Video retrieval method and device

Abstract

The embodiment of the present application provides a video retrieval method and device, which relates to the field of video processing technology. The above scheme is: obtain a retrieval time period; if there is a first sub-time period from the first time forward in the retrieval time period, then generate a first video retrieval request for searching the first sub-time period, send the first video retrieval request to the retrieval server, obtain the first retrieval result obtained by the retrieval server in response to the first video retrieval request based on the stored video retrieval information; if there is a second sub-time period after the first time in the retrieval time period, then generate a second video retrieval request for searching the second sub-time period, send the second video retrieval request to the video acquisition device, and obtain the second retrieval result fed back by the video acquisition device for the second video retrieval request. Applying the video retrieval scheme provided by the embodiment of the present application can improve the efficiency of video retrieval.

Description

Technical Field

[0001] The present application relates to the field of video processing technology, and in particular to a video retrieval method and device. Background Art

[0002] Video surveillance systems have been widely used to ensure safe production and public safety. Video surveillance systems are generally equipped with multiple video acquisition devices, which collect videos within their field of view. The videos collected by these video acquisition devices are generally stored in storage servers. Affected by factors such as storage server capacity and minimum storage time, these videos may be stored in multiple storage servers.

[0003] In this way, once it is necessary to retrieve videos that meet certain conditions, it is necessary to search in each storage server separately to find the videos that meet the requirements. Due to the large amount of video data, the video retrieval efficiency is low based on the above method. Summary of the invention

[0004] The purpose of the embodiment of the present application is to provide a video retrieval method and device to improve the efficiency of video retrieval. The specific technical solution is as follows:

[0005] In a first aspect, an embodiment of the present application provides a video retrieval method, which is applied to a client, and the method includes:

[0006] Get the search time period;

[0007] If there is a first sub-time period from the first time forward in the retrieval time period, a first video retrieval request for searching the first sub-time period is generated, the first video retrieval request is sent to the retrieval server, and a first retrieval result obtained by the retrieval server in response to the first video retrieval request based on the stored video retrieval information is obtained, wherein the video retrieval information is obtained by the retrieval server through inspection of the videos collected by the video acquisition device in each inspection cycle, the first time is: a preset time period from the current moment forward or the end time of the latest inspection cycle that the retrieval server has completed inspection, and the preset time period is greater than the time period of the inspection cycle;

[0008] If there is a second sub-time period after the first time in the retrieval time period, a second video retrieval request for searching the second sub-time period is generated, the second video retrieval request is sent to the video acquisition device, and a second retrieval result fed back by the video acquisition device for the second video retrieval request is obtained.

[0009] In a second aspect, an embodiment of the present application provides a video retrieval method, which is applied to a retrieval server, and the method includes:

[0010] In response to the video inspection indication, obtaining video retrieval information of the video captured by the video acquisition device within the inspection period indicated by the video inspection indication, and storing the obtained video retrieval information;

[0011] In response to a first video retrieval request from a client, based on the stored video retrieval information, a video satisfying the first video retrieval request is retrieved to obtain a first retrieval result of the retrieved video, wherein the first video retrieval request is: a first sub-time period in the retrieval time period of the client starting from a first time forward, the first time being: the end time of the latest inspection cycle that has completed the inspection or a preset time period forward from the moment when the client obtains the retrieval time period or the time when the retrieval server last retrieved the video collected by the video acquisition device, and the preset time period is greater than the time period of the inspection cycle;

[0012] The first search result is used as the search result to be sent, and the search result to be sent is sent to the client.

[0013] In a third aspect, an embodiment of the present application provides a video retrieval device, applied to a client, the device comprising:

[0014] A time acquisition module is used to obtain a search time period;

[0015] A first retrieval module is configured to generate a first video retrieval request for searching a first sub-time period if there is a first sub-time period from the first time forward in the retrieval time period, send the first video retrieval request to a retrieval server, and obtain a first retrieval result obtained by the retrieval server in response to the first video retrieval request based on the stored video retrieval information, wherein the video retrieval information is obtained by the retrieval server inspecting the videos collected by the video acquisition device in each inspection cycle, the first time is a preset time period from the current moment forward or an end time of the latest inspection cycle that the retrieval server has completed inspection, and the preset time period is greater than the time period of the inspection cycle;

[0016] The second retrieval module is used to generate a second video retrieval request for searching the second sub-time period if there is a second sub-time period after the first time in the retrieval time period, send the second video retrieval request to the video acquisition device, and obtain a second retrieval result fed back by the video acquisition device for the second video retrieval request.

[0017] In a fourth aspect, an embodiment of the present application provides a video retrieval device, characterized in that it is applied to a retrieval server, and the device includes:

[0018] An indication response module, used to obtain, in response to a video inspection indication, video retrieval information of a video captured by a video acquisition device within an inspection period indicated by the video inspection indication, and store the obtained video retrieval information;

[0019] A request response module, used to respond to a first video retrieval request from a client, retrieve videos satisfying the first video retrieval request based on stored video retrieval information, and obtain a first retrieval result of the retrieved video, wherein the first video retrieval request is: a first sub-time period in the retrieval time period of the client starting from a first time forward, the first time being: the end time of the latest inspection cycle that has completed the inspection or a preset time period forward from the moment when the client obtains the retrieval time period or the time when the retrieval server last retrieved the video collected by the video acquisition device, and the preset time period is greater than the time period of the inspection cycle;

[0020] The result sending module is used to take the first search result as the search result to be sent, and send the search result to be sent to the client.

[0021] In a fifth aspect, an embodiment of the present application provides a client, characterized in that it includes:

[0022] Memory, used to store computer programs;

[0023] The processor is used to implement the method described in the first aspect when executing the program stored in the memory.

[0024] In a sixth aspect, an embodiment of the present application provides a server, characterized in that it includes:

[0025] Memory, used to store computer programs;

[0026] The processor is used to implement the method described in the second aspect when executing the program stored in the memory.

[0027] In a seventh aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect or the second aspect is implemented.

[0028] Beneficial effects of the embodiments of the present application:

[0029] It can be seen from the above that when the solution provided by the embodiment of the present application is used to retrieve videos, the retrieval server stores video retrieval information of the videos captured by the video acquisition device. In this way, when there is a first sub-time period starting from the first time forward in the retrieval time period, the client only needs to send a video retrieval request to the retrieval server to obtain the first retrieval result fed back by the retrieval server, without sending a video retrieval request to each video acquisition device, that is, there is no need to search in each video acquisition device. Therefore, the video retrieval solution provided by the embodiment of the present application can improve the efficiency of video retrieval. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0031] Figure 1 A schematic diagram of interaction between multiple devices provided in an embodiment of the present application;

[0032] Figure 2 A schematic diagram of a flow chart of a first video retrieval method provided in an embodiment of the present application;

[0033] Figure 3 A schematic diagram of a process flow of a periodic retrieval method provided in an embodiment of the present application;

[0034] Figure 4a A schematic diagram of the first result display interface provided in the embodiment of the present application;

[0035] Figure 4b A schematic diagram of a video export interface provided in an embodiment of the present application;

[0036] Figure 4c A schematic diagram of an export format interface provided in an embodiment of the present application;

[0037] Figure 4d A schematic diagram of a search guide interface provided in an embodiment of the present application;

[0038] Figure 4e A schematic diagram of the second result display interface provided in the embodiment of the present application;

[0039] Figure 4f A schematic diagram of the third result display interface provided in the embodiment of the present application;

[0040] Figure 4g A schematic diagram of the fourth result display interface provided in the embodiment of the present application;

[0041] Figure 4h A schematic diagram of the fifth result display interface provided in the embodiment of the present application;

[0042] Figure 4i A schematic diagram of the sixth result display interface provided in the embodiment of the present application;

[0043] Figure 4j A schematic diagram of the seventh result display interface provided in the embodiment of the present application;

[0044] Figure 5 A schematic diagram of a flow chart of a second video retrieval method provided in an embodiment of the present application;

[0045] Figure 6 A schematic diagram of a flow chart of a third video retrieval method provided in an embodiment of the present application;

[0046] Figure 7 A schematic diagram of the structure of a first video retrieval device provided in an embodiment of the present application;

[0047] Figure 8 A schematic diagram of the structure of a second video retrieval device provided in an embodiment of the present application;

[0048] Fig. 9 A schematic diagram of the structure of the first client provided in the embodiment of the present application;

[0049] Fig.10 A schematic diagram of the structure of the first server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field based on the present application belong to the scope of protection of the present application.

[0051] First, the various devices mentioned in the embodiments of the present application and the interaction relationship between the various devices are explained.

[0052] like Figure 1 , showing a schematic diagram of the interaction between various devices.

[0053] Combine the following Figure 1 , introduce each device.

[0054] 1. Video Capture Equipment 101

[0055] The video capture device 101 is used to capture videos and cache them, or store them in the storage server 102 .

