of the one or more time periods being the same, the combination identifier of each time period being generated by an identifier ID of at least one characteristic signal collected within each time period, and the first location point being characterized by the combination identifier; the characteristic signals collected within the one or more time periods including at least one type of characteristic signal, and the attributes of the first location point including the number of characteristic signals of each type in the at least one type of characteristic signal and / or the quantity distribution characteristics of the characteristic signals of each type.

[0205] The memory 901 may be used to store the aforementioned multiple location points and the attributes of each of the multiple location points.

[0206] Specifically, the specific process of the computer device executing the method for characterizing trajectory data can be referred to the various steps in the method embodiment of FIG3 , which will not be described in detail here.

[0207] Memory 901 can be any of random access memory (RAM), read-only memory (ROM), or flash memory; RAM includes static RAM (SRAM) and dynamic RAM (DRAM), and ROM includes erasable programmable ROM (EPROM) and electrically erasable programmable read-only memory (EEPROM). Memory 901 can store programs. When the program stored in memory 901 is executed by processor 902, processor 902 and interface circuit 903 are used to perform the various steps of the trajectory data characterization method according to the embodiment of the present application.

[0208] The processor 902 can be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), a graphics processing unit (GPU), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the functions required to be performed by each unit in the trajectory data characterization device of the embodiment of the present application, or to execute the trajectory data characterization method of the method embodiment of the present application.

[0209] The interface circuit 903 uses a transceiver device such as, but not limited to, a transceiver to implement communication between the computer device and other devices or communication networks. For example, trajectory data can be obtained from a smart terminal (user device) through the interface circuit 903.

[0210] The bus 904 may include a path for transmitting information between various components (eg, the memory 901 , the processor 902 , and the interface circuit 903 ) on the computer device shown in FIG. 9 .

[0211] An embodiment of the present application provides a chip system, which includes at least one processor, a memory and an interface circuit. The memory, the interface circuit and the at least one processor are interconnected by lines, and instructions are stored in the at least one memory. When the instructions are executed by the processor, some or all of the steps of any one of the above method embodiments are implemented.

[0212] An embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed, part or all of the steps of any one of the above method embodiments are implemented.

[0213] An embodiment of the present application provides a computer program product, which includes program instructions. When the program instructions are executed on a computer, some or all of the steps of any one of the above method embodiments are implemented.

[0214] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. It should be noted that for the aforementioned method embodiments, in order to simplify the description, they are all expressed as a series of action combinations, but those skilled in the art should know that this application is not limited to the order of the actions described, because according to this application, some steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0215] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0216] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0217] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for characterizing trajectory data, characterized in that: The method comprises: Acquire a plurality of trajectory data, each of the plurality of trajectory data comprising a plurality of time periods and a characteristic signal collected in each of the plurality of time periods; generating a plurality of location points and an attribute of each of the plurality of location points based on the plurality of trajectory data; Among them, the multiple position points include a first position point, the first position point corresponds to one or more time periods in the multiple trajectory data, the combination identifier of each time period in the one or more time periods is the same, the combination identifier of each time period is generated by the identification ID of at least one characteristic signal corresponding to each time period, and the first position point is represented by the combination identifier; the characteristic signals collected in the one or more time periods include at least one type of characteristic signals, and the attributes of the first position point include the number of each type of characteristic signals in the at least one type of characteristic signals and / or the quantity distribution characteristics of each type of characteristic signals.

2. The method according to claim 1, characterized in that The one or more time periods include a first time period, the first time period includes M characteristic signals, the M characteristic signals include C type characteristic signals, and M and C are positive integers; The combined identifier is generated by the IDs of N characteristic signals among the M characteristic signals, wherein the N characteristic signals include D-type characteristic signals, N is a positive integer less than or equal to M, and D is a positive integer less than or equal to C.

3. The method according to claim 2, characterized in that The C-type characteristic signals include the first-type characteristic signals, The M characteristic signals include A first-category characteristic signals, the N characteristic signals include B first-category characteristic signals, the A first-category characteristic signals include the B first-category characteristic signals, and the signal strength of the B first-category characteristic signals is greater than the signal strength of other characteristic signals in the A first-category characteristic signals; wherein B is a positive integer less than or equal to A.

4. The method according to claim 3, wherein The attributes of the first location point further include L first-category characteristic signals, and the L first-category characteristic signals conform to the quantity distribution characteristics of the first-category characteristic signals.

