Fixed-site mining method, device, terminal equipment and readable storage medium

By obtaining the number and time information of the target person appearing in multiple places, using the Gaussian distribution model to process the site feature vector, the problem of incomplete detection of fixed places caused by noise interference in the prior art is solved, and multiple fixed places are realized Accurate detection and efficiency improvement.

CN113139006BActive Publication Date: 2024-11-15SHENZHEN INTELLIFUSION TECHNOLOGIES CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010058281.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-01-19
Publication Date
2024-11-15
Estimated Expiration
2040-01-19

AI Technical Summary

Technical Problem

In the prior art, when detecting a fixed place of a target person, due to interference noise in the frequency, it is impossible to effectively detect each fixed place, especially when there are multiple fixed places for the target person.

Method used

By obtaining the number of times the target person appears in multiple places, determining the probability of his/her in each place, and according to the preset constraints, the Gaussian distribution model is used to process the site feature vector, eliminate noise interference, and accurately determine multiple fixed areas according to the preset constraints. place.

Benefits of technology

It improves the accuracy and efficiency of mining in fixed sites, can accurately detect multiple fixed sites, eliminate noise interference, and improves the excavation effect.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113139006B_ABST
    Figure CN113139006B_ABST
Patent Text Reader

Abstract

The present application is applicable to the field of data processing technology, and provides a fixed place mining method, device, terminal device and readable storage medium, the method comprising: obtaining the number of times a target person appears in multiple places. According to the number of times the target person appears in multiple places, the probability of the target person appearing in each place is determined. According to the preset constraints, i fixed places among the multiple places are determined by the probability of the target person appearing in each of the places, where i is an integer greater than 1. Since the probability of the target person appearing in each place is obtained, i fixed places among the multiple places can be determined by the probability of the target person appearing in each place and the preset constraints. Fixed places are no longer determined by sorting by frequency of occurrence, noise interference can be eliminated, multiple fixed places can be accurately mined, mining efficiency is improved, and mining effect is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and in particular, relates to a fixed-site mining method, apparatus, terminal device, and readable storage medium. Background Art

[0002] A fixed place refers to a location where a target person appears for a long time or regularly, such as the target person's residential area, office building, etc. In some actual applications of security monitoring, it is necessary to explore the target person's fixed place as reference data to analyze the target person.

[0003] In the prior art, after capturing the target person with cameras installed at various locations, the frequency of the target person appearing at each location is counted, and then the frequency is clustered or sorted, and finally the place where the target person appears most frequently is selected as the fixed place of the target person.

[0004] However, in the prior art, since there is interference noise in the acquired frequency, the place with the highest frequency of occurrence is used as the fixed place of the target person. As a result, when the target person has multiple fixed places, only one fixed place can be detected, and every fixed place cannot be effectively detected. Summary of the invention

[0005] The embodiments of the present application provide a fixed-place mining method, apparatus, terminal device, and readable storage medium, which can improve the problem that when a target person has multiple fixed places, each fixed place cannot be effectively detected.

[0006] In a first aspect, an embodiment of the present application provides a fixed place mining method, comprising: obtaining the number of times a target person appears in a plurality of places. According to the number of times the target person appears in the plurality of places, determining the probability of the target person appearing in each place. According to a preset constraint condition, i fixed places among the plurality of places are determined by the probability of the target person appearing in each place, where i is an integer greater than 1.

[0007] In some implementations, obtaining the number of times a target person appears in a plurality of places includes: obtaining a place feature matrix of the target person.

[0008] Accordingly, according to the number of times the target person appears in multiple places, the probability of the target person appearing in each place is determined, including: converting the place feature matrix of the target person into a place feature vector. The place feature vector is input into a preset Gaussian distribution model for processing to obtain the place vector of the target person, wherein the place vector is used to represent the probability of the target person appearing in each place.

[0009] In some other embodiments, obtaining the location feature matrix of the target person includes: collecting multiple images of the target person, determining multiple locations and the number of times the target person appears in the multiple locations, determining the area ranges of the multiple locations, and structuring the number of times the target person appears in the multiple locations according to the mapping relationship between the area ranges and the preset location feature matrix to obtain the location feature matrix of the target person.