[0056] When the video acquisition device 101 caches the video, the video acquisition device can identify objects appearing in the video, and obtain and store object description information of the identified objects.

[0057] Among them, the above-mentioned objects can be people, cars, etc., and the object description information can be people’s clothing, age, gender, hairstyle, whether they wear a mask, the color, brand, license plate number, etc. of the vehicle.

[0058] There may be one or more video acquisition devices 101 .

[0059] 2. Storage Server 102

[0060] The storage server 102 is used to store the videos captured by the video capture device 101 .

[0061] In addition, after obtaining the video captured by the video capture device 101, the storage server 102 can also identify objects appearing in the video, and obtain and store object description information of the identified objects.

[0062] There may be one or more storage servers 102 .

[0063] 3. Search Server 103

[0064] The search server 103 can search for videos collected by the video acquisition device 101 to obtain video search information of the videos. Since the videos collected by the video acquisition device 101 can be stored in the video acquisition device 101 or the storage server 102, the search server 103 can be connected to the video acquisition device 101 and the storage server 102 to search for videos stored in the two devices.

[0065] The video retrieval information may include the video acquisition time period, bitstream type, video thumbnail, device information of the device that acquires the video, the location of the device that acquires the video, and the like.

[0066] In addition, when performing retrieval, the retrieval server 103 may periodically inspect the videos stored in the video acquisition device 101 or the storage server 102, and store the video retrieval information of the videos stored in the video acquisition device 101 or the storage server 102 during each inspection period.

[0067] For example, the retrieval server 103 conducts inspections every 5 hours, such as at 5:00, 10:00, 15:00 and 20:00 on a certain day. After the inspection at 5:00, the index server 103 can store the video retrieval information of the videos from 0:00 to 5:00 on the same day. After the inspection at 10:00, the index server 103 can continue to store the video retrieval information of the videos from 5:00 to 10:00 on the basis of the originally stored information, that is, the index server 103 stores the video retrieval information of the videos from the current 0:00 to 10:00. Similarly, after the inspection at 15:00, the index server 103 can store the video index information of the videos from 0:00 to 15:00 on the same day. After the inspection at 20:00, the index server 103 can store the video index information of the videos from 0:00 to 20:00 on the same day.

[0068] The following describes the interaction between the search server 103 and the video acquisition device 101, and the interaction between the search server 103 and the storage server 102.

[0069] 1. Interaction between the search server 103 and the video acquisition device 101

[0070] The search server 103 is connected to the video acquisition device 101 . The search server 103 can search for videos acquired and stored by the video acquisition device 101 , obtain video search information of the videos acquired by the video acquisition device 101 , and store the video search information.

[0071] In addition, when searching for videos in the video acquisition device 101 , the search server 103 may also obtain object description information of objects appearing in the videos stored in the video acquisition device 101 , and store the object description information.

[0072] 2. Interaction between the retrieval server 103 and the storage server 102

[0073] The search server 103 is connected to the storage server 102. The search server 103 can search for videos stored in the storage server 102, obtain video search information of the videos stored in the storage server 102, and store the video search information.

[0074] In addition, when searching for videos in the storage server 102 , the search server 103 may also obtain object description information of objects appearing in the videos stored in the storage server 102 , and store the object description information.

[0075] The search server 103 may also be connected to the auxiliary information collection device 104 to obtain information collected by the auxiliary information collection device 104 and store the information.

[0076] 4. Auxiliary information collection equipment 104

[0077] The auxiliary information collection device 104 may be a door access control device. In this case, the information collected by the door access control device may be authentication event information of persons, vehicles and other objects entering and exiting the door, such as information on card swiping, face swiping events and the like.

[0078] The auxiliary information collection device 104 may also be a clock-in machine. In this case, the information collected by the clock-in machine may be clock-in records.

[0079] The auxiliary information collection device may also be other devices for collecting information, and may be used to collect other types of information. The present application embodiment does not limit this.

[0080] 5. Client 105

[0081] The client 105 is connected to the search server 103 and is used to send a request to the search server 103 and obtain a result fed back by the search server 103 .

[0082] The client 105 may also be connected to the video acquisition device 101 or the storage server 102 to send a request to the video acquisition device 101 or the storage server 102 and obtain a result fed back by the video acquisition device 101 or the storage server 102 .

[0083] The following is a detailed description of a video retrieval method and device provided in an embodiment of the present application.

[0084] See also Figure 2 , Figure 2 A flowchart of the first video retrieval method provided in an embodiment of the present application. In this embodiment, the above method is applied to the client and includes the following steps S201-S203.

[0085] Step S201: Obtain a search time period.

[0086] Specifically, the client may display a user interaction interface, in which the user inputs the acquisition time period of the video that the user wishes to search, so that the client may obtain the time period input by the user as the retrieval time period.

[0087] In addition, the user interaction interface may also include multiple time period options, such as the past 6 hours, the past 1 day, yesterday, etc. The user may select one of the time period options, so that the client may determine the retrieval time period based on the current time and the time period option selected by the user.

[0088] For example, if the user selects the option of nearly 6 hours, and the current time is 12:00 on July 31, then the time period from 6:00 on July 31 to 12:00 on July 31 can be determined as the search time period.

[0089] Step S202: If there is a first sub-time period starting from the first time forward in the retrieval time period, a first video retrieval request for searching the first sub-time period is generated, the first video retrieval request is sent to the retrieval server, and a first retrieval result is obtained by the retrieval server in response to the first video retrieval request based on the stored video retrieval information.

[0090] Among them, the video retrieval information is obtained by the retrieval server inspecting the videos collected by the video acquisition device in each inspection cycle.

[0091] The video acquisition device can continuously acquire videos. Therefore, the retrieval server needs to periodically retrieve the videos acquired by the video acquisition device according to a preset inspection cycle, such as every 5 hours or every 3 hours, to ensure the timeliness of the video retrieval information stored in the retrieval server.

[0092] Since the video captured by the video capture device is cached in the video capture device or stored in the storage server, when the retrieval server retrieves the video captured by the video capture device, it can retrieve the video stored in the video capture device or the storage server.

[0093] See also Figure 3 , shows the retrieval process of the retrieval server periodically searching the videos collected by the video acquisition device. Figure 3 In the retrieval process shown, the retrieval server is started (step S301), and the video pre-retrieval function is turned on, so that the retrieval server periodically retrieves the videos collected by each video acquisition device, wherein the retrieval period is set to 5 hours, that is, the retrieval is performed once every 5 hours (step S302). During the retrieval process, the retrieval server obtains the video retrieval information of the videos in each video acquisition device and the storage server (step S303), and stores the obtained video retrieval information in the database of the retrieval server (step S304).

[0094] The first time mentioned above is: a preset time period from the current time forward or the end time of the latest inspection cycle in which the retrieval server has completed inspection.

[0095] The above-mentioned preset time length is greater than the time length of the inspection cycle, and the above-mentioned preset time length is a pre-set time length, such as 5 hours, 6 hours, etc.

[0096] The following describes two situations at the first time and how the client generates a first video retrieval request in these two situations.

[0097] 1. The first time is: the time from the current moment forward by a preset length of time

[0098] Since the above-mentioned preset duration is greater than the duration of the inspection cycle, the time preset from the current moment forward must be earlier than the end time of the most recent inspection of the retrieval server, and the retrieval server must store video retrieval information of the video before the first time. Therefore, the client can obtain the video retrieval information of the video in the first sub-time period before the first time from the retrieval server.

[0099] In view of this, after obtaining the retrieval time period, the client can go back the preset time from the current time to obtain the first time, and compare the first time with the start time and end time of the retrieval time period.

[0100] If the first time is earlier than the start time of the search time period, it means that the entire search time period is later than the first time, and there is no first sub-time period starting from the first time forward in the search time period;

[0101] If the first time is later than the start time of the search time period and later than the end time of the search time period, it means that part of the search time period is earlier than the first time and the other part is later than the first time. In this case, the client can determine that the time period from the start time of the search time period to the first time is the first sub-time period;

[0102] If the first time is later than the end time of the search time period, it means that the entire search time period is earlier than the first time. At this time, the client can determine that the entire search time period is the first sub-time period.

[0103] In the case that there is a first sub-time period in the retrieval time period, after the client determines the first sub-time period, it may generate a first video retrieval request for retrieving videos in the first sub-time period.

[0104] 2. The first time is: the end time of the latest inspection cycle that the retrieval server has completed inspection

[0105] The client can determine the end time of each inspection of the video collected by the video acquisition device by the retrieval server through the communication connection with the retrieval server. The latest inspection cycle is the inspection cycle of the last inspection completed by the retrieval server.

[0106] When the client obtains the retrieval time period, it can determine the end time closest to the current time from the determined end time. This time is the end time of the latest inspection cycle. The client can use it as the first time and compare the first time with the start time and end time of the retrieval time period.

