A method, apparatus, and computer-readable storage medium for processing facial data.

Abstract

This application discloses a method, apparatus, and computer-readable storage medium for processing facial image data. The method includes: acquiring aggregated facial image data, which includes multiple facial image data of different individuals; grouping the aggregated facial image data to obtain multiple first facial image datasets, wherein the facial image data in the first facial image datasets satisfy the first preset conditions, the first preset conditions including that the camera devices corresponding to the facial image data are the same and the identifiers of the individuals are the same; sorting the first facial image datasets to obtain second facial image datasets; cleaning the facial image data in the second facial image datasets based on the type of the task to be processed to obtain third facial image datasets; and generating early warning information related to the task to be processed when multiple third facial image datasets corresponding to the same target individual satisfy the second preset conditions. Through the above method, this application can remove redundant data, reduce the pressure of big data processing, and reduce storage consumption.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and specifically to a method, apparatus, and computer-readable storage medium for processing human portrait data. Background Technology

[0002] With the increasing prevalence of surveillance equipment, the amount of data collected is also growing. Technical departments need more precise methods to determine the accuracy and reliability of data from monitored locations. When a monitored object appears in multiple locations, the duration of its activity varies depending on the monitoring equipment. Therefore, only a small portion of the continuous snapshot data collected by the equipment is meaningful in post-processing; the majority is redundant. Thus, how to remove redundant data to reduce the burden of subsequent data processing has become an urgent problem to solve. Summary of the Invention

[0003] This application provides a method, apparatus, and computer-readable storage medium for processing human image data, which can remove redundant data and reduce the pressure of big data processing and storage consumption.

[0004] To address the aforementioned technical problems, the technical solution adopted in this application is as follows: A method for processing portrait data is provided. This method includes: acquiring aggregated portrait data, which includes multiple portrait data of different individuals; grouping the aggregated portrait data to obtain multiple first portrait datasets, wherein the portrait data in the first portrait datasets satisfy a first preset condition, the first preset condition including that the camera devices corresponding to the portrait data are the same and the identifiers of the individuals are the same; sorting the first portrait datasets to obtain second portrait datasets; cleaning the portrait data in the second portrait datasets based on the type of the task to be processed to obtain a third portrait dataset; and generating early warning information related to the task to be processed when multiple third portrait datasets corresponding to the same target individual satisfy the second preset condition.

[0005] To solve the above-mentioned technical problems, another technical solution adopted in this application is: to provide a data processing device, which includes a memory and a processor connected to each other, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, it is used to implement the image data processing method in the above-mentioned technical solution.

[0006] To solve the above-mentioned technical problems, another technical solution adopted in this application is to provide a computer-readable storage medium for storing a computer program, which, when executed by a processor, is used to implement the image data processing method in the above-mentioned technical solution.

[0007] The beneficial effects of this application through the above scheme are as follows: It acquires aggregated portrait data, which includes multiple portrait data of different individuals; it groups portrait data that meet a first preset condition into a first portrait dataset, the first preset condition including that the portrait data correspond to the same camera device and that the individual's identifier is the same; it then sorts the first portrait dataset to obtain a second portrait dataset; it then cleans the portrait data in the second portrait dataset using the type of the task to be processed to obtain a third portrait dataset; if multiple third portrait datasets corresponding to the same target individual meet the second preset condition, it generates early warning information related to the task to be processed; by grouping and sorting the portrait data, and filtering the captured portrait data in conjunction with the type of the task to be processed, redundant data is removed, achieving optimization, so that the third portrait dataset can be used to execute the task to be processed, greatly reducing the load pressure of processing large amounts of data and reducing data storage consumption. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0009] Figure 1 This is a flowchart illustrating an embodiment of the image data processing method provided in this application;

[0010] Figure 2 This is a flowchart illustrating another embodiment of the facial data processing method provided in this application;

[0011] Figure 3 This is a schematic diagram of the structure of an embodiment of the data processing apparatus provided in this application;

[0012] Figure 4 This is a schematic diagram of an embodiment of the computer-readable storage medium provided in this application. Detailed Implementation

[0013] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be particularly noted that the following embodiments are for illustrative purposes only and do not limit the scope of the application. Similarly, the following embodiments are only some, not all, embodiments of the present application, and all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of the present application.

