Data archiving method and apparatus

Abstract

Embodiments of the present application provide a data archiving method and device, the method comprising: determining a set of to-be-processed archive events, wherein the set of to-be-processed archive events comprises a plurality of archive events, the plurality of archive events are arranged in a first archiving according to a time sequence, and a matching degree between each archive event in the plurality of archive events and a first archive cover event and / or a second archive cover event is greater than or equal to a preset matching degree; performing secondary archiving on the plurality of archive events to obtain a first target archive event stream and a second target archive event stream, so as to complete archiving of the plurality of archive events, wherein the first target archive event stream is a set of archive events corresponding to a first person, and the second target archive event stream is a set of archive events corresponding to a second person. In this way, the secondary archiving of the plurality of archive events is performed to complete the archiving of the archive events, which is conducive to improving the archiving accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer vision, and in particular to a data archiving method and device. BACKGROUND

[0002] The archive archiving technology is one of the core technologies of AI vision intelligence. By archiving a large number of snapshot pictures to specific real-name personnel archives, a specific personnel archive event stream can be obtained, and relevant staff can perform case business investigation based on the event stream. Current archiving technologies mostly perform face archiving based on face feature comparison methods or combine with human event archiving, but for highly similar faces (for example, twins), there are great challenges for traditional archive archiving. In such a case, the probability of mutual misfiling of two highly similar personnel archive events is very high. SUMMARY

[0003] The embodiments of the present application provide a data archiving method and device, which are beneficial to improve the archiving accuracy.

[0004] The first aspect of the embodiments of the present application provides a data archiving method, comprising:

[0005] determining a set of to-be-processed archive events, wherein the set of to-be-processed archive events includes a plurality of archive events, the plurality of archive events are arranged in a first-time archiving order according to time sequence, and a matching degree between each archive event in the plurality of archive events and a first archive cover event and / or a second archive cover event is greater than or equal to a preset matching degree;

[0006] performing secondary archiving on the plurality of archive events to obtain a first target archive event stream and a second target archive event stream, so as to complete the archiving operation on the plurality of archive events, wherein the first target archive event stream is a set of archive events corresponding to a first person, and the second target archive event stream is a set of archive events corresponding to a second person.

[0007] The second aspect of the embodiments of the present application provides a data archiving device, comprising:

[0008] a determining unit configured to determine a set of to-be-processed archive events, wherein the set of to-be-processed archive events includes a plurality of archive events, the plurality of archive events are arranged in a first-time archiving order according to time sequence, and a matching degree between each archive event in the plurality of archive events and a first archive cover event and / or a second archive cover event is greater than or equal to a preset matching degree;

[0009] A secondary archiving unit is configured to perform secondary archiving on the plurality of archive events to obtain a first target archive event stream and a second target archive event stream, so as to complete the archiving operation on the plurality of archive events, wherein the first target archive event stream is a set of archive events corresponding to a first person, and the second target archive event stream is a set of archive events corresponding to a second person.

[0010] In a third aspect, an electronic device includes: a processor and a memory; and one or more programs stored in the memory and configured to be executed by the processor, the programs including instructions for some or all of the steps described in the first aspect.

[0011] In a fourth aspect, a computer-readable storage medium is provided, where the computer-readable storage medium is configured to store a computer program, where the computer program causes a computer to perform some or all of the steps described in the first aspect of the embodiments of the present application.

[0012] In a fifth aspect, a computer program product is provided, where the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product can be a software installation package.

[0013] The embodiments of the present application have the following beneficial effects:

[0014] It can be seen that, by the embodiments of the present application, a set of archive events to be processed is determined, where the set of archive events to be processed includes a plurality of archive events, the plurality of archive events are arranged in a chronological order according to a first time and a second time, and a matching degree between each archive event in the plurality of archive events and a first archive cover event and / or a second archive cover event is greater than or equal to a preset matching degree; the plurality of archive events are subjected to secondary archiving to obtain a first target archive event stream and a second target archive event stream, so as to complete the archiving operation on the plurality of archive events, where the first target archive event stream is a set of archive events corresponding to a first person, and the second target archive event stream is a set of archive events corresponding to a second person. In this way, the plurality of archive events are subjected to secondary archiving to complete the archiving operation on the archive events, which is conducive to reducing the probability of archiving errors, improving the archiving accuracy, and improving the accuracy when restoring the real archive later. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiments description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those of ordinary skill in the art without any creative effort based on these drawings.

[0016] Figure 1A is a system architecture schematic diagram of a data archiving method provided by an embodiment of the present application;

[0017] Figure 1B is an embodiment flow schematic diagram of a data archiving method provided by an embodiment of the present application;

[0018] Figure 2 is an embodiment flow schematic diagram of a data archiving method provided by an embodiment of the present application;

[0019] Figure 3 is a structure schematic diagram of a data archiving device provided by an embodiment of the present application;

[0020] Figure 4 is an embodiment structure schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without any creative effort belong to the scope of protection of the present application.

[0022] The terms "first", "second", "third", and "fourth" and the like in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a particular order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include other steps or units not listed or can optionally include other steps or units inherent to the process, method, product or device.

[0023] Reference to an "embodiment" in this document means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. As will be apparent to those of ordinary skill in the art, embodiments described herein can be combined with other embodiments.

[0024] For better understanding of the data archiving method, related device and electronic equipment provided by the embodiments of the present application, the system architecture of the data archiving method applicable to the embodiments of the present application is described first. Referring to Figure 1A , Figure 1A is a system architecture diagram of the data archiving method provided by the embodiments of the present application. As Figure 1A indicated, the system architecture can include one or more servers and a plurality of electronic devices, wherein:

[0025] The server can include, but is not limited to, a background server, a component server, a data archiving system server, or a data archiving software server, etc. The server can communicate with the plurality of electronic devices through the Internet to complete the data archiving operation, and can also send the data archiving result (for example, the first target archiving event stream and the second target archiving event stream in the embodiments of the present application) to the electronic device. Of course, in the present application, the electronic device can also complete the data archiving operation and send it to the server for data synchronization or storage.