[0107] For example, the retrieval server performs inspections at four times: 5:00, 10:00, 15:00 and 20:00. If the client obtains the retrieval time period at 6:00, the end time of the latest inspection cycle that the retrieval server has completed inspection at this time is 5:00; if the client obtains the retrieval time period at 14:00, the end time of the latest inspection cycle that the retrieval server has completed inspection at this time is 10:00.

[0108] When there is a first sub-time period in the search time period, after determining the first sub-time period, the client may generate a first video search request for searching videos in the first sub-time period, and send the first video search request to the search server.

[0109] The video retrieval information stored in the retrieval server may include the video collection time period. In this way, after receiving the first video request, the retrieval server can obtain the first sub-time period carried in the request, and determine the video retrieval information that has an intersection between the included collection time period and the first sub-time period in the video retrieval information stored in the retrieval server, and feed back the first retrieval result including the determined video retrieval information to the client, so that the client can obtain the first retrieval result fed back by the retrieval server.

[0110] Step S203: If there is a second sub-time period after the first time in the search time period, a second video search request for searching the second sub-time period is generated, and the second video search request is sent to the video acquisition device to obtain a second search result fed back by the video acquisition device for the second video search request.

[0111] Although the retrieval server can periodically retrieve the videos collected by the video collection device, it is still difficult for the retrieval server to ensure that the stored video retrieval information is updated in real time.

[0112] For example, the search server can perform a search every three hours. If two adjacent search times are 5 o'clock and 8 o'clock, that is, the search server performs a search at 5 o'clock and another search at 8 o'clock, in this case, for the video captured by the video acquisition device during the time period from 5 o'clock to 8 o'clock, the search server can only retrieve and obtain the video search information of the video during the time period from 5 o'clock to 8 o'clock when performing a search at 8 o'clock. If the client performs a video search at any time during the time period from 5 o'clock to 8 o'clock, it is difficult for the search server to feedback the video search information of the video after 5 o'clock to the client.

[0113] In view of this, if there is a second sub-time period after the first time period in the above retrieval time period, for the second sub-time period, it can be considered that the video acquisition device has acquired the video in the second time period, but the retrieval server has not yet retrieved the video retrieval information of the video in the first time period. At this time, the client needs to send a retrieval request to the video acquisition device.

[0114] Specifically, the client can compare the first time with the start time and end time of the search time period. If the first time is earlier than the start time of the search time period, it means that the entire search time period is later than the first time. At this time, the client can determine that the entire search time period is the second sub-time period;

[0115] If the first time is later than the start time of the retrieval time period and later than the end time of the retrieval time period, it means that part of the retrieval time period is earlier than the first time and the other part is later than the first time. At this time, the client can determine that the time period from the first time to the end time of the retrieval time period is the second sub-time period.

[0116] After determining the second sub-time period, the client may generate a second video retrieval request for retrieving videos in the second sub-time period, and send the second video retrieval request to the video acquisition device.

[0117] After capturing a video, the video capture device can store the captured video or the video retrieval information of the captured video, and the video retrieval information can include the video capture time period. In this way, after receiving the second video request, the video capture device can obtain the second sub-time period carried in the request, and determine the video retrieval information in the video retrieval information stored in itself that has an intersection between the captured time period and the second sub-time period, and feed back the second retrieval result including the determined video retrieval information to the client, so that the client can obtain the second retrieval result fed back by the retrieval server.

[0118] When the video acquisition device feeds back the second search result to the client, the video acquisition device may send the second search result directly to the client, or may send the second search result to the retrieval server, which then sends the second search result to the client. In this way, the retrieval server may also store the video retrieval information in the second search result after being transferred by the retrieval server.

[0119] After obtaining the search results, the client can display various video search information contained in the search results. For example, if the video search information contains a video thumbnail, the video thumbnail can be displayed.

[0120] It can be seen from the above that when the solution provided by the embodiment of the present application is used to retrieve videos, the retrieval server stores video retrieval information of the videos captured by the video acquisition device. In this way, when there is a first sub-time period starting from the first time forward in the retrieval time period, the client only needs to send a video retrieval request to the retrieval server to obtain the first retrieval result fed back by the retrieval server, without sending a video retrieval request to each video acquisition device, that is, there is no need to search in each video acquisition device. Therefore, the video retrieval solution provided by the embodiment of the present application can improve the efficiency of video retrieval.

[0121] In one embodiment of the present application, when a video search request is generated, it can be generated based on the search time period and the location of the video acquisition device, so that the video search request is sent to the search server to search for videos captured by the video acquisition device in the time period and the location included in the request. The location of the video acquisition device can be represented by the device name of the video acquisition device or the installation location of the device.

[0122] See also Figure 4a , provides an interface diagram of the first result display interface. Figure 4a In the interface shown, area 1 is the search condition area, and area 2 is the result display area.

[0123] Area 1 contains three items to be filled in: time, location, and target. The user selects the time period of the last 6 hours in the time item, and fills in camera 1, camera 2, door 1, and door 2 in the location item. The target item defaults to any target. In this way, a video retrieval request can be generated based on the above time period and location filled in by the user.

[0124] Area 1 also displays two information items: recent search and saved search. The recent search information item is used to display the search time of the most recent searches, and the saved search information item is used to display the saved search results.

[0125] Area 2 displays the search results obtained by the video search request generated based on the information filled in by the user in Area 1. The three options of ordinary video, target and label displayed in Area 2 correspond to three display areas. The display area corresponding to ordinary video is the display area of ​​the results obtained by searching based on the information displayed in Area 1. The display areas corresponding to target and label can be seen in the following Figure 4e , Figure 4f , which will not be described in detail here. The current area 2 is the display area corresponding to the general recording option.

[0126] Area 2 also includes a select all control 401, a filter control 402, and a sort control 403. The select all control 401 is used to select all displayed video retrieval information with one click; the filter control 402 is used to filter and display the video retrieval information included in the first search result. If the filter control 402 displays camera 1, it means that the video thumbnails in the video retrieval information displayed in area 2 are video thumbnails of videos captured by camera 1; the sort control 403 is used to control the video thumbnails displayed in area 2 to be displayed in chronological order or in reverse order.

[0127] Figure 4a Area 2 also includes a video export option. After the user clicks the video export option, the client can display the following Figure 4b In the video export interface shown, after the user selects the video to be exported in the video export interface, the user can click the Export button to export the video.

[0128] In addition, after the user clicks the export button, the client can also display Figure 4c The export format interface shown includes file type options and whether to export pictures. The file type options include Excel, PDF, and CSV. Users can choose the appropriate file type according to their needs and choose whether to export pictures.

[0129] In addition to sending video retrieval requests to the retrieval server, the client may also send other requests to the retrieval server to obtain retrieval results obtained according to the other requests.

[0130] In one embodiment of the present application, the client may generate an object retrieval request including description information of the object to be retrieved, send the object retrieval request to the device to be retrieved, and obtain the object retrieval result generated by the device to be retrieved in response to the object retrieval request.

[0131] The object retrieval result includes: video retrieval information of the first video and first object description information of the first object in the stored object description information.

[0132] The first video is: a video containing the first object retrieved from the second video based on the video retrieval information of the second video.

[0133] If the device to be searched is a search server, the second video is: the video corresponding to the first search result.

[0134] If the device to be searched is a video acquisition device, the second video is the video corresponding to the second search result.

[0135] The first object is: an object that appears in the first video and matches the description information of the object to be retrieved.

[0136] Specifically, after obtaining the first search result and / or the second search result, the client can display the first search result and / or the second search result. After consulting the displayed search results, the user can determine the object that the user expects to retrieve. For ease of description, the object that the user expects to retrieve is referred to as the target object.

[0137] After the user determines the target object, he can learn some descriptive information of the target object from the displayed search results. For example, the user can know the color of the target object's top, whether he wears glasses, whether he wears a mask, gender, etc. from the video thumbnail of the search results, and the user can enter the descriptive information he has learned in the client.

[0138] The client obtains the description information input by the user, and can use the description information as the description information of the object to be retrieved, generate an object retrieval request containing the description information of the object to be retrieved, and send the generated object retrieval request to the retrieval server and / or the video acquisition device.

[0139] For example, if the client only obtains the first search result, the device to be searched is a search server, so after the client generates an object search request, it can send the object search request to the search server;

[0140] If the client only obtains the second search result, the device to be searched is a data acquisition device. In this way, after the client generates an object search request, it can send the object search request to the video acquisition device.

[0141] If the client obtains the first search result and the second search result, the search results can be displayed in batches. If the client obtains the description information input by the user when displaying the first search result, the client can determine the search server as the device to be searched; if the client obtains the description information input by the user when displaying the second search result, the client can determine the video acquisition device as the device to be searched. Or when the user enters the description information, he selects the first search result or the second search result, so that the client can select the search server or the video acquisition device as the device to be searched.