[0010] In some other embodiments, obtaining the location feature matrix of the target person includes: collecting images and time information of the appearance of multiple target persons, determining multiple locations, the number of times the target person appears in the multiple locations, and the time points of the appearances. Determining the regional ranges of the multiple locations. According to the mapping relationship between the regional ranges and the preset location feature matrix, the number of times the target person appears in the multiple locations and the time points of the appearances are structured to obtain the location feature matrix of the target person.

[0011] In a second aspect, an embodiment of the present application further provides a fixed-site excavation device, comprising:

[0012] The acquisition module is used to acquire the number of times the target person appears in multiple places. The determination module is used to determine the probability of the target person appearing in each place according to the number of times the target person appears in multiple places. The determination module is also used to determine i fixed places among the multiple places according to the probability of the target person appearing in each place according to the preset constraint conditions, where i is an integer greater than 1.

[0013] In some implementations, the acquisition module is specifically used to acquire a location feature matrix of the target person.

[0014] Correspondingly, the determination module is specifically used to convert the location feature matrix of the target person into a location feature vector. The location feature vector is input into a preset Gaussian distribution model for processing to obtain the location vector of the target person, wherein the location vector is used to represent the probability of the target person appearing in each location.

[0015] In some other embodiments, the acquisition module is specifically used to collect images of multiple target persons, determine multiple places and the number of times the target person appears in the multiple places. Determine the regional ranges of the multiple places. According to the mapping relationship between the regional ranges and the preset place feature matrix, the number of times the target person appears in the multiple places is structured into data to obtain the place feature matrix of the target person.

[0016] In some other embodiments, the acquisition module is specifically used to collect images and time information of the appearance of multiple target persons, determine multiple places, the number of times the target person appears in the multiple places, and the time points when the target person appears. Determine the regional range of the multiple places. According to the mapping relationship between the regional range and the preset place feature matrix, the number of times the target person appears in the multiple places and the time points of the appearance are structured to obtain the place feature matrix of the target person.

[0017] In a third aspect, an embodiment of the present application provides a terminal device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided in the first aspect when executing the computer program.

[0018] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method provided in the first aspect.

[0019] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute the method provided in the first aspect.

[0020] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0021] First, the number of times the target person appears in multiple places is obtained. Then, according to the number of times the target person appears in multiple places, the probability of the target person appearing in each place is determined. Finally, according to the preset constraints, i fixed places in multiple places are determined by the probability of the target person appearing in each place. Since the probability of the target person appearing in each place is obtained, i fixed places in multiple places can be determined by the probability of the target person appearing in each place and the preset constraints. Fixed places are no longer determined by sorting by frequency of occurrence, which can eliminate noise interference, accurately mine multiple fixed places, improve mining efficiency, and improve mining effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0023] Figure 1 This is an application scenario of the fixed-site excavation method provided in an embodiment of the present application;

[0024] Figure 2 It is a flow chart of a fixed-site excavation method provided by an embodiment of the present application;

[0025] Figure 3 is a flow chart of a fixed-site excavation method provided by another embodiment of the present application;

[0026] Figure 4 is a flow chart of a fixed-site excavation method provided by another embodiment of the present application;

[0027] Figure 5 It is a schematic diagram of the regional range grid division in the fixed site excavation method provided by this application;

[0028] Figure 6 It is a structural schematic diagram of a fixed-site excavation device provided in one embodiment of the present application;

[0029] Figure 7 It is a schematic diagram of the structure of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0031] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0032] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0033] Figure 1 An application scenario of a fixed-site excavation method provided by an embodiment of the present application is shown.

[0034] In this scene, there are multiple surveillance cameras 11, each of which is used to capture the image of a target person in a place. The place may include an office building 14, a residence 15, a school 16, etc. In the present application, there may be other types of places, such as streets, shopping malls, etc., which can be imaged by the surveillance camera 11, and there is no limitation here.

[0035] It should be noted that a fixed place refers to a place where the target person appears for a long time or regularly, such as the target person’s office, home, school, etc.