[0026] The electronic device described in the embodiments of the present application can include a camera, a smart phone (such as an Android phone, an iOS phone, a Windows Phone phone, etc.), a tablet computer, a palm computer, a notebook computer, a mobile Internet device (MID, Mobile Internet Devices) or a wearable device, etc. The above are only examples and are not exhaustive, including but not limited to the above devices. Of course, the above electronic device can also be a server.

[0027] The related technical terms of the present application are described below:

[0028] 1) Real-name file: Each personnel has a unique ID, and each ID is associated with a real-name file for describing the basic information of the personnel

[0029] 2) Face feature value (feature): Each face snapshot picture has a unique feature value, which is used to store the basic features of the face in the picture. The feature value comparison value similarity of different face data of the same personnel is theoretically higher.

[0030] 3) Archiving: the process of analyzing all snapshot events under the name of a specific personnel file.

[0031] In the present application, the electronic device can determine a set of to-be-processed archival events, wherein the set of to-be-processed archival events includes a plurality of archival events, the plurality of archival events are arranged in chronological order in a first archival arrangement, and the matching degree between each of the plurality of archival events and the first archival cover event and / or the second archival cover event is greater than or equal to a preset matching degree; the plurality of archival events are subjected to a second archival arrangement to obtain a first target archival event stream and a second target archival event stream, so as to complete the archival operation on the plurality of archival events, wherein the first target archival event stream is a set of archival events corresponding to the first person, and the second target archival event stream is a set of archival events corresponding to the second person; the first external archival event information and the second external archival event information are obtained; the first target archival event stream and the second target archival event stream are respectively coupled and compared with the first external archival event and the second external archival event to obtain a plurality of coupling degrees; the first archival event or the to-be-analyzed event corresponding to the highest coupling degree is selected as a target archival event, the archival data corresponding to the target archival event is obtained, and the archival data is subjected to an archival processing.

[0032] It should be noted that in the present application, a plurality of can refer to two or more than two, and the subsequent description will not be repeated. The system architecture of the data archival method provided in the present application is not limited to Figure 1A as shown.

[0033] Please refer to Figure 1B , a flowchart of an embodiment of a data archival method provided by an embodiment of the present application. The data archival method described in the present embodiment includes the following steps:

[0034] 101, determining a set of to-be-processed archival events, wherein the set of archival events includes a plurality of archival events, the archival events are arranged in chronological order in a first archival arrangement, and the matching degree between each of the plurality of archival events and the first archival cover event and / or the second archival cover event is greater than or equal to a preset matching degree.

[0035] Each of the above-mentioned archival events can correspond to archival data, which can include an archival cover image, an identity authentication identifier, etc., wherein the archival cover image can be a face image, a body image, etc. of a user corresponding to the archival data, which is not limited here.

[0036] Each of the archival events can correspond to a real-name archival file. The electronic device can arrange the above-mentioned plurality of archival events in chronological order in the first archival arrangement.

[0037] In the electronic device, the first archival cover event and the second archival cover event can be preset, and the first archival cover event is different from the second archival cover event.

[0038] The first profile cover event and the second profile cover event can constitute the same profile library, and the data corresponding to the first profile cover event and the data corresponding to the second profile cover event are highly similar user profile data, for example, the first profile cover event can correspond to an elder sister in a pair of twins, and the second profile cover event can correspond to a younger sister in the pair of twins. The first profile cover event and / or the second profile cover event can be a face image, a body image, or the like.

[0039] In a possible example, the determining of the set of profile events to be processed includes the following steps:

[0040] A1, acquiring a set of snapshot events, the set of snapshot events including a plurality of snapshot events;

[0041] A2, performing face feature value matching on each of the snapshot events in the plurality of snapshot events with the first profile cover event and the second profile cover event respectively to obtain a plurality of matching degrees;

[0042] A3, according to the plurality of matching degrees, archiving the plurality of snapshot events into a set corresponding to the first profile cover event and a set corresponding to the second profile cover event to obtain a first event stream and a second event stream, wherein a matching degree corresponding to any profile event in the first event stream and / or the second event stream is greater than the preset matching degree;

[0043] A4, determining the set of profile events according to the first event stream after archiving and the second preset stream after archiving.

[0044] The set of snapshot events can include a plurality of snapshot events, and each snapshot event can correspond to snapshot data, which can include at least one of the following: face feature value feature, snapshot time, location (latitude and longitude, GPS information, etc.), body attribute (upper body color, lower body color, clothing style, etc.), and the like, which are not limited herein.

[0045] Specifically, the face feature value corresponding to each snapshot event can be matched with the face feature value corresponding to the first profile cover event to obtain a plurality of first matching degrees; the face feature value corresponding to each snapshot event can be matched with the face feature value corresponding to the second profile cover event to obtain a plurality of second matching degrees; the snapshot events corresponding to the first matching degrees greater than or equal to a preset matching degree (which can be set by a user or by default by a system, and is not limited herein, and the preset matching degree can be set to a high similarity threshold value such as 0.89, 0.92, 0.95, etc.) are selected and divided into a set corresponding to the first profile cover event to obtain a first event stream after archiving, and the archived events in the first event stream can be sorted in chronological order.

[0046] Further, the snapshot events corresponding to the second matching degrees greater than or equal to the preset matching degree can be selected from the plurality of second matching degrees and divided into the set corresponding to the second archive cover event, to obtain the second event stream after archiving. The archived events in the second event stream can be sorted in chronological order. Finally, the first event stream and the second event stream can be merged to obtain the archive event set. In this way, the plurality of snapshot events can be first archived by the face feature value matching manner, so as to archive the snapshot events corresponding to the image data with high similarity in the same event stream (for example, the first event stream or the second event stream).