[0142] In the case where the client sends an object retrieval request to the retrieval server, the second video is the video corresponding to the first retrieval result. After receiving the object retrieval request, the retrieval server can determine the object description information of the object appearing in the video corresponding to the first retrieval result in the stored object description information, and match the determined object description information with the object description information to be retrieved carried in the object retrieval request, thereby obtaining the object description information that matches the object description information to be retrieved in the determined object description information as the first object description information, and determining that the video corresponding to the first object description information is the first video, thereby generating the video retrieval information including the first video and the object retrieval result of the first object description information, and feeding back the object retrieval result to the client.

[0143] The case where the client sends an object retrieval request to the video acquisition device is similar to the case where the client sends an object retrieval request to the retrieval server, and will not be described in detail here.

[0144] After the client obtains the object search result generated by the device to be searched in response to the object search request, the client may display the video search information and the first object description information included in the object search result.

[0145] As can be seen from the above, when applying the solution provided in the embodiment of the present application to retrieve videos, the client can send an object retrieval request to the device to be retrieved, and obtain the object retrieval result generated by the device to be retrieved for the object retrieval request, and the object retrieval result includes the video retrieval information of the first video and the first object description information. The first video is a video containing the first object, and the first object is an object that appears in the first video and matches the description information of the object to be retrieved. It can be seen that the client can obtain the video retrieval information of the video of the object requested to be retrieved and the retrieval result of the object description information of the object by interacting with the retrieval server, that is, the client expects to retrieve the video of the object, and the retrieval server can feedback the video retrieval information of the video containing the object and the retrieval result of the object description information of the object, thereby realizing the object retrieval function. Therefore, by applying the video retrieval solution provided in the embodiment of the present application, the client can not only provide users with the function of video retrieval according to time periods, but also provide object retrieval functions, thereby broadening the scope of application of the solution.

[0146] In one embodiment of the present application, in addition to generating an object retrieval request based on object description information, an object retrieval request may also be generated based on any of the following information:

[0147] Images, keywords, locations of video capture devices, and employee position information entered by the user.

[0148] See also Figure 4d , provides a schematic diagram of the interface of the search guide interface, Figure 4dThe interface shown provides the user with a variety of items to be filled in, namely time, location, target, and key features. Among them, the time item is used for the user to enter the above-mentioned search time period; the location item is used for the user to enter the location of the video acquisition device, and the user can select the location through the selection control of the item; the target item is used for the user to input an image, which can be a person image, a face image, a vehicle image, etc. The user can upload the image through the upload image control of the item; the key feature item is used for the user to enter keywords, and the user can enter the key features, or keywords, through the input feature control of the item.

[0149] from Figure 4d It can be seen that the user selected the time period of the last 6 hours in the time field, and filled in young people, men, and name: Lisa in the key feature field. Therefore, an object search request can be generated based on the search time period and keywords to search for videos in the last 6 hours that contain young people, men, and a person named Lisa.

[0150] In addition, the user did not fill in the content in the location and target items. The preset guidance information was displayed in these two items. One guidance message for the location item was: I can search for people and vehicles by the selected location, and the other guidance message was: Select a camera, door, or a specific area in the camera screen (VCA detection area). One guidance message for the target item was: I can also use pictures to search for people, and the other guidance message was: Move the picture to any position on the screen to search. There was also a guidance message displayed in the key feature item: I can still search for people and vehicles based on key features.

[0151] After obtaining the search results, the client may also execute the steps in the following embodiments to display information to the user.

[0152] In one embodiment of the present application, when the client obtains the first search result, it can display the first search result and the video auxiliary information generated based on the first search result;

[0153] When the client obtains the second search result, it can display the second search result and the video auxiliary information generated based on the second search result.

[0154] The video auxiliary information includes at least one of the following information:

[0155] The collection time distribution information of the video corresponding to the search result;

[0156] The attribute value selection items of the objects in the video corresponding to the search results.

[0157] Specifically, when the video auxiliary information includes acquisition period distribution information, after receiving the search results, the client can count the video acquisition time periods contained in the video retrieval information in the search results, generate the acquisition period distribution information based on the statistically obtained video acquisition time periods, and display the acquisition period distribution information.

[0158] In the case where the video auxiliary information includes attribute value selection items, after receiving the search results, the client can integrate the attribute value distribution of the same type of attributes in the object description information corresponding to each video in the search results, and generate attribute value selection items corresponding to the integrated attribute type.

[0159] For example, if the search results contain object description information corresponding to videos a and b, wherein the object description information corresponding to video a contains description information of person 1: gender male, red top, black pants, and the object description information corresponding to video b contains description information of person 2: gender female, blue top, and age between 20 and 30 years old, then the client can integrate the object description information corresponding to videos a and b to obtain four attribute types, namely gender, top color, pants color, and age range, and the attribute value of gender is determined to include male and female, the attribute value of top color includes red and blue, the attribute value of pants color includes black, and the attribute value of age range includes 20-30. At this time, the client can display the attribute value selection items of the obtained four attribute types. And when the user selects one of the attribute value selection items, the client can display the type value of the attribute type corresponding to the attribute value selection item selected by the user. For example, if the user selects the attribute value selection item of gender, the client can display two attribute values ​​of male and female, and the user can further select one of the two attribute values. In this way, the client can filter the results containing the attribute value selected by the user in the first search result and display the filtered results. For example, if the user selects the attribute value "male", the client can filter out the object description information of video a, thereby displaying the object description information of video a.

[0160] In the case where the video auxiliary information includes the acquisition period distribution information and the attribute value selection items, the client may generate and display the acquisition period distribution information and the attribute value selection items in the manners mentioned in the above two cases.

[0161] See also Figure 4e , provides a schematic diagram of the second result display interface, Figure 4e The interface shown contains a display area corresponding to the target option. Figure 4a Compared with the displayed interface, Figure 4eThe display area of ​​the interface shown also adds attribute value selection items of people and cars in the video corresponding to the search results. The attribute selection items of people include gender, age, whether wearing glasses, whether not wearing a mask, whether wearing a hat, top color, whether having a backpack, and whether riding a bicycle. The attribute value selection items of cars include vehicle list, license plate number, owner's name, vehicle type and color.

[0162] In addition, Figure 4a as well as Figure 4e The result statistics information item displays the collection period distribution information of the video corresponding to the search results.

[0163] From the above, it can be seen that when the solution provided in the embodiment of the present application is used to retrieve videos, the client not only displays the search results, but also displays the video auxiliary information generated based on the search results. The display content is richer, which can improve the user experience and enhance user stickiness.

[0164] In one embodiment of the present application, if the above-mentioned first time is within the retrieval time period, the client can generate a first video retrieval request for searching the first sub-time period and a second video retrieval request for searching the second sub-time period, so that the client can obtain the first retrieval result fed back by the retrieval server and the second retrieval result fed back by the video acquisition device.

[0165] In this case, when displaying the search results, the client can display the search results and the video auxiliary information generated based on each search result in batches according to the order in which the search results are obtained.

[0166] Specifically, if the client first receives a first search result fed back by the search server and then receives a second search result fed back by the video acquisition device, the client may first display the first search result and then display the second search result.

[0167] If the client first receives the second search result fed back by the video acquisition device and then receives the first search result fed back by the search server, the client may first display the second search result and then display the first search result.

[0168] When the client receives one of the first and second search results first, the search result may be displayed immediately, and when the client receives the other search result again, the other search result may be displayed.

[0169] For example, after the client receives the first search result, the first search result is displayed immediately, and then when the client receives the second search result, the second search result is displayed.

[0170] This solution adopts the method of displaying each search result and video auxiliary information in batches, which can avoid displaying too much information at one time and causing users to miss information when searching for information. Displaying information in batches can also facilitate user browsing.

[0171] In one embodiment of the present application, the client displays the following Figure 4a , Figure 4e When the interface is shown, the user can manually mark the video retrieval information of interest displayed on the interface, or the client can mark the video retrieval information by itself according to the object behavior information contained in the video retrieval information. After the video retrieval information is marked, the user clicks Figure 4a , Figure 4e After clicking the tag option in the interface shown, an interface containing the tagged video retrieval information can be displayed so that users can view, collect and export the tagged information.

[0172] like Figure 4f , provides a schematic diagram of the third result display interface, Figure 4f The interface shown contains a display area corresponding to the label options. Figure 4a Compared with the displayed interface, Figure 4f The display area of ​​the interface shown also adds an event alarm tag option, a manual tag option, and a tag name option. The event alarm tag option is used to filter video retrieval information with event alarm tags in the retrieval results, that is, video retrieval information tagged by the client itself; the manual tag option is used to filter video retrieval information with manual user tags in the retrieval results; the tag name option is used to filter video retrieval information with various tags in the retrieval results.