[0036] Among them, each monitoring camera 11 is connected to the server 12 through network communication. The monitoring camera 11 sends the captured image to the server 12 through the network. At the same time, the server 12 can also be connected to other devices through the network. For example, the server 12 can be connected to the smart phone 13, and the smart phone 13 can request to view the fixed place mining information obtained by the server 12. Other devices can also be laptops, tablets, desktop computers, wearable devices, etc., which are not limited here. The network may be in the form of a wired network or a wireless network. A wired network may be a local area network (LAN), a wide area network (WAN), etc. A wireless network may include wireless local area networks (WLAN), near field communication technology (NFC), and a cellular communication network. The cellular communication network may use any communication standard or protocol, including but not limited to the Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), etc.

[0037] Figure 2 A schematic flow chart of a fixed-place mining method provided by the present application is shown. As an example but not a limitation, the method can be applied to the above-mentioned server 12. In some other embodiments, the method can also be applied to smart phones, cloud servers, tablet computers, laptop computers, desktop computers and other devices with computing capabilities.

[0038] like Figure 2 As shown, the fixed-site excavation method comprises:

[0039] S21. Obtain the number of times the target person appears in multiple places.

[0040] In some implementations, at least one monitoring device can be set up in each place as a data point acquisition device. The monitoring device can collect images of the place, and then identify the collected images through an image recognition algorithm to determine whether the target person appears in the place, and update the data value of the corresponding data point of the place according to the recognition result. The data value of the data point is used to indicate the number of times the target person appears at the data point. For example, in a possible scenario, a monitoring device is set up in the lobby of an office building, the parking lot outside the office building, and the road connected to the office building. Then there are data points in three places (hall, parking lot, road). After the corresponding monitoring device identifies and determines that the target person appears in the parking lot and the lobby, the data value of the lobby and parking lot data points can be increased by one. The target person can be a target that needs to be monitored for security, which is not limited here.

[0041] S22. Determine the probability of the target person appearing in each place according to the number of times the target person appears in each of the multiple places.

[0042] In some implementations, the probability of the target person appearing in each place should be the true probability. Since noise points are often collected when collecting data points, noise points refer to the target person passing through a certain place many times, but the place is not a fixed place of the target person. For example, if a road can lead to multiple fixed places at the same time, when going to a fixed place, data points of the road will inevitably be collected, but the road is not a fixed place. Therefore, it is necessary to eliminate noise points through a noise suppression model, such as using a Gaussian distribution model, to obtain the true probability of appearance in each place.

[0043] S23. According to preset constraints, i fixed places among the multiple places are determined by the probability of the target person appearing in each place, where i is an integer greater than 1.

[0044] In some embodiments, the preset constraint condition is used to screen out i places among multiple places that are most likely to be fixed places, and use the i places as fixed places. For example, the preset constraint condition can be to sort the probability of the target person appearing in each place, and then take the top three places in the probability sorting as fixed places, but it is not limited to this.

[0045] In this embodiment, the number of times the target person appears in multiple places is first obtained. Then, according to the number of times the target person appears in multiple places, the probability of the target person appearing in each place is determined. Finally, according to the preset constraints, i fixed places in multiple places are determined by the probability of the target person appearing in each place. Since the probability of the target person appearing in each place is obtained, i fixed places in multiple places can be determined by the probability of the target person appearing in each place and the preset constraints. Fixed places are no longer determined by sorting by frequency of occurrence, which can eliminate noise interference, accurately mine multiple fixed places, improve mining efficiency, and improve mining effect. .

[0046] In some implementations, obtaining the number of times the target person appears in multiple places includes: obtaining a place feature matrix of the target person, wherein the place feature matrix is ​​used to represent the number of times the target person appears in each place in a matrix manner.

[0047] Figure 3 Another schematic flow chart of a fixed-site excavation method provided by the present application is shown. In some embodiments, Figure 3 As shown, the location feature matrix of the target person is obtained, including:

[0048] S31, collecting images in which multiple target persons appear, and determining multiple places and the number of times the target persons appear in the multiple places respectively.

[0049] For example only and not limitation, refer to Figure 1 , multiple images of target persons can be collected by image collection devices distributed in each place, wherein the image collection device can be a monitoring camera 11, each monitoring camera 11 collects images in the corresponding place and sends them to the server 12. The server 12 can determine whether there is a target person in the received image through an image recognition algorithm, and record the place where the target person is collected as a collected data point.