[0047] In a possible example, the determining the archive event set according to the first event stream after archiving and the second event stream after archiving includes the following steps:

[0048] B1, mixing all the archive events in the first event stream after archiving and the second event stream after archiving to obtain a third event stream;

[0049] B2, arranging the archive events in the third event stream in chronological order to obtain the archive event set.

[0050] Since the face data corresponding to the first archive cover event and the second archive cover event are highly similar, when the plurality of snapshot events are first archived, the archiving operation is completed only by the face feature value matching. If the first archive cover event and the second archive cover event correspond to the face data of a pair of twins, the archiving error probability is very high, and subsequent trajectory analysis based on the archiving result after archiving will have a large error. Therefore, all the archived events in the first event stream and the second event stream can be mixed and arranged in chronological order to obtain the archive event set, so as to realize secondary archiving, which is beneficial to reducing the archiving error probability of the archive event.

[0051] 102, performing secondary archiving on the plurality of archive events to obtain a first target archive event stream and a second target archive event stream, to complete the archiving operation on the plurality of archive events, wherein the first target archive event stream is an archive event set corresponding to a first person, and the second target archive event stream is an archive event set corresponding to a second person.

[0052] The plurality of archive events are determined only by the face feature value matching manner. If the face data corresponding to the first preset event and the second preset event are highly similar, there may be an archiving error. Therefore, in order to improve the archiving accuracy, the secondary archiving analysis operation can be further performed according to the archive event set, to prevent the archive event stream of the person with highly similar face from being incorrectly archived.

[0053] The first person and the second person mentioned above are not the same person, and the first person and the second person can be people with highly similar facial features.

[0054] In one possible example, the secondary archiving of the multiple archive events to obtain a first target archive event stream and a second target archive event stream includes the following steps:

[0055] 21. Based on the chronological order, select the archive event that appears first from the multiple archive events as the analysis event, and select the next archive event after the analysis event as the event to be analyzed;

[0056] 22. Using the analyzed event as the starting point of the first target archived event stream corresponding to the first person, analyze whether the event to be analyzed and the analyzed event are archived events of the same person;

[0057] 23. If it is determined that the analyzed event and the event to be analyzed are file events of the same person, then the event to be analyzed is archived in the first target archived event stream, and the event to be analyzed is arranged after the analyzed event;

[0058] 24. If it is determined that the event to be analyzed and the event to be analyzed are not archive events of the same person, then the event to be analyzed is archived into the second target archive event stream corresponding to the second person, and the event to be analyzed is used as the starting event of the second target archive event stream corresponding to the second person.

[0059] The aforementioned events to be analyzed can refer to archive events that have not yet undergone secondary archiving, while the aforementioned events to be analyzed can refer to archive events that have already undergone secondary archiving. The aforementioned events to be analyzed can be used to analyze the events to be analyzed.

[0060] This involves using multiple archive events as analysis objects and analyzing them in chronological order. In practice, these multiple archive events are arranged in chronological order, and the first archive event is identified as the analysis event. This analysis event can then be used as either one of the two target archive event streams (the first target archive event stream and the second target archive event stream). For example, the analysis event can be used as the starting point or the starting event in the first target archive event stream.

[0061] Further, the next archive event of the analysis event, i.e. the most front archive event in the plurality of archive events, can be taken as the to-be-analyzed event corresponding to the analysis event, and then the personnel corresponding to the first target archive event stream can be defined as the first personnel, and similarly, the personnel corresponding to the second target archive event stream can be defined as the second personnel; then, the analysis event can be determined as the starting point of the first target archive event stream corresponding to the first personnel, i.e. the archive event set, and whether the to-be-analyzed event and the analysis event are archive events corresponding to the same personnel is analyzed.

[0062] Further, if it is determined that the to-be-analyzed event and the analysis event are not archive events of the same personnel, the to-be-analyzed event can be determined as the starting event of the second target archive event stream of the second personnel. In the case where there is only the archive event stream of the first personnel, i.e. the to-be-analyzed event and the analysis event are archive events of the same personnel, the to-be-analyzed event is archived into the first target archive event stream, and the to-be-analyzed event is arranged behind the analysis event.

[0063] It can be seen that in the example, the electronic device can take the plurality of archive events to be second-archived as analysis objects, and select the to-be-analyzed event and the analysis event according to the arrangement order of the plurality of archive events, and compare whether the two events are archive events of the same personnel to complete the first round of circulation or the processing of the first second-archiving process to determine the archive events corresponding to the first personnel and / or the second personnel; finally, the last archive event arranged in the first target archive event stream or the second target archive event stream can be taken as the starting point of the next second-archiving, which is beneficial to help subsequent successful and correct archiving of each archive event into the corresponding target archive event stream, and is beneficial to improve the second-archiving accuracy.

[0064] Optionally, after step 23, i.e. after arranging the to-be-analyzed event behind the analysis event, the method further includes the following steps:

[0065] C1, taking the most front archive event in the plurality of archive events as the to-be-analyzed event of the next second-archiving, and taking the most rear archive event in the first target archive event stream as the analysis event of the next second-archiving;

[0066] C2, analyzing whether the analysis event and the to-be-analyzed event are the same archive event in the next second-archiving;

[0067] C3, if it is determined that the analysis event and the to-be-analyzed event are not archive events of the same personnel, the to-be-analyzed event is archived into the second target archive event stream corresponding to the second personnel.

[0068] Wherein, after step 22, if it is determined that the to-be-analyzed event in steps 21-24 is the same as the analyzed event, only the next to-be-analyzed event (the next one in the multiple archive events that are not secondarily archived, i.e., the archive event that is currently arranged at the top) needs to be compared with the archive event arranged at the last in the first target archive event stream of the first person (for example, it can be the to-be-analyzed event in steps 21-24), to determine whether to continue to archive the archive event currently arranged at the top into the first target archive event stream of the first person, and if it is determined that the archive event currently arranged at the top (the to-be-analyzed event) is the same as the archive event arranged at the last in the first target archive event stream (the analyzed event), the to-be-analyzed event can be archived into the first target archive event stream; otherwise, the to-be-analyzed event can be directly archived into the second target archive event stream corresponding to the second person.