5. The method according to any one of claims 2 to 4, characterized in that The multiple position points further include a second position point, and a combined identifier representing the second position point is generated by the IDs of E characteristic signals; When the first position point and the second position point satisfy one or more of the first condition, the second condition, or the third condition, the first position point is adjacent to the second position point; The first condition is that: the E characteristic signals and the N characteristic signals contain common G characteristic signals, the ratio of G to E and the ratio of G to N are both greater than or equal to a first threshold; and the difference between the average signal strength of the first signal in the E characteristic signals and the average signal strength of the first signal in the N characteristic signals is less than or equal to a second threshold, and the first signal is any one of the G characteristic signals; The second condition is: the first position point corresponds to H time periods in the plurality of trajectory data, the second position point corresponds to I time period in the plurality of trajectory data, the H time periods include J time periods, the ratio of J to H is greater than or equal to a third threshold, for a second time period in the J time periods, the I time period includes the third time period, the second time period and the third time period are located on the same trajectory data, the interval between the second time period and the third time period is less than or equal to a fourth threshold, and the second time period is any time period within the J time periods; The third condition is: the distance between the first position point and the second position point is less than or equal to the fifth threshold, the distance between the first position point and the second position point is calculated by the coordinates of the first position point and the coordinates of the second position point, and the coordinates of the first position point are obtained by summing the position coordinates collected in the one or more time periods and taking the average.

6. The method according to claim 5, characterized in that The attributes of the first location point include a first attribute, and the method further includes: A first graph structure is generated based on the adjacent relationship between the plurality of location points; wherein the first graph structure is used to describe the connection relationship between the plurality of location points, and when the first location point is adjacent to the second location point, the first location point and the second location point are connected by an edge in the first graph structure, the first graph structure includes a first category of location points and a second category of location points, an attribute of each location point in the first category includes the first attribute, and an attribute of each location point in the second category does not include the first attribute; The first graph structure is cut to obtain a second graph structure; wherein the edge between any two first-category position points in the first graph structure is cut, the edge between any two second-category position points connected to the first-category position points is cut, and each position point in the second graph structure has a connection relationship with at least one position point.

7. The method according to claim 6, characterized in that The method further comprises: Based on the connection relationship between each position point in the second graph structure, an adjacency distance matrix is ​​obtained; wherein each element in the adjacency distance matrix is ​​used to represent the number of edges between a position point of the second type and a position point of the first type in the second graph structure; Normalizing the adjacency distance matrix to obtain a weight matrix; The weight matrix and the first matrix are multiplied to obtain a second matrix; wherein the elements in the first matrix are used to represent the first attribute included in the attributes of each first-category location point in the second graph structure, and the elements in the second matrix are used to represent the first attribute included in the attributes of each second-category location point in the second graph structure.

8. The method according to claim 6 or 7, characterized in that The first attribute is the coordinates or indoor or outdoor location identifiers of the first location point, and the indoor or outdoor location identifiers are used to indicate whether the first location point is an indoor location point or an outdoor location point.

9. The method according to claim 8, characterized in that The method further comprises: Position positioning, navigation, big data statistical analysis or service recommendation are performed based on the coordinates of each of the multiple location points.

10. The method according to any one of claims 1 to 9, characterized in that The quantity distribution feature includes at least one of normal distribution, Poisson distribution, discrete distribution or interval distribution, and the interval distribution is used to describe the quantity of characteristic signals located in different intervals.

11. The method according to any one of claims 1 to 10, characterized in that The characteristic signal includes one or more of a global navigation satellite system GNSS signal, position coordinates, a radio frequency signal, an optical signal, an acoustic signal, a sensor signal or a geomagnetic signal, wherein the radio frequency signal includes one or more of a WIFI signal, a Bluetooth signal, a cell CELL signal or an ultra-wideband UWB signal.

12. A trajectory data representation device, characterized in that: The device comprises: an acquisition unit, configured to acquire a plurality of trajectory data, each of the plurality of trajectory data comprising a plurality of time periods and a characteristic signal collected in each of the plurality of time periods; a processing unit, configured to generate a plurality of location points and an attribute of each of the plurality of location points based on the plurality of trajectory data; Among them, the multiple position points include a first position point, the first position point corresponds to one or more time periods in the multiple trajectory data, the combination identifier of each time period in the one or more time periods is the same, the combination identifier of each time period is generated by the identification ID of at least one characteristic signal corresponding to each time period, and the first position point is represented by the combination identifier; the characteristic signals collected in the one or more time periods include at least one type of characteristic signals, and the attributes of the first position point include the number of each type of characteristic signals in the at least one type of characteristic signals and / or the quantity distribution characteristics of each type of characteristic signals.

13. The device according to claim 12, characterized in that The one or more time periods include a first time period, the first time period includes M characteristic signals, the M characteristic signals include C type characteristic signals, and M and C are positive integers; The combined identifier is generated by the IDs of N characteristic signals among the M characteristic signals, wherein the N characteristic signals include D-type characteristic signals, N is a positive integer less than or equal to M, and D is a positive integer less than or equal to C.

14. The device according to claim 13, characterized in that The C-type characteristic signals include the first-type characteristic signals; The M characteristic signals include A first-category characteristic signals, the N characteristic signals include B first-category characteristic signals, the A first-category characteristic signals include the B first-category characteristic signals, and the signal strength of the B first-category characteristic signals is greater than the signal strength of other characteristic signals in the A first-category characteristic signals; wherein B is a positive integer less than or equal to A.