[0050] S32. Determine the area range of multiple places.

[0051] In some implementations, the target person may appear in multiple places, each of which may be a fixed place of the target person. The area range of the fixed place of the target person may be the smallest range that encloses each place where the target person appears, or the smallest administrative area range that includes all places where the target person appears, which is not limited here.

[0052] S33. According to the mapping relationship between the area range and the preset place feature matrix, the number of times the target person appears in multiple places is structured into data to obtain the place feature matrix of the target person.

[0053] In some implementations, the number of times the target person appears in multiple places is structured according to the mapping relationship between the area range and the preset place feature matrix, and the area range can be divided into N grids, where each grid area represents a place, and N is an integer greater than 1.

[0054] Figure 5 A schematic diagram of regional range grid division in the fixed-site excavation method provided in the present application is shown.

[0055] For example only and not limitation, see Figure 1 and Figure 5 , the target people appeared in office buildings 14, residences 15, schools 16 and other places. Figure 5 The area range in is the minimum range of the administrative district including office buildings 14, residences 15, and schools 16. If the preset place feature matrix is ​​a 12×12 matrix, the area range can be divided into 12×12 grids, then there are a total of 144 grids (ie, N is 144), each grid corresponds to an element in the preset place feature matrix, that is, an element in each preset place feature matrix represents a place.

[0056] Then, determine the number of times the target person appears in each grid.

[0057] In some implementations, the collected data points are ,but , where x and y represent the coordinates of the grid corresponding to the data point, and T represents the total number of data points collected. The coordinates of each data point corresponding to the grid are counted, and the number of times the grid coordinate appears is the number of times the target person appears in each grid.

[0058] Finally, the number of times the target person appears in each grid is filled into the preset place feature matrix to obtain the place feature matrix of the target person.

[0059] In some other implementations, the location feature matrix also includes the time point at which the target person appears in each location.

[0060] Figure 4 Another schematic flow chart of a fixed-site excavation method provided by the present application is shown. In some embodiments, Figure 4 As shown, the location feature matrix of the target person is obtained, including:

[0061] S34, collecting images and time information of multiple target persons appearing, determining multiple places, the number of times the target person appears in the multiple places, and the time points of the appearances.

[0062] The collection method in S34 is the same as that in S31, except that when recording the collected data points, the collection time is also recorded.

[0063] S35. Determine the area range of multiple places.

[0064] S36. According to the mapping relationship between the area range and the preset place feature matrix, the number of times the target person appears in multiple places and the time points of the appearance are structured to obtain the place feature matrix of the target person.

[0065] Among them, in S35 and S36, determining the area range and the mapping relationship between the area range and the preset place feature matrix are the same as those in S32 and S33, and are not repeated here.

[0066] In some implementations, the data points collected in S34 are assumed to be ,but , where x and y represent the coordinates of the grid corresponding to the data point, t represents the time point when the target person appears in the grid, and T represents the total number of data points collected. The coordinates of the grid corresponding to each data point are counted, and the number of times the grid coordinates appear is the number of times the target person appears in each grid.

[0067] Then, the place feature matrix that only represents the geographic location information can be obtained through the method in S31-S33, and then the matrix can be extended in the time direction, and the time point of each collected data point can be filled in to obtain a three-dimensional matrix that represents both the geographic location information and the time point information, which serves as the place feature matrix of the target person.

[0068] Accordingly, according to the number of times the target person appears in multiple places, the probability of the target person appearing in each place is determined, including:

[0069] Convert the target person's place feature matrix into a place feature vector.

[0070] In some implementations, if the location feature matrix of the target person is an R×R matrix, R>1, each element in the location feature matrix can be arranged in order of rows or columns to obtain a matrix with a dimension of R. 2 The vector of is the place feature vector.

[0071] The above-mentioned place feature vector is input into a preset Gaussian distribution model for processing to obtain the place vector of the target person, wherein the place vector is used to represent the probability of the target person appearing in each place.