[0069] Optionally, after step 24 or C3, after archiving the to-be-analyzed event into the second target archive event stream corresponding to the second person; the method further comprises the following steps:

[0070] D1, determining the next archive event of the to-be-analyzed event as a to-be-analyzed archive in the next secondary archiving process;

[0071] D2, taking the archive event arranged at the last in the first target archive event as a first analyzed event, and taking the archive event arranged at the last in the second target archive event as a second analyzed event;

[0072] D3, comparing the to-be-analyzed archive with the first analyzed event and the second analyzed event respectively, to archive the to-be-analyzed archive into the first target archive event stream or the second target archive event stream.

[0073] Wherein, after step 22, if it is determined that the to-be-analyzed event in steps 21-24 is not the same as the analyzed event, i.e., in the case that the first target archive event stream and the second target archive event stream corresponding to the first person and the second person respectively exist, the next to-be-analyzed event needs to be compared with the archive event arranged at the last in the archive event stream of the first person and the second person, i.e., the first analyzed event and the second analyzed event, and then classified, until all archive events in the archive event set are classified.

[0074] It can be seen that in the example, the top-ranked archive event in the plurality of archive events that are not secondarily archived can be always taken as the event to be analyzed, compared and analyzed with the starting event or the last-ranked archive event in the first target archive event stream and / or the second target archive event stream, so as to secondarily archive the top-ranked archive event, which is conducive to archiving the archive event into the correct target archive event stream and improving the archiving accuracy.

[0075] In one possible example, the step 22 of analyzing whether the event to be analyzed and the analysis event are archive events of the same person includes the following steps:

[0076] 221. Determine a first time difference value and a first distance difference value between the analysis event and the event to be analyzed, and calculate a spatiotemporal coupling degree between the analysis event and the event to be analyzed according to the first time difference value and the first distance difference value;

[0077] 222. Determine a second time difference value and a second distance difference value between the analysis event and the event to be analyzed, and calculate a body attribute change possibility value between the analysis event and the event to be analyzed according to the second time difference value and the second distance difference value;

[0078] 223. If the spatiotemporal coupling degree is less than a preset threshold value or the body attribute change possibility value is less than the preset threshold value, it is determined that the analysis event and the event to be analyzed are not archive events of the same person;

[0079] 224. If the spatiotemporal coupling degree is greater than or equal to a preset threshold value and the body attribute change possibility value is greater than or equal to the preset threshold value, it is determined that the analysis event and the event to be analyzed are archive events of the same person.

[0080] In specific implementations, the preset first calculation formula and / or the preset second calculation formula can be set by a user or by default of a system, which is not limited herein. The analysis event and the event to be analyzed can be scored by the first calculation formula and the second calculation formula to obtain the spatiotemporal coupling degree and the body attribute change possibility value.

[0081] Specifically, the analysis event and the event to be analyzed can be scored in two dimensions (spatiotemporal coupling degree dimension and human body attribute change value dimension), and the spatiotemporal coupling degree or the human body attribute change value obtained by scoring in each dimension ranges from 0 to 100. The first calculation formula can be set as o1=k1 / (t1*d1), where k1 is a configurable coefficient, t1 is a time difference value (unit: s) corresponding to two events, and d1 is a distance difference value (unit: m) corresponding to two events. It can be known from the first calculation formula that the spatiotemporal coupling degree is inversely proportional to the distance difference value and the time difference value of two events. The lower the score, the lower the probability that the two events belong to the same personnel's file event; the higher the score, the higher the probability that the two events belong to the same personnel's file event. Further, the spatiotemporal coupling degree corresponding to the analysis event and the event to be analyzed can be determined according to the first calculation formula, the first time difference value and the distance difference value.

[0082] Further, the second calculation formula can be set as o2=(k2*t2) / d2, where d2 is a second distance difference value, k2 is a configurable coefficient, and the k2 value corresponding to different types of human body attribute changes is different and can be set according to the actual scene. For example, since it is easier to change a top than a bottom, the k2 value corresponding to the bottom color and style change scene can be set to be higher than the k2 value corresponding to the top color and style change scene. Wherein o2 is proportional to the second time difference value and inversely proportional to the second distance difference value. Further, the human body attribute change value corresponding to the analysis event and the event to be analyzed can be determined according to the second calculation formula, the second time difference value and the second distance difference value.

[0083] It should be noted that if there is no change in the human body attribute, o2 is the highest score of 100.

[0084] Further, the above-mentioned preset threshold value can be set by the user or by the system by default, which is not limited herein. The preset threshold value can refer to the standard value of the analysis event and the event to be analyzed being the same file under the above two dimensions; for example, the preset threshold value can be set to 60.

[0085] Further, if the spatiotemporal coupling degree is less than the preset threshold value, or the human body attribute change value is less than the preset threshold value, it is determined that the analysis event and the event to be analyzed are not the file events corresponding to the same personnel; if the spatiotemporal coupling degree is greater than or equal to the preset threshold value, and the human body attribute change value is greater than or equal to the preset threshold value, it is determined that the analysis event and the event to be analyzed are the file events corresponding to the same personnel.

[0086] It can be seen that, in the present example, the spatiotemporal coupling degree and the body attribute change possibility value can be calculated by two dimensions, and the two archive events are calculated under different dimensions; and whether the two archive events are corresponding archive events of the same person is evaluated by combining the spatiotemporal coupling degree and the body attribute change possibility value, so as to determine whether the two archive events are corresponding archive events of the same person, which is beneficial to improve the archiving accuracy.

[0087] Optionally, in step D3, comparing the to-be-archived archive with the first analysis event and the second analysis event respectively to archive the to-be-archived archive into the first target archive event stream or the second target archive event stream can include the following steps: the first spatiotemporal coupling degree and the first body attribute change possibility value between the to-be-archived event and the first analysis event, and the second spatiotemporal coupling degree and the second body attribute change possibility value between the to-be-archived event and the second analysis event can be calculated by the first calculation formula and the second calculation formula in steps 221-224; and then, the first spatiotemporal coupling degree, the first body attribute change possibility value, the second spatiotemporal coupling degree and the second body attribute change possibility value can be compared.