[0173] See also Figure 4g , provides a schematic diagram of the fourth result display interface. Figure 4g In the example, the time item is filled in as the last 6 hours, the location item is filled in as all locations by default, and the target item is filled in as the attributes of the person and vehicle, among which the person attributes include youth, male, and not wearing glasses, and the vehicle attributes include sedan and red. Figure 4g The interface shown includes a display area corresponding to the target option, and the video thumbnails displayed therein are video thumbnails of videos filtered according to the information displayed in area 1 and the filtering conditions displayed in the filtering control in the display area.

[0174] See also Figure 4h , provides a schematic diagram of the fifth result display interface. Figure 4g compared to, Figure 4h The target items to be filled in are filled with the position information of two system employees. Figure 4hThe display area corresponding to the target option is included in the display area, which displays the search results of two employees. When the user selects one of the search results, the following can be displayed: Figure 4i The result display interface shown.

[0175] and Figure 4a compared to, Figure 4i The display area corresponding to the target option includes the name of the employee corresponding to the search result selected by the user. Figure 4i The display area also displays three record options: face comparison record, authentication record, and vehicle record. Selecting one of the options will display the video thumbnail of the corresponding video.

[0176] See also Figure 4j , provides a schematic diagram of the seventh result display interface, and Figure 4g compared to, Figure 4j The target item in the target list is filled in as a picture, including the target picture and the face picture and body picture segmented from the target picture. Figure 4j The similarity option is also included, and the similarity is: the similarity between any image in the target item to be filled in and the video thumbnail in the video search information included in the first search result, and the similarity is set through the similarity option. Figure 4j The video thumbnails of the video retrieval information meeting the similarity requirements can be displayed.

[0177] Corresponding to the video retrieval method applied to the client, the embodiment of the present application also provides a video retrieval method applied to the retrieval server.

[0178] In one embodiment of the present application, see Figure 5 , a flow chart of a second video retrieval method is provided. In this embodiment, the method includes the following steps S501-S503.

[0179] Step S501: in response to a video inspection indication, obtaining video retrieval information of a video captured by a video acquisition device within an inspection period indicated by the video inspection indication, and storing the obtained video retrieval information;

[0180] The video inspection instruction is used to instruct the retrieval server to perform video retrieval on the video acquisition device and / or the storage server to obtain video retrieval information of the video acquired by the video acquisition device and / or video retrieval information of the video stored by the storage server.

[0181] The above-mentioned video inspection instruction may be generated periodically by the retrieval server, or may be input by the operation and maintenance personnel of the retrieval server.

[0182] For example, the duration of the above-mentioned inspection cycle can be 5 hours. If the retrieval server has performed an inspection at 0 o'clock, then when the time reaches 5 o'clock, the retrieval server can generate a video inspection indication again to instruct itself to search for the videos within the inspection cycle from 0 o'clock to 5 o'clock stored in the video acquisition device and / or storage server, and obtain the video retrieval information of the videos from 0 o'clock to 5 o'clock; when the time reaches 10 o'clock, the retrieval server can generate a video inspection indication again to retrieve the video retrieval information of the videos from 5 o'clock to 10 o'clock. At this time, the retrieval server stores the video retrieval information of the videos from 0 o'clock to 10 o'clock.

[0183] Specifically, in response to the video inspection instruction, the retrieval server may obtain the video retrieval information of the video captured by the video capture device in any one of the following three ways.

[0184] In a first implementation manner, the video collected within the inspection period indicated by the video inspection indication stored in the storage server is retrieved to obtain video retrieval information.

[0185] The storage server is used to store videos uploaded by the video acquisition device.

[0186] After the video acquisition device acquires the video, it stores the acquired video in the storage server. In response to the video inspection indication, the retrieval server can determine the inspection cycle indicated by the video inspection indication, so that the retrieval server can send a retrieval request for the video acquired within the inspection cycle determined by the inspection to the storage server. After receiving the retrieval request, the storage server can respond to the request, determine the inspection cycle requested for inspection, and feed back the video retrieval information of the video acquired within the determined inspection cycle stored in itself to the retrieval server, so that the subsequent retrieval server can perform video retrieval based on the stored video retrieval information.

[0187] In a second implementation, the video captured within the inspection period indicated by the video inspection indication buffered by the video acquisition device is retrieved to obtain video retrieval information.

[0188] After the video acquisition device acquires the video, the video can be cached. In response to the video inspection indication, the retrieval server can determine the inspection cycle indicated by the video inspection indication, thereby sending a retrieval request for inspecting the video acquired within the inspection cycle determined by the inspection to the video acquisition device. After receiving the retrieval request, the video acquisition device can respond to the request, determine the inspection cycle requested for inspection, and feed back the cached video retrieval information of the video acquired within the determined inspection cycle to the retrieval server, so that the retrieval server can subsequently perform video retrieval based on the stored video retrieval information.

[0189] In a third implementation, the retrieval server may retrieve the videos stored in the storage server and the video acquisition device and acquired within the inspection period indicated by the video inspection indication.

[0190] The retrieval server not only searches for videos stored in the storage server, but also searches for captured videos cached by the video capture device. In this way, the retrieval server can obtain more comprehensive and richer video retrieval information of the video, and thus perform video retrieval based on the more comprehensive and richer video retrieval information, which can improve the video retrieval function of the retrieval server.

[0191] After obtaining the video search information, the search server stores the obtained video search information. The specific implementation of storing the obtained video search information can be found in the subsequent embodiments, which will not be described in detail here.

[0192] Step S502: In response to a first video search request from the client, based on the stored video search information, searching for videos that meet the video search request, and obtaining a first search result of the retrieved videos.

[0193] The first video retrieval request is: the first sub-time period starting from the first time in the retrieval time period of the client.

[0194] The first time is: the end time of the latest inspection cycle that has completed the inspection or the time from the moment when the client obtains the retrieval time period forward by a preset time period. The preset time period is greater than the time period of the inspection cycle.

[0195] For the description of the first time, inspection cycle, preset duration, search time period, first sub-time period and first video search request, please refer to the aforementioned step S101, which will not be repeated here.

[0196] After the retrieval server receives the first video retrieval request sent by the client, it can determine the first sub-time period carried in the first video retrieval request, and based on the video acquisition time period included in the stored video retrieval information, determine the video retrieval information in which the video acquisition time period intersects with the first sub-time period. The video corresponding to the determined video retrieval information is the video that satisfies the video retrieval request. At this time, the retrieval server can generate a first retrieval result including the determined video retrieval information.

[0197] Step S503: taking the first search result as the search result to be sent, and sending the search result to be sent to the client.

[0198] It can be seen from the above that when the solution provided by the embodiment of the present application is used to retrieve videos, the client sends a first video retrieval request to the retrieval server. The retrieval server can retrieve videos that meet the first video retrieval request based on the stored video retrieval information, and obtain a first retrieval result of the retrieved video. In this way, the client does not need to search in each video acquisition device and storage server. Therefore, the video retrieval solution provided by the embodiment of the present application can improve the efficiency of video retrieval.

[0199] In one embodiment of the present application, the retrieval server responds to a first video retrieval request. If no video satisfying the first video retrieval request is retrieved based on the stored video retrieval information, the retrieval server may send the first video retrieval request to the video acquisition device, and obtain the retrieval result of the video acquisition device performing the retrieval on the first video retrieval request as the first retrieval result, thereby using the first retrieval result as the retrieval result to be sent and sending the retrieval result to be sent to the client.

[0200] Since all collected videos can be cached in the video capture device, when the retrieval server fails to retrieve a video that satisfies the first video retrieval request based on the stored video retrieval information, it can send a first video retrieval request to the video capture device to retrieve the video that satisfies the first video retrieval request from all videos collected by the video capture device, thereby obtaining a retrieval result and feeding back the retrieval result to the client, which can improve the reliability of video retrieval.

[0201] In the above-mentioned embodiment, it is mentioned that if there is a second sub-time period in the retrieval time period, the client sends a second video retrieval request to the video acquisition device.

[0202] In response to this situation, in one embodiment of the present application, the retrieval server can receive the second retrieval result for the second video retrieval request sent by the video acquisition device, use the second retrieval result as the retrieval result to be sent, send the retrieval result to be sent to the client, and obtain the video lock information of the video in the second retrieval result, and update the locally stored video retrieval information based on the obtained video retrieval information.

[0203] The second video retrieval request is a request for video retrieval in the second sub-time period.

[0204] The second sub-time period is: a time period in the client's retrieval time period that is located after the first time period.

[0205] For the description of the second sub-time period and the second video retrieval request, please refer to the aforementioned embodiment and will not be repeated here.

[0206] Specifically, the client can send a second video retrieval request to the video acquisition device. After receiving the second video retrieval request, the video acquisition device can determine the video retrieval information of the video stored in its own video retrieval information, in which the video acquisition time period contained in the information has an intersection with the second sub-time period, thereby generating a retrieval result containing the determined video retrieval information, and sending the generated retrieval result to the retrieval server.