[0014] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0015] It should be noted that the terms "first," "second," and "third" in this application are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0016] Please see Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the facial data processing method provided in this application. The method includes:

[0017] S11: Obtain portrait cluster data.

[0018] Human image clustering data can be obtained from image databases or collected by using camera equipment to capture the current monitoring scene. This human image clustering data includes multiple human image data of different people.

[0019] In one specific embodiment, the camera device captures images of the monitored scene, generating video data. The video data is then cleaned in a data warehouse to obtain portrait aggregated data, which is then sent to an image database. Specifically, the portrait data includes face data. The size of the face capture area can be determined based on the function of each camera device. In actual use, captured portraits or portraits obtained from captured videos are stored in an image database specifically for storing portraits. Therefore, the amount of portrait aggregated data is enormous. Due to the large amount of data, resource load requirements are very high, and most of this data is redundant. For the task to be processed, only a small portion of the data is usable. Therefore, data filtering is necessary. The following describes how data filtering is performed.

[0020] S12: Group the portrait data to obtain multiple sets of first portrait datasets.

[0021] First, the portrait data is grouped according to the set rules to generate multiple first portrait datasets. The portrait data in the first portrait datasets meet the first preset conditions, which include that the camera devices corresponding to the portrait data are the same and the indentation (ID) of the person is the same. By grouping the person's ID with the capture point (i.e., the location of the camera device or the location of the person), the subject (i.e., the person) and the capture point can be determined.

[0022] In a specific embodiment, grouping can also be based on a filtering time interval accurate to the minute (e.g., 1 minute or 10 minutes). For example, assuming a 1-minute filtering time interval is used as the grouping basis, portrait data A1 and portrait data A2 are both data corresponding to person P1, portrait data A3 and portrait data A4 are both data corresponding to person P2, portrait data A1 and portrait data A2 are captured by camera device C1, portrait data A3 is captured by camera device C2, and portrait data A4 is captured by camera device C3. The capture time corresponding to portrait data A1 is 5 minutes and 10 seconds, the capture time corresponding to portrait data A2 is 6 minutes and 5 seconds, the capture time corresponding to portrait data A3 is 8 minutes and 30 seconds, and the capture time corresponding to portrait data A4 is 9 minutes and 20 seconds. Then, portrait data A1 and portrait data A2 are assigned to the first portrait dataset G1, portrait data A3 is assigned to the first portrait dataset G2, and portrait data A4 is assigned to the first portrait dataset G3. Of course, the filtering time interval can also be other times. For example, if the task to be processed is theft monitoring, the filtering time interval for the facial data can be set to a longer interval, such as 10 minutes. That is, for the same person and the same camera device, the time interval between two adjacent first facial data sets is 10 minutes. For example, first facial data set K1 corresponds to 10-20 minutes, and first facial data set K2 corresponds to 20-30 minutes. Understandably, if the facial data is a video clip, the capture time can be the start time of the video.

[0023] Furthermore, to facilitate the storage of the capture time corresponding to each portrait data, the capture time can be converted to obtain the corresponding number of minutes and stored in the image database. Specifically, the following methods can be used: ① Obtain the number of minutes through the time function in related technologies; ② Convert the capture time into a capture time number and then divide it by 1000 to obtain the number of minutes; ③ Convert the capture time into a string and take the length accurate to the minute to obtain the number of minutes.

[0024] S13: Sort the first portrait dataset to obtain the second portrait dataset.

[0025] After grouping the portrait images, the generated first portrait dataset can be sorted, for example, by sorting in ascending order of capture time or by sorting in descending order of capture time; for example, sorting by capture time accurate to the second (i.e., the original capture time field).