[0088] Further, if any one of the calculation values between the first spatiotemporal coupling degree and the second spatiotemporal coupling degree is less than or equal to the preset threshold value, and the first body attribute change possibility value is greater than the preset threshold value and the second body attribute change possibility value is greater than the preset threshold value, it is determined that the to-be-archived event and the second analysis event are archive events of the same person, and the to-be-archived event can be archived into the second target archive event stream.

[0089] If any one of the calculation values between the first body attribute change possibility value and the second body attribute change possibility value is less than or equal to the preset threshold value, and the first spatiotemporal coupling degree is greater than the preset threshold value and the second spatiotemporal coupling degree is greater than the preset threshold value, it is determined that the to-be-archived event and the first analysis event are archive events of the same person, and the to-be-archived event can be archived into the first target archive event stream.

[0090] If the first spatiotemporal coupling degree, the second spatiotemporal coupling degree, the first body attribute change possibility value and the second body attribute change possibility value are all greater than the preset threshold value, or the first spatiotemporal coupling degree, the second spatiotemporal coupling degree, the first body attribute change possibility value and the second body attribute change possibility value are all less than or equal to the preset threshold value, the sum of the first spatiotemporal coupling degree and the second spatiotemporal coupling degree is calculated to obtain a first result, and the sum of the first body attribute change possibility value and the second body attribute change possibility value is calculated to obtain a second result.

[0091] If the first result is greater than the second result, it is determined that the to-be-archived event and the first analysis event are archive events of the same person, and the to-be-archived event can be archived into the first target archive event stream.

[0092] If the first result is less than the second result, it is determined that the event to be analyzed and the second analysis event are profile events of the same person, and the event to be analyzed can be archived into the second target archive event stream.

[0093] Optionally, after obtaining the first target archive event stream and the second target archive event stream, the following steps can be further included:

[0094] E1, obtaining first external profile event information and second external profile event information;

[0095] E2, performing the first external profile event information and the second external profile event information on the first target archive event stream and / or the second target archive event stream to obtain a plurality of coupling degrees;

[0096] E3, obtaining an archive event corresponding to the highest coupling degree in the plurality of coupling degrees; that is, determining the target external profile event information (first external profile event information or second external profile event information) corresponding to the archive event.

[0097] After the secondary archiving of all the plurality of profile events, the first target archive event stream and the second target archive event stream can be output; but it cannot be determined which specific real-name profile corresponds to which target archive event stream, and it is necessary to couple and compare with the third-party externally provided two target archive events (imsi code information or identity card swiping information, etc.) to compare the event with the highest coupling degree of the archive event stream, and then determine the profile identity information to which the archive event belongs; the more target archive events provided by the third party, the higher the probability of the correct profile corresponding to the target external profile event information and the archive event obtained by analysis.

[0098] For example, as shown in Figure 2 Fig. 1 is a flowchart of a data archiving method, as shown in the figure, module 1 can be used to execute the method shown in A1-A4 of the present application, module 2 can be used to execute the method shown in B1-B2 of the present application, module 3 can be used to execute the method shown in steps 21-24 of the present application and related methods; module 4 can be used to execute the method shown in steps E1-E3 of the present application.

[0099] It can be seen that, by the embodiment of the present application, a to-be-processed archive event set is determined, wherein the to-be-processed archive event set includes a plurality of archive events, the plurality of archive events are arranged in chronological order for first archiving, and a matching degree between each of the plurality of archive events and the first archive cover event and / or the second archive cover event is greater than or equal to a preset matching degree; the plurality of archive events are secondarily archived to obtain a first target archive event stream and a second target archive event stream to complete the archiving operation on the plurality of archive events, wherein the first target archive event stream is an archive event set corresponding to a first person, and the second target archive event stream is an archive event set corresponding to a second person. In this way, the archiving operation on the archive events can be completed by secondarily archiving the plurality of archive events, which is beneficial to reducing the probability of archiving error of the archive events, improving the archiving accuracy, and improving the accuracy when restoring the real archives subsequently.

[0100] Consistent with the above, the following is a device for implementing the above data archiving method, specifically as follows:

[0101] Please refer to Figure 3 , an embodiment structure schematic diagram of a data archiving device provided by the embodiment of the present application. The data archiving device described in the embodiment includes a determination unit 301 and a secondary archiving unit 302, specifically as follows:

[0102] The determination unit 301 is configured to determine a to-be-processed archive event set, wherein the to-be-processed archive event set includes a plurality of archive events, the plurality of archive events are arranged in chronological order for first archiving, and a matching degree between each of the plurality of archive events and the first archive cover event and / or the second archive cover event is greater than or equal to a preset matching degree;

[0103] The secondary archiving unit 302 is configured to secondarily archive the plurality of archive events to obtain a first target archive event stream and a second target archive event stream to complete the archiving operation on the plurality of archive events, wherein the first target archive event stream is an archive event set corresponding to a first person, and the second target archive event stream is an archive event set corresponding to a second person.

[0104] In one possible example, the to-be-processed archive event set is determined; the determination unit 301 is specifically configured to:

[0105] Obtain a snapshot event set, wherein the snapshot event set includes a plurality of snapshot events;

[0106] Match a face feature value of each of the plurality of snapshot events with the first archive cover event and the second archive cover event respectively to obtain a plurality of matching degrees;

[0107] According to the plurality of matching degrees, the plurality of snapshot events are respectively archived into the first archive cover event corresponding set and the second archive cover event corresponding set, to obtain a first event stream and a second event stream, wherein the matching degree corresponding to any archive event in the first event stream and / or the second event stream is greater than the preset matching degree;

[0108] According to the first event stream after archiving and the second event stream after archiving, the archive event set is determined

[0109] In one possible example, in terms of determining the archive event set according to the first event stream after archiving and the second event stream after archiving, the determination unit 301 is specifically configured to:

[0110] Mix all archive events in the first event stream after archiving and the second event stream after archiving to obtain a third event stream;

[0111] Arrange the archive events in the third event stream in chronological order to obtain the archive event set.