[0207] After receiving the search result generated by the video acquisition device, the search server can forward the search result to the client, obtain the video search information contained in the search result, and update the video search information stored locally on the search server based on the obtained video search information.

[0208] It can be seen from the above that when the solution provided in the embodiment of the present application is used to retrieve videos, the retrieval server can obtain the second retrieval result sent by the video acquisition device, and on the one hand send the second retrieval result to the client, and on the other hand obtain the video retrieval information of the video in the second retrieval result, and update the locally stored video retrieval information based on the obtained video retrieval information. In this way, using the retrieval server as a transit can not only ensure that the client can perform video retrieval normally, but the retrieval server can also update the locally stored video retrieval information, thereby improving the timeliness of the retrieval server providing video retrieval information to the client.

[0209] In one embodiment of the present application, when the first time is within the retrieval time period, the client can send a first video retrieval request to the retrieval server and send a second video retrieval request to the video acquisition device, so that the retrieval server can not only generate the first retrieval result itself, but also receive the second retrieval result sent by the video acquisition device. At this time, when the retrieval server feeds back the retrieval results to the client, the retrieval results to be sent include the first retrieval results and the second retrieval results. The retrieval server can send each retrieval result to the client in batches according to the order in which the retrieval results to be sent are obtained.

[0210] Specifically, when the search server generates a first search result first and then receives a second search result sent by the video acquisition device, the search server may first send the first search result to the client and then send the second search result to the client.

[0211] When the search server first receives the second search result sent by the video acquisition device and then generates the first search result, the search server may first send the second search result to the client and then send the first search result to the client.

[0212] In addition, when the search server first obtains one of the first and second search results, it can immediately send the search result to the client, and then obtain the other search result, it can send the other search result to the client.

[0213] For example, if the search server generates a first search result first, it can send the first search result to the client immediately after the first search result is generated, and then receive the second search result, and then send the second search result to the client.

[0214] In this solution, the retrieval server sends each retrieval result to be sent to the client in batches, which can avoid occupying more transmission bandwidth when sending too many retrieval results at one time, and the time when the retrieval server generates the first retrieval result and receives the second retrieval result is different. When the retrieval server receives the second retrieval result first, it can send the second retrieval result to the client first. When the retrieval server generates the first retrieval result first, it can send the first retrieval result to the client first, without waiting for the first retrieval result and the second retrieval result to be obtained before feeding back the retrieval result to the client. This can improve the response efficiency of video retrieval requests, thereby improving the retrieval efficiency of video retrieval.

[0215] The specific implementation method of storing the video retrieval information mentioned in the above step S501 is described below.

[0216] In one embodiment of the present application, when storing video retrieval information, if the video retrieval information has been stored, then the newly added information in the obtained video retrieval information is stored; if the video retrieval information has not been stored, then all the obtained video retrieval information is stored.

[0217] When the retrieval server responds to the video inspection request for the first time and obtains the video retrieval information of the video collected by the video acquisition device, no video retrieval information is stored in the retrieval server. At this time, after obtaining the video retrieval information, all the obtained video retrieval information can be directly stored; when the retrieval server has obtained the video retrieval information of the video collected by the video acquisition device, the retrieval server has stored the video retrieval information that has been obtained. At this time, after obtaining the video retrieval information this time, the stored video retrieval information and the video retrieval information obtained this time can be compared to obtain the new information of this video retrieval, thereby storing the new information.

[0218] As can be seen from the above, when the solution provided in the embodiment of the present application is used to retrieve videos, if the retrieval server has not stored video retrieval information, then all the obtained video retrieval information is stored; if the video retrieval information has been stored, then the newly added information in the obtained video retrieval information is stored. This ensures that the retrieval server can store the video retrieval information of all videos collected by the video acquisition device, so that the retrieval server performs video retrieval based on more comprehensive, stored video retrieval information, which can improve the accuracy of video retrieval.

[0219] When the storage location of the video captured by the video acquisition device changes, for example, the video is transferred from the video acquisition device to the storage server; the video cached in the video acquisition device changes, and the video stored in the storage server changes, for example, the video acquisition device or storage server only stores videos from the past week, and as time goes by, the stored videos continue to change, some video retrieval information stored in the retrieval server will become invalid.

[0220] In view of the above situation, in one embodiment of the present application, after obtaining the video retrieval information, based on the obtained video retrieval information, the invalid retrieval information in the stored video retrieval information is determined; an invalidation mark is added to the invalid retrieval information or the invalid retrieval information is deleted.

[0221] Specifically, for each video retrieval information stored in the retrieval server, it can be detected whether the video retrieval information is stored in the video retrieval information obtained this time. If it is stored, it means that the video corresponding to the video retrieval information has not changed. If it does not exist, it means that the video corresponding to the video retrieval information has changed. In this way, the video retrieval information whose detection result is non-existent is invalid retrieval information.

[0222] After the invalid retrieval information is determined, an invalid mark may be added to the invalid retrieval information to indicate that the marked video retrieval information has expired, or the invalid retrieval information may be directly deleted.

[0223] As can be seen from the above, when the solution provided by the embodiment of the present application is used to retrieve videos, after determining the invalid search information, if an invalid flag is added to the invalid search information, the record of the stored video search information can be retained without affecting the normal operation of the search server, so as to facilitate subsequent information backtracking. If the invalid search information is deleted, the storage resources of the search server can be saved.

[0224] Similar to the aforementioned method embodiment applied to the client, in one embodiment of the present application, the retrieval server can obtain the object description information and store the object description information.

[0225] Since the retrieval server can store video retrieval information and object description information, the retrieval server can provide users with richer information, thereby improving the user experience.

[0226] The object description information may include at least one of the following information:

[0227] The first type of information: object attributes and behavior description information obtained by the video acquisition device through object detection on the acquired video;

[0228] The second type of information: object behavior description information and object attributes collected by auxiliary information collection equipment.

[0229] For the first type of information mentioned above, the objects may be people, cars, etc.; the object attributes may be people's clothing, age, gender, vehicles' color, brand, license plate number, etc.; the object's behavior description information may be information representing people's walking, running, jumping, etc., vehicles' driving, stationary, turning, etc.

[0230] The video acquisition device can use object detection technology to perform object detection on the acquired video to obtain the attributes and behavior description information of the objects in the video.

[0231] For the second type of information, the auxiliary information collection device includes: information collection devices other than video collection devices, for example, the auxiliary information collection device may be an access control device, a time clock, and the like.

[0232] The object description information includes at least one of the two types of information, so that the retrieval server can store at least one of the two types of information, so that the retrieval server can provide users with richer information during the video retrieval process and improve the user experience.

[0233] See also Figure 6 , a flow chart of a third video retrieval method is provided, and the method includes the following steps S601-S607.

[0234] Step S601: Establishing a communication connection between the access control device, the video acquisition device and the search server.

[0235] Step S602: When the access control device detects an authentication event such as card swiping or face swiping, the object behavior description information and the object attributes of the object in the authentication event are sent to the search server.

[0236] Step S603: When the video acquisition device acquires a video, the video acquisition device performs object detection on the acquired video, and sends the attributes of the detected object and the behavior description information of the object to the search server.

[0237] Step S604: After the retrieval server obtains the information, it stores the obtained information in a structured manner.

[0238] Step S605: When the search server receives the search request sent by the client, the search server responds to the search request, searches for the stored information, and feeds back the search result to the client.

[0239] Step S606: The client displays the video thumbnails, videos, and attribute information included in the search results.

[0240] Step S607: The client displays or exports the video indicated by the instruction in response to the viewing or exporting instruction input by the user according to the displayed information.

[0241] In the case where the retrieval server stores the object description information, in addition to the video retrieval method mentioned in the above embodiment, the method mentioned in the following embodiment can also be used to perform video retrieval.

[0242] In one embodiment of the present application, the retrieval server can respond to an object retrieval request containing description information of an object to be retrieved, retrieve a first video containing a first object from the second video based on the retrieval information of the second video, and retrieve the first object description information of the first object from the stored object description information, to generate an object retrieval result containing a video index detail system of the first video and the first object description information.

[0243] The second video is: a video corresponding to the first search result and / or the second search result, and the first object is: an object that matches the description information of the object to be searched.

[0244] For a detailed description of this embodiment, please refer to the aforementioned method embodiment of the video retrieval method applied to the client, which will not be repeated here.

[0245] It can be seen from the above that when the solution provided in the embodiment of the present application is used to retrieve videos, the retrieval server can not only perform video retrieval in response to video retrieval requests, but also perform video retrieval in response to object retrieval requests. This can provide users with a variety of retrieval functions, thereby broadening the scope of application of the present solution.

[0246] Corresponding to the aforementioned video retrieval method, an embodiment of the present application also provides a video retrieval device.