[0026] S14: Clean the portrait data in the second portrait dataset based on the type of task to be processed to obtain the third portrait dataset.

[0027] After obtaining the second portrait dataset, a cleaning method can be used to clean it, resulting in a cleaned portrait dataset (i.e., the third portrait dataset). For example, the cleaning method can be to select a preset number of portrait data from the second portrait dataset. The cleaning frequency (i.e., the number of portrait data extracted from each second portrait dataset) can be set according to application needs or experience. Specifically, when the type of the task to be processed is a first preset type, a first preset number of portrait data are selected from the second portrait dataset to form the third portrait dataset; when the type of the task to be processed is a second preset type, a second preset number of portrait data are selected from the second portrait dataset to form the third portrait dataset. The first preset number is less than the second preset number. The first preset type can be location tracking, and the second preset type can be theft monitoring.

[0028] Furthermore, when the same person is captured continuously in the same space, a single image from the second image dataset can be selected to perform the task to be processed. For example, if the task to be processed is to locate the landing point, a single image can be selected at one-minute intervals to achieve the landing point location.

[0029] S15: When multiple third-person portrait datasets corresponding to the same target person meet the second preset condition, generate early warning information related to the task to be processed.

[0030] After cleaning the facial image data, the generated third-party facial image dataset can be applied to the task at hand. Specifically, it determines whether multiple third-party facial image datasets for the same target person meet a second preset condition. If so, it indicates that the conditions for generating an early warning message are met. This warning message, related to the task at hand, can be sent to a preset contact person or organization, or displayed and / or played. For example, the third-party facial image dataset can be used to determine the target person's location, thus determining if their whereabouts have changed. If a change is detected, an early warning message is generated. Alternatively, the third-party facial image dataset can be used to determine if a theft has occurred; if so, an early warning message is generated.

[0031] This embodiment filters captured portrait data by sorting and deduplicating the data, removing redundant data to achieve optimization. Redundant portrait data can be filtered by specifying the data filtering frequency. In addition, the captured portrait data can be more precisely adjusted according to business requirements, making the portrait dataset for business logic calculations corresponding to the task in question a more concise, accurate, and unified dataset. This saves a lot of resources, improves computing performance, and effectively reduces computing time when using portrait data for correlation.

[0032] Please see Figure 2 , Figure 2 This is a flowchart illustrating another embodiment of the facial data processing method provided in this application, the method comprising:

[0033] S201: Obtain facial image clustering data.

[0034] S201 is the same as S11 in the above embodiment, and will not be described again here.

[0035] S202: Select one portrait data from the portrait data in the portrait cluster data as the current portrait data.

[0036] To group the portrait archive data, one portrait data point can be extracted from the portrait archive data as the current portrait data.

[0037] S203: Determine whether the identifier of the current portrait data is the same as the identifier of the remaining portrait data in the portrait aggregation data.

[0038] For the current portrait data, it can be determined whether the identifier of the current portrait data is the same as the identifier of the remaining portrait data. That is, it can be determined whether the person in the current portrait data is the same person as the person in the remaining portrait data. The remaining portrait data is the portrait data other than the current portrait data in the portrait aggregation data.

[0039] S204: If the identifier of the current portrait data is the same as the identifier of the remaining portrait data, then based on the camera device corresponding to the portrait data, the portrait data is grouped to generate the first portrait dataset.

[0040] If the identifier of the current portrait data is the same as the identifier of the remaining portrait data, it indicates that the people in the two are the same and may meet the conditions to be assigned to the same group. At this time, further processing is required, that is, the portrait data is grouped by using the camera device corresponding to the portrait data.