[0112] In one possible example, in terms of performing secondary archiving on the plurality of archive events to obtain a first target archive event stream and a second target archive event stream, the secondary archiving unit 302 is specifically configured to:

[0113] According to the chronological order, arrange the archive events in chronological order to obtain the archive event set.

[0114] Take the analysis event as the starting point of the first target archive event stream corresponding to the first person, and analyze whether the to-be-analyzed event and the analysis event are archive events of the same person;

[0115] If it is determined that the analysis event and the to-be-analyzed event are archive events of the same person, the to-be-analyzed event is archived into the first target archive event stream, and the to-be-analyzed event is arranged behind the analysis event;

[0116] If it is determined that the analysis event and the to-be-analyzed event are not archive events of the same person, the to-be-analyzed event is archived into the second target archive event stream corresponding to the second person, and the to-be-analyzed event is taken as the starting event of the second target archive event stream corresponding to the second person.

[0117] In a possible example, after the arranging the event to be analyzed behind the event analyzed, the secondary archiving unit 302 is further configured to:

[0118] arrange a currently first-arranged event in the plurality of archive events as an event to be analyzed in a next secondary archiving, and arrange a last-arranged event in the first target archive event stream as an event analyzed in the next secondary archiving;

[0119] analyze whether the event analyzed and the event to be analyzed are archive events of a same person in the next secondary archiving;

[0120] if it is determined that the event analyzed and the event to be analyzed are archive events of the same person, archive the event to be analyzed into the first target archive event stream, and arrange the event to be analyzed behind the archive event of the event analyzed;

[0121] if it is determined that the event analyzed and the event to be analyzed are not archive events of the same person, archive the event to be analyzed into the second target archive event stream corresponding to the second person.

[0122] In a possible example, after the archiving the event to be analyzed into the second target archive event stream corresponding to the second person, the secondary archiving unit 302 is further configured to:

[0123] determine a next archive event of the event to be analyzed as an event to be analyzed in a next secondary archiving process;

[0124] arrange a last-arranged archive event in the first target archive event stream as a first event analyzed, and arrange a last-arranged archive event in the second target archive event stream as a second event analyzed;

[0125] compare the event to be analyzed with the first event analyzed and the second event analyzed respectively, to archive the event to be analyzed into the first target archive event stream or the second target archive event stream.

[0126] In a possible example, in the analyzing whether the event to be analyzed and the event analyzed are archive events of a same person, the secondary archiving unit 302 is further configured to:

[0127] determine a first time difference and a first distance difference between the event analyzed and the event to be analyzed, and calculate a spatiotemporal coupling degree between the event analyzed and the event to be analyzed according to the first time difference and the first distance difference;

[0128] determine a second time difference value and a second distance difference value between the analysis event and the event to be analyzed, and calculate a human attribute change possible value between the analysis event and the event to be analyzed according to the second time difference value and the second distance difference value;

[0129] If the spatiotemporal coupling degree is less than a preset threshold value, or the human attribute change possible value is less than the preset threshold value, it is determined that the analysis event and the event to be analyzed are not archive events of the same person.

[0130] If the spatiotemporal coupling degree is greater than or equal to a preset threshold value, and the human attribute change possible value is greater than or equal to the preset threshold value, it is determined that the analysis event and the event to be analyzed are archive events of the same person.

[0131] It can be seen that the data archiving device described in the embodiment of the present application determines a set of archive events to be processed, wherein the set of archive events to be processed includes a plurality of archive events, the plurality of archive events are arranged in chronological order for the first time, and the matching degree between each of the plurality of archive events and the first archive cover event and / or the second archive cover event is greater than or equal to a preset matching degree; the plurality of archive events are subjected to secondary archiving to obtain a first target archive event stream and a second target archive event stream, so as to complete the archiving operation of the plurality of archive events, wherein the first target archive event stream is a set of archive events corresponding to a first person, and the second target archive event stream is a set of archive events corresponding to a second person. In this way, the secondary archiving of the plurality of archive events is performed to complete the archiving operation of the archive events, which is beneficial to reducing the probability of archiving errors of the archive events, improving the archiving accuracy, and improving the accuracy when restoring the real archive in the future.

[0132] Consistent with the above, please refer to Figure 4 An embodiment structure schematic diagram of an electronic device is provided for the embodiment of the present application. The electronic device includes the data archiving system, the camera, or the server described in the embodiment, and includes at least one input device 1000, at least one output device 2000, at least one processor 3000 such as a CPU, and a memory 4000, wherein the above-mentioned input device 1000, output device 2000, processor 3000, and memory 4000 are connected through a bus 5000.

[0133] Specifically, the input device 1000 can be a touch panel, a physical button, or a mouse.

[0134] Specifically, the output device 2000 can be a display screen.

[0135] The memory 4000 can be a high-speed RAM memory, and can also be a non-volatile memory such as a disk memory. The memory 4000 is used to store a set of program codes, and the input device 1000, the output device 2000, and the processor 3000 are used to call the program codes stored in the memory 4000 to perform the following operations:

[0136] The processor 3000 is configured to:

[0137] determine a set of to-be-processed archive events, the set of to-be-processed archive events including a plurality of archive events, the plurality of archive events being arranged in a chronological order according to a first archiving;

[0138] perform a second archiving on the plurality of archive events to obtain a first target archive event stream and a second target archive event stream, so as to complete the archiving operation on the plurality of archive events.