[0247] In one embodiment of the present application, see Figure 7 , provides a structural schematic diagram of a first video retrieval device. In this embodiment, the above device is applied to a client, including:

[0248] A time acquisition module 701 is used to obtain a search time period;

[0249] The first retrieval module 702 is used to generate a first video retrieval request for searching the first sub-time period if there is a first sub-time period from the first time forward in the retrieval time period, send the first video retrieval request to the retrieval server, and obtain a first retrieval result obtained by the retrieval server in response to the first video retrieval request based on the stored video retrieval information, wherein the video retrieval information is obtained by the retrieval server through inspection of the video collected by the video acquisition device in each inspection cycle, the first time is: a preset time period from the current moment forward or an end time of the latest inspection cycle that the retrieval server has completed inspection, and the preset time period is greater than the time period of the inspection cycle;

[0250] The second retrieval module 703 is used to generate a second video retrieval request for searching the second sub-time period if there is a second sub-time period after the first time in the retrieval time period, send the second video retrieval request to the video acquisition device, and obtain a second retrieval result fed back by the video acquisition device for the second video retrieval request.

[0251] It can be seen from the above that when the solution provided by the embodiment of the present application is used to retrieve videos, the retrieval server stores video retrieval information of the videos captured by the video acquisition device. In this way, when there is a first sub-time period starting from the first time forward in the retrieval time period, the client only needs to send a video retrieval request to the retrieval server to obtain the first retrieval result fed back by the retrieval server, without sending a video retrieval request to each video acquisition device, that is, there is no need to search in each video acquisition device. Therefore, the video retrieval solution provided by the embodiment of the present application can improve the efficiency of video retrieval.

[0252] In one embodiment of the present application, the device further includes:

[0253] A request generation module, used for generating an object retrieval request including description information of an object to be retrieved;

[0254] An object retrieval module is used to send the object retrieval request to the device to be retrieved, and obtain the object retrieval result generated by the device to be retrieved for the object retrieval request, wherein the object retrieval result includes: video retrieval information of the first video and first object description information of the first object in the stored object description information, the first video is: a video containing the first object retrieved from the second video based on the video retrieval information of the second video, if the device to be retrieved is the retrieval server, then the second video is: a video corresponding to the first retrieval result, if the device to be retrieved is the video acquisition device, then the second video is: a video corresponding to the second retrieval result, and the first object is: an object appearing in the first video and matching the object description information to be retrieved.

[0255] As can be seen from the above, when applying the solution provided in the embodiment of the present application to retrieve videos, the client can send an object retrieval request to the device to be retrieved, and obtain the object retrieval result generated by the device to be retrieved for the object retrieval request, and the object retrieval result includes the video retrieval information of the first video and the first object description information. The first video is a video containing the first object, and the first object is an object that appears in the first video and matches the description information of the object to be retrieved. It can be seen that the client can obtain the video retrieval information of the video of the object requested to be retrieved and the retrieval result of the object description information of the object by interacting with the retrieval server, that is, the client expects to retrieve the video of the object, and the retrieval server can feedback the video retrieval information of the video containing the object and the retrieval result of the object description information of the object, thereby realizing the object retrieval function. Therefore, by applying the video retrieval solution provided in the embodiment of the present application, the client can not only provide users with the function of video retrieval according to time periods, but also provide object retrieval functions, thereby broadening the scope of application of the solution.

[0256] In one embodiment of the present application, the device further includes:

[0257] A result display module is used to display the first search result and the video auxiliary information generated based on the first search result when the first search result is obtained; and to display the second search result and the video auxiliary information generated based on the second search result when the second search result is obtained.

[0258] The video auxiliary information includes at least one of the following information: the acquisition period distribution information of the video corresponding to the search result; and the attribute value selection items of the object in the video corresponding to the search result.

[0259] From the above, it can be seen that when the solution provided in the embodiment of the present application is used to retrieve videos, the client not only displays the search results, but also displays the video auxiliary information generated based on the search results. The display content is richer, which can improve the user experience and enhance user stickiness.

[0260] In one embodiment of the present application, the device further includes: a batch display module, which is used to display each search result and video auxiliary information generated based on each search result in batches when the first search result and the second search result are obtained.

[0261] This solution adopts the method of displaying each search result and video auxiliary information in batches, which can avoid displaying too much information at one time and causing users to miss information when searching for information. Displaying information in batches can also facilitate user browsing.

[0262] In one embodiment of the present application, see Figure 8 , a schematic diagram of the structure of a second video retrieval device is provided. In this embodiment, the device includes:

[0263] The indication response module 801 is used to obtain, in response to the video inspection indication, the video retrieval information of the video collected by the video acquisition device within the inspection period indicated by the video inspection indication, and store the obtained video retrieval information;

[0264] The request response module 802 is used to respond to the first video retrieval request of the client, retrieve the video that meets the first video retrieval request based on the stored video retrieval information, and obtain the first retrieval result of the retrieved video, wherein the first video retrieval request is: the first sub-time period in the retrieval time period of the client starting from the first time forward, the first time is: the end time of the latest inspection cycle that has completed the inspection or the time of a preset time forward from the moment when the client obtains the retrieval time period or the time when the retrieval server last retrieved the video collected by the video acquisition device, and the preset time length is greater than the time length of the inspection cycle;

[0265] The result sending module 803 is used to take the first search result as the search result to be sent, and send the search result to be sent to the client.

[0266] It can be seen from the above that when the solution provided by the embodiment of the present application is used to retrieve videos, the client sends a first video retrieval request to the retrieval server. The retrieval server can retrieve videos that meet the first video retrieval request based on the stored video retrieval information, and obtain a first retrieval result of the retrieved video. In this way, the client does not need to search in each video acquisition device and storage server. Therefore, the video retrieval solution provided by the embodiment of the present application can improve the efficiency of video retrieval.

[0267] In one embodiment of the present application, the indication response module 801 is specifically used to: if the video retrieval information has been stored, then store the newly added information in the obtained video retrieval information; if the video retrieval information has not been stored, then store all the obtained video retrieval information.

[0268] As can be seen from the above, when the solution provided in the embodiment of the present application is used to retrieve videos, if the retrieval server has not stored video retrieval information, then all the obtained video retrieval information is stored; if the video retrieval information has been stored, then the newly added information in the obtained video retrieval information is stored. This ensures that the retrieval server can store the video retrieval information of all videos collected by the video acquisition device, so that the retrieval server performs video retrieval based on more comprehensive, stored video retrieval information, which can improve the accuracy of video retrieval.

[0269] In one embodiment of the present application, the device also includes: an information determination module, which is used to determine the invalid retrieval information in the stored video retrieval information based on the obtained video retrieval information; an information processing module, which is used to add an invalidation mark to the invalid retrieval information or delete the invalid retrieval information.

[0270] As can be seen from the above, when the solution provided by the embodiment of the present application is used to retrieve videos, after determining the invalid search information, if an invalid flag is added to the invalid search information, the record of the stored video search information can be retained without affecting the normal operation of the search server, so as to facilitate subsequent information backtracking. If the invalid search information is deleted, the storage resources of the search server can be saved.

[0271] In one embodiment of the present application, the indication response module is specifically used to: retrieve the video collected within the inspection period indicated by the video inspection indication stored in the storage server to obtain video retrieval information, wherein the storage server is used to store the video uploaded by the video acquisition device.

[0272] After the video acquisition device acquires the video, it stores the acquired video in the storage server. In response to the video inspection indication, the retrieval server can send a retrieval request to the storage server. After receiving the retrieval request, the storage server can respond to the request and feed back the video retrieval information of the stored video to the retrieval server, so that the subsequent retrieval server can perform video retrieval based on the stored video retrieval information.

[0273] In one embodiment of the present application, the indication response module 801 is specifically used to retrieve the video captured in the inspection period indicated by the video inspection indication and cached by the video acquisition device to obtain video retrieval information.

[0274] After the video acquisition device acquires the video, it can cache the video. In response to the video inspection indication, the retrieval server can send a retrieval request to the video acquisition device. After receiving the retrieval request, the video acquisition device can respond to the request and feed back the video retrieval information of the cached video to the retrieval server, so that the retrieval server can perform video retrieval based on the stored video retrieval information.

[0275] In one embodiment of the present application, the device further includes:

[0276] a request resending module, configured to send the video retrieval request to a video acquisition device if no video satisfying the video retrieval request is retrieved based on the stored video retrieval information;

[0277] The first result obtaining module is used to obtain a first search result of the video acquisition device searching for the video search request.

[0278] Since all captured videos can be cached in the video capture device, when the retrieval server fails to retrieve a video that meets the video retrieval request based on the stored video retrieval information, it can send a video retrieval request to the video capture device to retrieve the video that meets the video retrieval request from all videos captured by the video capture device. This can improve the reliability of video retrieval.