[0041] In a specific embodiment, it can be determined whether the camera device corresponding to the current portrait data is the same as the camera device corresponding to the remaining portrait data. If the camera device corresponding to the current portrait data is the same as the camera device corresponding to the remaining portrait data, it indicates that the two were shot using the same camera device. At this time, it can be determined that the current portrait data and the remaining portrait data meet the first preset condition, and the current portrait data and the remaining portrait data are placed into the same first portrait data set. If the camera device corresponding to the current portrait data is different from the camera device corresponding to the remaining portrait data, it indicates that the two were shot using different camera devices. At this time, it can be determined that the current portrait data and the remaining portrait data do not meet the first preset condition, and the current portrait data and the remaining portrait data are placed into different first portrait data sets respectively.

[0042] In another specific embodiment, the first preset condition further includes the capture time of each portrait data in the first portrait dataset falling within a first preset time period, which can be achieved using the following scheme:

[0043] 1) Determine whether the camera device corresponding to the current portrait data is the same as the camera device corresponding to the remaining portrait data.

[0044] 2) If the camera device corresponding to the current portrait data is the same as the camera device corresponding to the remaining portrait data, then determine whether the first capture time and the second capture time fall within the first preset time period.

[0045] The first capture time is the capture time of the current portrait data, and the second capture time is the capture time of the remaining portrait data.

[0046] 3) If the first capture time and the second capture time fall within the first preset time period, then the current portrait data and the remaining portrait data are determined to meet the first preset condition, and the current portrait data and the remaining portrait data are put into the same first portrait data set.

[0047] In other embodiments, it can also be determined whether the difference between the first capture time and the second capture time falls within a preset difference range; if the difference between the first capture time and the second capture time falls within the preset difference range, then the two are grouped into the same group. For example, assuming the preset difference range is 1 minute, the first capture time is 30 minutes and 20 seconds, and the second capture time is 31 minutes and 15 seconds, then the two can be grouped into the same group.

[0048] 4) If the difference between the first capture time and the second capture time does not fall within the first preset time period, it is determined that the current portrait data and the remaining portrait data do not meet the first preset condition, and the current portrait data and the remaining portrait data are put into different first portrait datasets.

[0049] 5) If the camera device corresponding to the current portrait data is different from the camera device corresponding to the remaining portrait data, it is determined that the current portrait data and the remaining portrait data do not meet the first preset condition, and the current portrait data and the remaining portrait data are put into different first portrait data sets.

[0050] S205: If the identifier of the current portrait data is different from the identifier of the remaining portrait data, it is determined that the current portrait data and the remaining portrait data do not meet the first preset condition, and the current portrait data and the remaining portrait data are placed into different first portrait datasets.

[0051] If the identifier of the current portrait data is different from the identifier of the remaining portrait data, it indicates that the two records are not the data of the same person. In this case, they need to be put into different first portrait datasets.

[0052] S206: Sort all the portrait data in the first portrait dataset according to the order of the capture time from smallest to largest to obtain the second portrait dataset.

[0053] After grouping the portrait data, the first portrait dataset of each group can be sorted, for example, by arranging the portrait data in ascending order of capture time, to generate a sorted portrait dataset (i.e., the second portrait dataset).

[0054] S207: Select a preset number of portrait data from the second portrait dataset to form a third portrait dataset.

[0055] A preset number of portrait data points for each person and each capture point can be selected to form a third portrait dataset. The preset number can be set according to specific application needs or experience. For example, the first portrait data point in the second portrait dataset can be used as the third portrait dataset. Of course, if there are special business requirements, the first two or three portrait data points in the second portrait dataset can also be used as the third portrait dataset. For example, if some business requires two portrait data points to be captured every minute, the first two portrait data points in the second portrait dataset can be used. This can filter out other useless data and unify the capture frequency between different people and different capture points, so as to obtain the same number of data samples (i.e., portrait data in the third portrait dataset) for the processing tasks.

[0056] S208: Process multiple third-party portrait datasets to obtain the processing results.