[0139] It can be seen that the electronic device described in the embodiment of the present application determines a set of to-be-processed archive events, the set of to-be-processed archive events including a plurality of archive events, the plurality of archive events being arranged in a chronological order according to a first archiving, and a matching degree between each archive event in the plurality of archive events and a first archive cover event and / or a second archive cover event being greater than or equal to a preset matching degree; a second archiving is performed on the plurality of archive events to obtain a first target archive event stream and a second target archive event stream, so as to complete the archiving operation on the plurality of archive events, the first target archive event stream being a set of archive events corresponding to a first person, and the second target archive event stream being a set of archive events corresponding to a second person. In this way, the second archiving is performed on the plurality of archive events to complete the archiving operation on the archive events, which is beneficial to reducing the probability of archiving errors, improving the archiving accuracy, and improving the accuracy when restoring the real archive later.

[0140] In one possible example, the set of to-be-processed archive events is determined, and the processor 3000 is configured to:

[0141] obtain a set of snapshot events, the set of snapshot events including a plurality of snapshot events;

[0142] perform face feature value matching on each snapshot event in the plurality of snapshot events with the first archive cover event and the second archive cover event respectively to obtain a plurality of matching degrees;

[0143] According to the plurality of matching degrees, the plurality of snapshot events are respectively archived into the first archive cover event corresponding set and the second archive cover event corresponding set, to obtain a first event stream and a second event stream, wherein the matching degree corresponding to any archive event in the first event stream and / or the second event stream is greater than the preset matching degree;

[0144] According to the archived first event stream and the archived second event stream, the archive event set is determined

[0145] In one possible example, in the aspect of determining the archive event set according to the archived first event stream and the archived second event stream, the processor 3000 is configured to:

[0146] Mix all archive events in the archived first event stream and the archived second event stream to obtain a third event stream;

[0147] Arrange the archive events in the third event stream in chronological order to obtain the archive event set.

[0148] In one possible example, in the aspect of performing secondary archiving on the plurality of archive events to obtain a first target archive event stream and a second target archive event stream, the processor 3000 is configured to:

[0149] According to the chronological order, arrange the archive event in the front as an analysis event, and arrange the next archive event of the analysis event as a to-be-analyzed event;

[0150] Take the analysis event as the starting point of the first target archive event stream corresponding to the first person, and analyze whether the to-be-analyzed event and the analysis event are archive events of the same person;

[0151] If it is determined that the analysis event and the to-be-analyzed event are archive events of the same person, the to-be-analyzed event is archived into the first target archive event stream, and the to-be-analyzed event is arranged behind the analysis event;

[0152] If it is determined that the analysis event and the to-be-analyzed event are not archive events of the same person, the to-be-analyzed event is archived into the second target archive event stream corresponding to the second person, and the to-be-analyzed event is taken as the starting point event of the second target archive event stream corresponding to the second person.

[0153] In one possible example, after the to-be-analyzed event is arranged behind the analysis event, the processor 3000 is further configured to:

[0154] ranking the first target archive event stream according to the archive events in the first target archive event stream, and ranking the second target archive event stream according to the archive events in the second target archive event stream;

[0155] analyzing whether the analysis event and the to-be-analyzed event are archive events of the same person in the next secondary archiving;

[0156] if it is determined that the analysis event and the to-be-analyzed event are archive events of the same person, archiving the to-be-analyzed event into the first target archive event stream, and ranking the to-be-analyzed event behind the archive event of the analysis event;

[0157] if it is determined that the analysis event and the to-be-analyzed event are not archive events of the same person, archiving the to-be-analyzed event into the second target archive event stream corresponding to the second person.

[0158] In one possible example, after the to-be-analyzed event is archived into the second target archive event stream corresponding to the second person, the processor 3000 is further configured to:

[0159] determine a next archive event of the to-be-analyzed event as a to-be-analyzed archive in a next secondary archiving process;

[0160] ranking the first target archive event stream according to the archive events in the first target archive event stream, and ranking the second target archive event stream according to the archive events in the second target archive event stream;

[0161] comparing the to-be-analyzed archive with the first analysis event and the second analysis event respectively, to archive the to-be-analyzed archive into the first target archive event stream or the second target archive event stream.

[0162] In one possible example, in the analysis of whether the to-be-analyzed event and the analysis event are archive events of the same person, the processor 3000 is configured to:

[0163] determining a first time difference and a first distance difference between the analysis event and the to-be-analyzed event, and calculating a spatiotemporal coupling degree between the analysis event and the to-be-analyzed event according to the first time difference and the first distance difference;

[0164] determining a second time difference and a second distance difference between the analysis event and the to-be-analyzed event, and calculating a body attribute change probability between the analysis event and the to-be-analyzed event according to the second time difference and the second distance difference.

[0165] If the spatio-temporal coupling degree is less than a preset threshold, or the human body attribute change possible value is less than the preset threshold, it is determined that the analysis event and the event to be analyzed are not archive events of the same person.

[0166] If the spatio-temporal coupling degree is greater than or equal to a preset threshold, and the human body attribute change possible value is greater than or equal to the preset threshold, it is determined that the analysis event and the event to be analyzed are archive events of the same person.

[0167] The embodiment of the present application further provides a computer storage medium, wherein the computer storage medium can store a program, and the program performs part or all steps of any one of the data archiving methods described in the above method embodiments when executed.

[0168] Although the present application is described herein in conjunction with various embodiments, those skilled in the art will appreciate that other changes in the described embodiments can be understood and implemented by those skilled in the art upon viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "one" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. Measures described in mutually different dependent claims can be combined and produce good results.

[0169] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, apparatuses (devices), or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code. The computer program can be stored / distributed in a suitable medium, provided with other hardware, or as part of the hardware, and can also take other distribution forms, such as through the Internet or other wired or wireless telecommunications systems.

[0170] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0171] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks.

[0172] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0173] Although the present application has been described in connection with certain specific features, embodiments, and implementations, it is evident that many alternatives, modifications, and variations will be apparent to those skilled in the art in light of these teachings. Accordingly, the description and drawings are to be regarded as illustrative in nature and not as restrictive. It is intended that the scope of the application be defined by the appended claims and their equivalents. It will be obvious to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the application.