[0072] If the venue feature vector does not include the time point, then:

[0073] In some implementations, the preset Gaussian distribution model (model 1) is:

[0074]

[0075] in, It means calculating the probability that the target person appears in one of the places. represents the standard deviation of the Gaussian distribution, represents the probability that the target person appears in the jth location, is the place vector, which is a multidimensional vector, with each dimension corresponding to a place (so There are N dimensions), the value of which is the probability of the target person appearing in the place. l Indicates the physical location where the target person appears. Indicates that the target person appears at a physical location l Longitude information, and normalized to the Cartesian coordinate system, Indicates The longitude information of a fixed place in longitude and latitude is normalized to the Cartesian coordinate system. Indicates that the target person appears at a physical location The latitude information is normalized to the Cartesian coordinate system. Indicates The latitude and longitude information of a fixed place is normalized to the Cartesian coordinate system.

[0076] Referring to the above model, mining the fixed places of the target person is an optimization problem of the following model:

[0077]

[0078] in, Representation vector The solution domain must satisfy and .

[0079] For the above model, the optimization method can be:

[0080] Without considering the constraints, we iterate and solve the problem through the gradient descent method. Then, in the last iteration, we set the constraints and perform conditional mapping so that the vector Satisfy the constraints of the above solution domain.

[0081] Through the Gaussian distribution model and the site feature vector, it is iterated according to the constraints to obtain the site vector that satisfies the solution domain constraints , eliminating the influence of noise points, making The actual probability of the target person appearing in each place improves the accuracy of mining.

[0082] If the location feature vector includes the time point, then:

[0083] The preset Gaussian distribution model (Model 2) is:

[0084]

[0085] in, Indicates the standard deviation of the Gaussian distribution in different time periods. Indicates the time period The target person appears at the physical location The probability of Indicates the time period The target person appears in the jth place at the physical location The probability of Indicates the time period The target person appears at the physical location Longitude information, and normalized to the Cartesian coordinate system, Indicates the time period The target person appears at the physical location The latitude information is normalized to the Cartesian coordinate system.

[0086] Referring to the above model, mining the fixed places of the target person is an optimization problem of the following model:

[0087]

[0088] The optimization method of this model is the same as that of the above model 1 and will not be repeated here.

[0089] In this embodiment, since the time when the target person appears is taken into consideration, the fixed locations of the target person in different time periods can be obtained more accurately, so that the detection effect is further improved.

[0090] The following is an example of how to determine, among multiple places, a place where the probability of the target person appearing is greater than or equal to a preset probability as a fixed place of the target person.

[0091] In some implementations, if the location feature matrix does not include time points, let the location vector of a target person be ={0.2,0.3,0.2,0.1,0.1,0.1}, the preset constraint condition is set to 3, then The top three places in the medium probability ranking are taken as fixed places, that is, the places corresponding to the first dimension, the second dimension, and the third dimension are determined as the fixed places of the target person.

[0092] In some other embodiments, if the location feature matrix includes time points, assuming that the preset constraint condition is set to 3, the location vector of a target person in the first time period is ={0.2,0.3,0.2,0.1,0.1,0.1}, then within the first time range, The top three places with the highest probability are taken as fixed places, that is, the places corresponding to the first dimension, the second dimension, and the third dimension are determined as the fixed places of the target person. If the place vector of the target person in the second time range is ={0,0.1,0.2,0.5,0.2,0}, then in the second time period The top three places in the medium probability ranking are taken as fixed places, that is, the places corresponding to the third dimension, the fourth dimension, and the fifth dimension are determined as the fixed places of the target person, but this is not limited to this.

[0093] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0094] Corresponding to the fixed-site excavation method described in the above embodiment, Figure 6 A structural block diagram of a fixed-site excavation device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0095] Reference Figure 6 , the fixed site excavation device comprises:

[0096] The acquisition module 41 is used to acquire the number of times the target person appears in multiple places. The determination module 42 is used to determine the probability of the target person appearing in each place according to the number of times the target person appears in the multiple places. The determination module 42 is also used to determine i fixed places among the multiple places according to the probability of the target person appearing in each place according to the preset constraint conditions, where i is an integer greater than 1.

[0097] In some implementations, the acquisition module 41 is specifically configured to acquire a location feature matrix of a target person.