[0057] This embodiment uses the example of a change in the landing point of a task to be processed. The change in the landing point corresponds to a specified time period. For example, if the landing point of a suspect this week changes from the landing point last week, it is considered that a change in the landing point has occurred. The specified time period is from last week to this week.

[0058] S209: Process the processing result to generate a landing position, and determine whether the second preset condition is met based on the landing position.

[0059] The second preset condition is to determine whether the landing position (i.e., the position of the target person) has changed.

[0060] S210: If the second preset condition is determined to be met, then an early warning message related to the task to be processed is generated.

[0061] The landing location includes a first landing location and a second landing location. Based on the location configuration data and multiple third-party portrait datasets, a processing result is generated. The processing result is then processed to generate the first landing location and the second landing location. It is then determined whether the distance between the first landing location and the second landing location is greater than a preset distance. If the distance between the first landing location and the second landing location is greater than the preset distance, it is determined that the second preset condition is met, and an early warning message is generated. If the distance between the first landing location and the second landing location is less than or equal to the preset distance, it is determined that the second preset condition is not met, and no early warning message needs to be generated.

[0062] Furthermore, the location configuration data includes the location of the camera device corresponding to each portrait data in the portrait cluster data, as well as the identifier of the camera device corresponding to the location. The identifier of the camera device corresponding to the third portrait dataset can be matched with the location configuration data to obtain the location of the camera device; then the location of the camera device is determined as the landing location; based on the landing location, the processing result is generated.

[0063] In one specific embodiment, the processing result includes the number of times or the number of days the target person appears at the same location within a second preset time period. Based on the location of the person's arrival, it can be determined whether the number of times the target person appears at the same location within the second preset time period is greater than a preset number. If the number of times the target person appears at the same location within the second preset time period is greater than the preset number, then that location is determined as the location of the person's arrival. Alternatively, it can be determined whether the number of days the target person appears at the same location within the second preset time period is greater than a preset number of days. If the number of days the target person appears at the same location within the second preset time period is greater than the preset number of days, then that location is determined as the location of the person's arrival.

[0064] In another specific embodiment, the processing result includes the duration of stay or appearance time of the target person at the same location within a second preset time period, where the second preset time period is a pre-set time period, such as one week or one month; it can be determined whether the appearance time of the target person at the same location within the second preset time period falls within a third preset time period, where the third preset time period is a pre-set time period, such as a certain time period within a day, such as 17:00 to 20:00; if the appearance time of the target person at the same location within the second preset time period falls within the third preset time period, then the duration of stay of the target person at that location is statistically analyzed to obtain a statistical duration; then it is determined whether the average value of the statistical duration is greater than a preset duration; if the average value of the statistical duration is greater than the preset duration, then the location is determined to be the place of stay.

[0065] In one implementation, taking the target person as a suspect as an example, it is necessary to detect whether there is any change in the suspect's location in the previous month (30 days ago) and the location in the month before last (30 to 60 days ago). Therefore, it is necessary to obtain the facial image data of the previous month and the data of the month before last from the facial image archive data for calculation.

[0066] To determine whether there has been any change in the suspect's location, the following basic indicators can be used as a reference: the number of times the suspect appeared at the same location within a month, the total duration of the suspect's stay at the same location within a month, the number of days the suspect appeared at the same location within a month, or whether the suspect's stay at a certain location within a month was during the day or at night. These indicators can be obtained by calculating the facial recognition data and the location configuration data of the camera equipment.

[0067] Based on the indicators for determining the suspect's hideout, judgment criteria can be set. For example, if the suspect appears at the same location more than 10 times at night within a month, or if the suspect appears at the same location at night within a month and stays there for an average of more than 6 hours, or if the suspect appears at the same location for more than 5 days within a month, then the location can be determined to be the suspect's hideout within that month.

[0068] After obtaining the location of the person's whereabouts for the previous month and the month before last, the distance between the two locations is calculated based on their Global Positioning System (GPS) coordinates. Then, according to a specified standard, such as setting 500 meters as the boundary distance for changes in location, if the distance between the two locations is greater than 500 meters, it can be determined that the person's whereabouts for the previous two months have changed. Information such as the suspect's information, the GPS coordinates and addresses of the two locations are obtained to generate an early warning.