Claims

1. A data archiving method characterized by, The method comprises the following steps: determining a set of to-be-processed archive events, wherein the set of to-be-processed archive events comprises a plurality of archive events, the plurality of archive events are arranged in a time sequence, each of the plurality of archive events has a matching degree with a first archive cover event and / or a second archive cover event greater than or equal to a preset matching degree; performing secondary archiving on the plurality of archive events to obtain a first target archive event stream and a second target archive event stream, so as to complete the archiving operation on the plurality of archive events, wherein the first target archive event stream is a set of archive events corresponding to a first person, and the second target archive event stream is a set of archive events corresponding to a second person; the step of performing secondary archiving on the plurality of archive events to obtain the first target archive event stream and the second target archive event stream comprises the following steps: selecting an archive event arranged at the front in the plurality of archive events as an analysis event and selecting a next archive event of the analysis event as a to-be-analyzed event according to the time sequence; taking the analysis event as a starting point of the first target archive event stream corresponding to the first person, and analyzing whether the to-be-analyzed event and the analysis event are archive events of the same person; if it is determined that the analysis event and the to-be-analyzed event are archive events of the same person, archiving the to-be-analyzed event into the first target archive event stream and arranging the to-be-analyzed event behind the analysis event; if it is determined that the analysis event and the to-be-analyzed event are not archive events of the same person, archiving the to-be-analyzed event into the second target archive event stream corresponding to the second person and taking the to-be-analyzed event as a starting point event of the second target archive event stream corresponding to the second person.

2. The method of claim 1, wherein, The step of determining the set of to-be-processed archive events comprises the following steps: obtaining a set of snapshot events, wherein the set of snapshot events comprises a plurality of snapshot events; performing face feature value matching between each of the plurality of snapshot events and the first archive cover event and the second archive cover event respectively to obtain a plurality of matching degrees; according to the plurality of matching degrees, archiving the plurality of snapshot events into a set corresponding to the first archive cover event and a set corresponding to the second archive cover event respectively to obtain a first event stream and a second event stream, wherein the matching degree of any archive event in the first event stream and / or the second event stream is greater than the preset matching degree; determining the set of archive events according to the first event stream after archiving and the second event stream after archiving.

3. The method of claim 2, wherein, The step of determining the set of archive events according to the first event stream after archiving and the second event stream after archiving comprises the following steps: mixing all archive events in the first event stream after archiving and the second event stream after archiving to obtain a third event stream; arranging archive events in the third event stream in a time sequence to obtain the set of archive events.

4. The method of claim 1, wherein, After the step of arranging the to-be-analyzed event behind the analysis event, the method further comprises the following steps: arranging the first target archive event stream in a first target archive event queue, and arranging the second target archive event stream in a second target archive event queue; arranging a first archive event in the first target archive event stream as a first analysis event, and arranging a second archive event in the second target archive event stream as a second analysis event; arranging the first analysis event and the second analysis event in a first analysis event queue, and arranging the second analysis event in a second analysis event queue; arranging the first analysis event and the second analysis event in a first analysis event queue, and arranging the second analysis event in a second analysis event queue; 5. The method according to claim 1 or 4, characterized in that, arranging the first analysis event and the second analysis event in a first analysis event queue, and arranging the second analysis event in a second analysis event queue; the analysis unit is configured to: determine a first time difference and a first distance difference between the analysis event and the to-be-processed archive event, and calculate a spatiotemporal coupling degree between the analysis event and the to-be-processed archive event according to the first time difference and the first distance difference; determine a second time difference and a second distance difference between the analysis event and the to-be-processed archive event, and calculate a body attribute change possibility between the analysis event and the to-be-processed archive event according to the second time difference and the second distance difference; 6. The method of claim 5, wherein, if the spatiotemporal coupling degree is less than a preset threshold value, or the body attribute change possibility is less than the preset threshold value, it is determined that the analysis event and the to-be-processed archive event are not archive events of the same person; if the spatiotemporal coupling degree is greater than or equal to the preset threshold value, and the body attribute change possibility is greater than or equal to the preset threshold value, it is determined that the analysis event and the to-be-processed archive event are archive events of the same person. the determining unit is configured to: determine a to-be-processed archive event set, wherein the to-be-processed archive event set includes a plurality of archive events, the plurality of archive events are arranged in chronological order according to a first time of archiving, and a matching degree between each archive event in the plurality of archive events and a first archive cover event and / or a second archive cover event is greater than or equal to a preset matching degree; ​ 7. A data archiving apparatus characterized by comprising: ​ ​ A secondary archiving unit is configured to archive the plurality of archive events to obtain a first target archive event stream and a second target archive event stream, so as to complete the archiving operation on the plurality of archive events, wherein the first target archive event stream is a set of archive events corresponding to a first person, and the second target archive event stream is a set of archive events corresponding to a second person; The secondary archiving of the plurality of archive events to obtain the first target archive event stream and the second target archive event stream comprises: According to the time sequence, selecting a most front archive event from the plurality of archive events as an analysis event, and selecting a next archive event of the analysis event as a to-be-analyzed event; Taking the analysis event as a starting point of the first target archive event stream corresponding to the first person, analyzing whether the to-be-analyzed event and the analysis event are archive events of a same person; If it is determined that the analysis event and the to-be-analyzed event are archive events of a same person, archiving the to-be-analyzed event into the first target archive event stream, and arranging the to-be-analyzed event behind the analysis event; If it is determined that the analysis event and the to-be-analyzed event are not archive events of a same person, archiving the to-be-analyzed event into the second target archive event stream corresponding to the second person, and taking the to-be-analyzed event as a starting point event of the second target archive event stream corresponding to the second person.

8. An electronic device, comprising: A computer program product for electronic data interchange, wherein the computer program product causes a computer to perform the method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, A computer program product for electronic data interchange, wherein the computer program product causes a computer to perform the method of any one of claims 1-6.

Images