[0098] Accordingly, the determination module 42 is specifically used to convert the location feature matrix of the target person into a location feature vector. The location feature vector is input into a preset Gaussian distribution model for processing to obtain the location vector of the target person, wherein the location vector is used to represent the probability of the target person appearing in each location.

[0099] In some other embodiments, the acquisition module 41 is specifically used to collect images where multiple target persons appear, determine multiple places and the number of times the target person appears in the multiple places. Determine the regional ranges of the multiple places. According to the mapping relationship between the regional ranges and the preset place feature matrix, the number of times the target person appears in the multiple places is structured into data to obtain the place feature matrix of the target person.

[0100] In some other embodiments, the acquisition module 41 is specifically used to collect images and time information of the appearance of multiple target persons, determine multiple places, the number of times the target person appears in the multiple places, and the time points when the target person appears. Determine the regional range of the multiple places. According to the mapping relationship between the regional range and the preset place feature matrix, the number of times the target person appears in the multiple places and the time points of the appearance are structured to obtain the place feature matrix of the target person.

[0101] It should be noted that the information interaction, execution process and other contents between the modules in the above-mentioned device are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0102] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0103] The present application also provides a terminal device, Figure 7 A schematic diagram of the structure of a terminal device is shown.

[0104] like Figure 7 As shown, the terminal device 5 includes a memory 52, a processor 51, and a computer program 53 stored in the memory 5 and executable on the processor 51. When the processor 51 executes the computer program 53, the above-mentioned video playback method is implemented.

[0105] The processor 51 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0106] In some embodiments, the memory 52 may be an internal storage unit of the terminal device 5, such as a hard disk, flash memory or memory of the terminal device 5. In other embodiments, the memory 52 may also be an external storage device of the terminal device 5, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 5. Further, the memory 52 may also include both an internal storage unit and an external storage device of the terminal device 5. The memory 52 is used to store an operating system, an application program, a boot loader (BootLoader), data and other programs, such as program code of a computer program 53, video data, etc. The memory 52 may also be used to temporarily store data that has been output or is to be output.

[0107] In some implementations, the intelligent robot 5 may also include an audio acquisition device, a network module, a button, a mobile device, an image acquisition device, a projection device, etc., and realize functions such as intelligent word learning, an interactive drawing board, remote monitoring, and movement through the above devices, which will not be elaborated here.

[0108] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0109] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0110] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the terminal device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0111] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0112] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0113] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, 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, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] The embodiments described above 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 aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such 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, and should all be included in the protection scope of the present application.

Claims

1. A fixed-site excavation method, characterized in that: include: Get the number of times the target person appears in multiple places; Determining the probability of the target person appearing in each of the multiple places according to the number of times the target person appears in each of the multiple places; According to the preset constraint conditions, i fixed places among the multiple places are determined by the probability of the target person appearing in each of the multiple places, wherein i is an integer greater than 1, and the preset constraint conditions are used to screen out i places among the multiple places that are most likely to be fixed places, and use the i places as fixed places; The obtaining of the number of times the target person appears in multiple places includes: Obtain the location feature matrix of the target person; Accordingly, determining the probability of the target person appearing in each of the multiple places according to the number of times the target person appears in each of the multiple places includes: Converting the target person's location feature matrix into a location feature vector; Inputting the place feature vector into a preset Gaussian distribution model for processing to obtain a place vector of the target person, wherein the place vector is used to represent the probability of the target person appearing in each of the places; If the venue feature vector does not include a time point, the preset Gaussian distribution model is: in, It means calculating the probability that the target person appears in one of the places. Indicates that the target person appears in j The probability of a place, represents the standard deviation of the Gaussian distribution, represents the probability that the target person appears in the jth location, is the location vector, N is The number of dimensions that exist, l Indicates the physical location where the target person appears. Indicates that the target person appears at a physical location l Longitude information, and normalized to the Cartesian coordinate system, Indicates The longitude information of a fixed place in longitude and latitude, and normalized to the Cartesian coordinate system, Indicates that the target person appears at a physical location The latitude information is normalized to the Cartesian coordinate system. Indicates The latitude information of a fixed place in longitude and latitude, and normalized to the Cartesian coordinate system; If the venue feature vector includes a time point, the preset Gaussian distribution model is: in, Indicates the standard deviation of the Gaussian distribution in different time periods. Indicates the time period The target person appears at the physical location The probability of Indicates the time period The target person appears in the jth place at the physical location The probability of Indicates the time period The target person appears at the physical location Longitude information, and normalized to the Cartesian coordinate system, Indicates the time period The target person appears at the physical location The latitude information is normalized to the Cartesian coordinate system.