[0069] The above solution provides a method for determining location anomalies based on facial image data. Assuming a target person stays in different locations, and a monitoring device at location A captures ten data points within one minute, while a monitoring device at location B captures three data points within one minute, it cannot be concluded that the person is more active at location A than at location B. This is because even with multiple data points, most are redundant and meaningless. Therefore, this solution cleans the redundant data by adding time interval conditions, such as retaining only one facial image data point per minute, resulting in more accurate and reliable results.

[0070] This embodiment performs redundant data filtering on the portrait archive data at a specified frequency according to the type of task to be processed, making the portrait archive dataset more concise and making the frequency of portrait data of different people and different locations more uniform, that is, the number of portrait data in the third portrait dataset is the same; moreover, the portrait data of each person and location is compressed to a certain extent, reducing the data volume by 3 to 4 times, which can greatly reduce the data storage space, shorten the program running time, and maintain the stability of the daily scheduling tasks of the database platform.

[0071] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of an embodiment of the data processing device provided in this application. The data processing device 30 includes a memory 31 and a processor 32 connected to each other. The memory 31 is used to store computer programs. When the computer programs are executed by the processor 32, they are used to implement the image data processing method in the above embodiment. The data processing device 30 can be a database platform, such as a server.

[0072] Please see Figure 4 , Figure 4 This is a schematic diagram of an embodiment of the computer-readable storage medium provided in this application. The computer-readable storage medium 40 is used to store a computer program 41. When the computer program 41 is executed by a processor, it is used to implement the image data processing method in the above embodiment.

[0073] The computer-readable storage medium 40 can be any medium capable of storing program code, such as a server, USB flash drive, portable hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0074] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0075] The units described as separate components may or may not be physically separate. 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 the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0076] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0077] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for processing facial image data, characterized in that, include: Acquire portrait cluster data, which includes multiple portrait data of different individuals; The portrait data is grouped to obtain multiple first portrait datasets. The portrait data in the first portrait datasets meet a first preset condition. The first preset condition includes that the camera devices corresponding to the portrait data are the same and the identifiers of the people are the same. The first portrait dataset is sorted to obtain the second portrait dataset; Based on the type of task to be processed, the portrait data in the second portrait dataset is cleaned to obtain the third portrait dataset; When multiple third-person portrait datasets corresponding to the same target person meet the second preset condition, early warning information related to the task to be processed is generated; The step of cleaning the portrait data in the second portrait dataset based on the type of task to be processed to obtain the third portrait dataset includes: When the type of the task to be processed is a first preset type, a first preset number of portrait data are selected from the second portrait dataset to form the third portrait dataset; When the type of the task to be processed is the second preset type, a second preset number of portrait data are selected from the second portrait dataset to form the third portrait dataset, wherein the first preset number is less than the second preset number.

2. The method for processing facial data according to claim 1, characterized in that, The step of grouping the portrait data to obtain multiple sets of first portrait datasets includes: Select one image data from the image data in the image archive data as the current image data; Determine whether the identifier of the current portrait data is the same as the identifier of the remaining portrait data in the portrait aggregation data; If so, the portrait archive data is grouped based on the camera device corresponding to the portrait data; If not, it is determined that the current portrait data and the remaining portrait data do not meet the first preset condition, and the current portrait data and the remaining portrait data are placed into different first portrait datasets.

3. The method for processing facial data according to claim 2, characterized in that, The step of grouping the facial image data based on the camera device corresponding to the facial image data includes: Determine whether the camera device corresponding to the current portrait data is the same as the camera device corresponding to the remaining portrait data; If so, then the current portrait data and the remaining portrait data are determined to meet the first preset condition, and the current portrait data and the remaining portrait data are placed into the same first portrait dataset.