15. The device according to claim 14, characterized in that The attributes of the first location point further include L first-category characteristic signals, and the L first-category characteristic signals conform to the quantity distribution characteristics of the first-category characteristic signals.

16. The device according to any one of claims 12 to 15, characterized in that The multiple position points further include a second position point, and a combined identifier representing the second position point is generated by the IDs of E characteristic signals; When the first position point and the second position point satisfy one or more of the first condition, the second condition, or the third condition, the first position point is adjacent to the second position point; The first condition is that: the E characteristic signals and the N characteristic signals contain common G characteristic signals, the ratio of G to E and the ratio of G to N are both greater than or equal to a first threshold; and the difference between the average signal strength of the first signal in the E characteristic signals and the average signal strength of the first signal in the N characteristic signals is less than or equal to a second threshold, and the first signal is any one of the G characteristic signals; The second condition is: the first position point corresponds to H time periods in the plurality of trajectory data, the second position point corresponds to I time period in the plurality of trajectory data, the H time periods include J time periods, the ratio of J to H is greater than or equal to a third threshold, for a second time period in the J time periods, the I time period includes the third time period, the second time period and the third time period are located on the same trajectory data, the interval between the second time period and the third time period is less than or equal to a fourth threshold, and the second time period is any time period within the J time periods; The third condition is: the distance between the first position point and the second position point is less than or equal to the fifth threshold, the distance between the first position point and the second position point is calculated by the coordinates of the first position point and the coordinates of the second position point, and the coordinates of the first position point are obtained by summing the position coordinates collected in the one or more time periods and taking the average.

17. The device according to claim 16, characterized in that The attributes of the first location point include a first attribute, and the processing unit is further configured to: A first graph structure is generated based on the adjacent relationship between the plurality of location points; wherein the first graph structure is used to describe the connection relationship between the plurality of location points, and when the first location point is adjacent to the second location point, the first location point and the second location point are connected by an edge in the first graph structure, the first graph structure includes a first category of location points and a second category of location points, an attribute of each location point in the first category includes the first attribute, and an attribute of each location point in the second category does not include the first attribute; The first graph structure is cut to obtain a second graph structure; wherein the edge between any two first-category position points in the first graph structure is cut, the edge between any two second-category position points connected to the first-category position points is cut, and each position point in the second graph structure has a connection relationship with at least one position point.

18. The device according to claim 17, characterized in that The processing unit is further configured to: Based on the connection relationship between each position point in the second graph structure, an adjacency distance matrix is ​​obtained; wherein each element in the adjacency distance matrix is ​​used to represent the number of edges between a position point of the second type and a position point of the first type in the second graph structure; Normalizing the adjacency distance matrix to obtain a weight matrix; The weight matrix and the first matrix are multiplied to obtain a second matrix; wherein the elements in the first matrix are used to represent the first attribute included in the attributes of each first-category location point in the second graph structure, and the elements in the second matrix are used to represent the first attribute included in the attributes of each second-category location point in the second graph structure.

19. The device according to claim 17 or 18, characterized in that The first attribute is the coordinates or indoor or outdoor location identifiers of the first location point, and the indoor or outdoor location identifiers are used to indicate whether the first location point is an indoor location point or an outdoor location point.

20. The device according to claim 19, characterized in that The processing unit is further configured to: Position positioning, navigation, big data statistical analysis or service recommendation are performed based on the coordinates of each of the multiple location points.

21. The device according to any one of claims 12 to 20, characterized in that The quantity distribution feature includes at least one of normal distribution, Poisson distribution, discrete distribution or interval distribution, and the interval distribution is used to describe the quantity of characteristic signals located in different intervals.

22. The device according to any one of claims 12 to 21, characterized in that The characteristic signal includes one or more of a global navigation satellite system GNSS signal, position coordinates, a radio frequency signal, an optical signal, an acoustic signal, a sensor signal or a geomagnetic signal, wherein the radio frequency signal includes one or more of a WIFI signal, a Bluetooth signal, a cell CELL signal or an ultra-wideband UWB signal.

23. A computer device, characterized in that: The computer device includes at least one processor, a memory and an interface circuit, the memory, the interface circuit and the at least one processor are interconnected via lines, and instructions are stored in the at least one memory; when the instructions are executed by the processor, any one of the methods in claims 1 to 11 above is implemented.

24. The device according to claim 23, characterized in that The computer device is a server or a terminal device, wherein the terminal device includes a mobile phone, a computer, a car computer or a tablet.

25. A chip system, comprising at least one processor, a memory and an interface circuit, wherein the memory, the interface circuit and the at least one processor are interconnected via lines, and instructions are stored in the at least one memory; when the instructions are executed by the processor, any one of the methods in claims 1-11 above is implemented.

26. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed, any one of the methods in claims 1 to 11 is implemented.

27. A computer program product, characterized in that The computer program product includes program instructions, and when the program instructions are run on a computer, the method according to any one of claims 1 to 11 is implemented.

Images