2. The method according to claim 1, characterized in that The method of obtaining the location feature matrix of the target person includes: Collecting multiple images in which the target person appears, and determining the multiple places and the number of times the target person appears in the multiple places respectively; determining the regional scope of the plurality of locations; According to the mapping relationship between the area range and the preset place feature matrix, the number of times the target person appears in multiple places is structured to obtain the place feature matrix of the target person.

3. The method according to claim 1, characterized in that The method of obtaining the location feature matrix of the target person includes: Collecting multiple images and time information of the target person appearing, and determining the multiple places, the number of times the target person appears in the multiple places, and the time points of the appearances; determining the regional scope of the plurality of locations; According to the mapping relationship between the area range and the preset place feature matrix, the number of times the target person appears in multiple places and the time points of the appearance are respectively structured to obtain the place feature matrix of the target person.

4. A fixed-site excavation device, characterized in that: include: An acquisition module is used to acquire the number of times a target person appears in multiple places; A determination module, used to determine the probability of the target person appearing in each of the multiple places according to the number of times the target person appears in each of the multiple places; The determination module is further used to determine i fixed places among the multiple places according to the probability of the target person appearing in each of the places according to the preset constraint conditions, wherein i is an integer greater than 1, and the preset constraint conditions are used to screen out i places among the multiple places that are most likely to be fixed places, and use the i places as fixed places; The acquisition module is specifically used to acquire the location feature matrix of the target person; Accordingly, the determination module is specifically used to convert the place feature matrix of the target person into a place feature vector; Inputting the place feature vector into a preset Gaussian distribution model for processing to obtain a place vector of the target person, wherein the place vector is used to represent the probability of the target person appearing in each of the places; If the venue feature vector does not include a time point, the preset Gaussian distribution model is: in, It means calculating the probability that the target person appears in one of the places. Indicates that the target person appears in j The probability of a place, represents the standard deviation of the Gaussian distribution, represents the probability that the target person appears in the jth location, is the location vector, N is The number of dimensions that exist, l Indicates the physical location where the target person appears. Indicates that the target person appears at a physical location l Longitude information, and normalized to the Cartesian coordinate system, Indicates The longitude information of a fixed place in longitude and latitude is normalized to the Cartesian coordinate system. Indicates that the target person appears at a physical location The latitude information is normalized to the Cartesian coordinate system. Indicates The latitude information of a fixed place in longitude and latitude, and normalized to the Cartesian coordinate system; If the venue feature vector includes a time point, the preset Gaussian distribution model is: in, Indicates the standard deviation of the Gaussian distribution in different time periods. Indicates the time period The target person appears at the physical location The probability of Indicates the time period The target person appears in the jth place at the physical location The probability of Indicates the time period The target person appears at the physical location Longitude information, and normalized to the Cartesian coordinate system, Indicates the time period The target person appears at the physical location The latitude information is normalized to the Cartesian coordinate system.

5. The device according to claim 4, characterized in that The acquisition module is specifically used to collect multiple images in which the target person appears, and determine the multiple places and the number of times the target person appears in the multiple places respectively; determining the regional scope of the plurality of locations; According to the mapping relationship between the area range and the preset place feature matrix, the number of times the target person appears in multiple places is structured to obtain the place feature matrix of the target person.

6. The device according to claim 4, characterized in that The acquisition module is specifically used to collect multiple images and time information of the target person appearing, determine the multiple places, the number of times the target person appears in the multiple places, and the time point of the appearance; determining the regional scope of the plurality of locations; According to the mapping relationship between the area range and the preset place feature matrix, the number of times the target person appears in multiple places and the time points of the appearance are respectively structured to obtain the place feature matrix of the target person.

7. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 3 is implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.