4. The method for processing facial data according to claim 2, characterized in that, The first preset condition further includes the step of grouping the portrait data based on the camera device corresponding to the portrait data within a first preset time period, wherein the capture time of each portrait data in the first portrait dataset falls within a first preset time period. Determine whether the camera device corresponding to the current portrait data is the same as the camera device corresponding to the remaining portrait data; If the camera device corresponding to the current portrait data is the same as the camera device corresponding to the remaining portrait data, then it is determined whether the first capture time and the second capture time fall within the first preset time period. The first capture time is the capture time of the current portrait data, and the second capture time is the capture time of the remaining portrait data. If the first capture time and the second capture time fall within the first preset time period, then it is determined that the current portrait data and the remaining portrait data meet the first preset condition, and the current portrait data and the remaining portrait data are placed in the same first portrait data set; If the difference between the first capture time and the second capture time does not fall within the first preset time period, it is determined that the current portrait data and the remaining portrait data do not meet the first preset condition, and the current portrait data and the remaining portrait data are placed into different first portrait datasets. If the camera device corresponding to the current portrait data is different from the camera device corresponding to the remaining portrait data, then it is determined that the current portrait data and the remaining portrait data do not meet the first preset condition, and the current portrait data and the remaining portrait data are placed into different first portrait datasets.

5. The method for processing facial image data according to claim 1, characterized in that, The step of sorting the first portrait dataset to obtain the second portrait dataset includes: The second portrait dataset is obtained by sorting all the portrait data in the first portrait dataset according to the order of the capture time from smallest to largest.

6. The method for processing facial image data according to claim 1, characterized in that, The method further includes: The multiple third-party portrait datasets are processed to obtain the processing results; The processing results are processed to generate the landing location; Based on the landing position, determine whether the second preset condition is met; If so, then the warning information is generated.

7. The method for processing facial data according to claim 6, characterized in that, The landing position includes a first landing position and a second landing position, and the method includes: The processing result is generated based on the location configuration data and the multiple third-party portrait datasets; The processing result is processed to generate the first landing position and the second landing position; Determine whether the distance between the first landing position and the second landing position is greater than a preset distance; If so, the second preset condition is determined to be met, and the warning information is generated.

8. The method for processing facial data according to claim 7, characterized in that, The location configuration data includes the location of the camera device corresponding to each portrait data in the portrait aggregation data and the identifier of the camera device corresponding to the location. The step of generating the processing result based on the location configuration data and the multiple third portrait datasets includes: The location of the camera device is obtained by matching the identifier of the camera device corresponding to the third portrait dataset with the location configuration data; The location of the camera device is determined as the landing location; The processing result is generated based on the landing location.

9. The method for processing facial image data according to claim 8, characterized in that, The processing result includes the number of times or days the target person appears at the same location within a second preset time period. The step of generating the processing result based on the location of the person's presence includes: Based on the location of the landing, determine whether the number of times the target person appears in the same location is greater than a preset number, or whether the number of days the target person appears in the same location is greater than a preset number of days; If so, then the location is determined as the landing location.

10. The method for processing facial data according to claim 8, characterized in that, The processing result includes the duration of stay or appearance time of the target person at the same location within a second preset time period. The step of generating the processing result based on the location of the person's stay includes: Determine whether the appearance time of the target person at the same location falls within a third preset time period; If so, the duration of the target person's stay at the location is statistically analyzed to obtain the statistical duration; Determine whether the average value of the statistical duration is greater than a preset duration; If so, then the location is determined as the landing location.

11. A data processing apparatus, characterized in that, The device includes an interconnected memory and a processor, wherein the memory is used to store a computer program, which, when executed by the processor, is used to implement the method for processing portrait data according to any one of claims 1-10.

12. A computer-readable storage medium for storing a computer program, characterized in that, When executed by a processor, the computer program is used to implement the method for processing portrait data according to any one of claims 1-10.

Images