[0279] In one embodiment of the present application, the device further includes:

[0280] A second result obtaining module is used to receive a second search result for a second video search request sent by the video acquisition device, wherein the second video search request is a request for video search for a second sub-time period, and the second sub-time period is: a time period in the search time period of the client that is located after the first time period;

[0281] The result processing module is used to use the second search result as the search result to be sent, send the search result to be sent to the client, obtain video search information of the video in the second search result, and update the locally stored video search information based on the obtained video search information.

[0282] It can be seen from the above that when the solution provided in the embodiment of the present application is used to retrieve videos, the retrieval server can obtain the second retrieval result sent by the video acquisition device, and on the one hand send the second retrieval result to the client, and on the other hand obtain the video retrieval information of the video in the second retrieval result, and update the locally stored video retrieval information based on the obtained video retrieval information. In this way, using the retrieval server as a transit can not only ensure that the client can perform video retrieval normally, but the retrieval server can also update the locally stored video retrieval information, thereby improving the timeliness of the retrieval server providing video retrieval information to the client.

[0283] In one embodiment of the present application, the result sending module 803 is specifically used to: when the retrieval results to be sent include the first retrieval result and the second retrieval result, send each retrieval result to be sent to the client in batches.

[0284] In this solution, the retrieval server sends each retrieval result to be sent to the client in batches, which can avoid occupying more transmission bandwidth when sending too many retrieval results at one time, and the time when the retrieval server generates the first retrieval result and receives the second retrieval result is different. When the retrieval server receives the second retrieval result first, it can send the second retrieval result to the client first. When the retrieval server generates the first retrieval result first, it can send the first retrieval result to the client first, without waiting for the first retrieval result and the second retrieval result to be obtained before feeding back the retrieval result to the client. This can improve the response efficiency of video retrieval requests, thereby improving the retrieval efficiency of video retrieval.

[0285] In one embodiment of the present application, the device further includes:

[0286] An information acquisition module is used to obtain object description information;

[0287] The information storage module is used to store the object description information.

[0288] The object description information includes at least one of the following information: object attributes and object behavior description information obtained by the video acquisition device performing object detection on the acquired video; object behavior description information and object attributes acquired by the auxiliary information acquisition device, wherein the auxiliary information acquisition device includes: information acquisition devices other than the video acquisition device.

[0289] Since the retrieval server can store video retrieval information and object description information, the retrieval server can provide users with richer information, thereby improving the user experience.

[0290] The object description information includes at least one of the two types of information, so that the retrieval server can store at least one of the two types of information, so that the retrieval server can provide users with richer information during the video retrieval process and improve the user experience.

[0291] In one embodiment of the present application, the device further includes:

[0292] An information retrieval module is used to respond to an object retrieval request containing description information of an object to be retrieved, retrieve a first video containing a first object from the second video based on the retrieval information of the second video, and retrieve the first object description information of the first object from the stored object description information, wherein the second video is: a video corresponding to the first retrieval result and / or the second retrieval result, and the first object is: an object that matches the description information of the object to be retrieved; a retrieval result generation module is used to generate an object retrieval result containing the video retrieval information of the first video and the first object description information.

[0293] It can be seen from the above that when the solution provided in the embodiment of the present application is used to retrieve videos, the retrieval server can not only perform video retrieval in response to video retrieval requests, but also perform video retrieval in response to object retrieval requests. This can provide users with a variety of retrieval functions, thereby broadening the scope of application of the present solution.

[0294] In the technical solution of this application, the operations involved in obtaining, storing, using, processing, transmitting, providing and disclosing user personal information are all carried out with the user's authorization.

[0295] It should be noted that the two-dimensional face images in this embodiment come from a public data set.

[0296] The present application embodiment also provides a client, such as Fig. 9 As shown, including:

[0297] Memory 901, used for storing computer programs;

[0298] The processor 902 is used to execute the program stored in the memory 901, and implements the following steps:

[0299] Get the search time period;

[0300] If there is a first sub-time period from the first time forward in the retrieval time period, a first video retrieval request for searching the first sub-time period is generated, the first video retrieval request is sent to the retrieval server, and a first retrieval result obtained by the retrieval server in response to the first video retrieval request based on the stored video retrieval information is obtained, wherein the video retrieval information is obtained by the retrieval server through inspection of the videos collected by the video acquisition device in each inspection cycle, the first time is: a preset time period from the current moment forward or the end time of the latest inspection cycle that the retrieval server has completed inspection, and the preset time period is greater than the time period of the inspection cycle;

[0301] If there is a second sub-time period after the first time in the retrieval time period, a second video retrieval request for searching the second sub-time period is generated, the second video retrieval request is sent to the video acquisition device, and a second retrieval result fed back by the video acquisition device for the second video retrieval request is obtained.

[0302] Furthermore, the electronic device may further include a communication bus and / or a communication interface, and the processor 902, the communication interface, and the memory 901 communicate with each other via the communication bus.

[0303] The present application also provides a server, such as Fig.10 As shown, including:

[0304] Memory 1001, used for storing computer programs;

[0305] The processor 1002 is used to implement the following steps when executing the program stored in the memory 1001:

[0306] In response to the video inspection indication, obtaining video retrieval information of the video captured by the video acquisition device within the inspection period indicated by the video inspection indication, and storing the obtained video retrieval information;

[0307] In response to a first video retrieval request from a client, based on the stored video retrieval information, a video satisfying the first video retrieval request is retrieved to obtain a first retrieval result of the retrieved video, wherein the first video retrieval request is: a first sub-time period in the retrieval time period of the client starting from a first time forward, the first time being: the end time of the latest inspection cycle that has completed the inspection or a preset time period forward from the moment when the client obtains the retrieval time period or the time when the retrieval server last retrieved the video collected by the video acquisition device, and the preset time period is greater than the time period of the inspection cycle;

[0308] The first search result is used as the search result to be sent, and the search result to be sent is sent to the client.

[0309] Furthermore, the electronic device may further include a communication bus and / or a communication interface, and the processor 1002, the communication interface, and the memory 1001 communicate with each other via the communication bus.

[0310] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0311] The communication interface is used for communication between the above electronic device and other devices.

[0312] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0313] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0314] In another embodiment provided in the present application, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned video retrieval methods are implemented.

[0315] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute any one of the video retrieval methods in the above embodiments.

[0316] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a solid-state hard disk (SSD), etc.

[0317] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0318] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, client, server, readable storage medium, and computer program product embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0319] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. A video retrieval method, characterized in that: Applied to a client, the method comprises: Get the search time period; If there is a first sub-time period from the first time forward in the retrieval time period, a first video retrieval request for searching the first sub-time period is generated, the first video retrieval request is sent to the retrieval server, and a first retrieval result obtained by the retrieval server in response to the first video retrieval request based on the stored video retrieval information is obtained, wherein the video retrieval information is obtained by the retrieval server through inspection of the videos collected by the video acquisition device in each inspection cycle, the first time is: a preset time period from the current moment forward or the end time of the latest inspection cycle that the retrieval server has completed inspection, and the preset time period is greater than the time period of the inspection cycle; If there is a second sub-time period after the first time period in the retrieval time period, a second video retrieval request for searching the second sub-time period is generated, the second video retrieval request is sent to the video acquisition device, and a second retrieval result fed back by the video acquisition device for the second video retrieval request is obtained; The method further comprises: When the first search result is obtained, displaying the first search result and video auxiliary information generated based on the first search result; In the case of obtaining the second search result, displaying the second search result and the video auxiliary information generated based on the second search result; The video auxiliary information includes at least one of the following information: The collection time distribution information of the video corresponding to the search result; Attribute value selection items of objects in the video corresponding to the search results; In the case where the video auxiliary information includes collection period distribution information, after receiving the search result, the client counts the video collection time periods included in each video search information in the search result, generates collection period distribution information according to the statistically obtained video collection time periods, and displays the collection period distribution information; In the case where the video auxiliary information includes attribute value selection items, after receiving the search results, the client integrates the attribute value distribution of the same type of attributes in the object description information corresponding to each video in the search results, and generates attribute value selection items corresponding to the integrated attribute type; The client integrates the object description information corresponding to the video to obtain the attribute type, and displays the attribute value selection items of the obtained attribute type. When the user selects one of the attribute value selection items, the client displays the attribute value of the attribute type corresponding to the attribute value selection item selected by the user. The user further selects one of the displayed attribute values. The client filters the search results for results containing the attribute value selected by the user, and displays the filtered results. The method further comprises: When the first search result and the second search result are obtained, displaying the search results and the video auxiliary information generated based on the search results in batches according to the order in which the search results are obtained; If the client first receives the first search result fed back by the search server and then receives the second search result fed back by the video acquisition device, the client first displays the first search result and then displays the second search result; If the client first receives the second search result fed back by the video acquisition device and then receives the first search result fed back by the search server, the client first displays the second search result and then displays the first search result; When the client receives one of the first and second search results, the client displays the search result. When the client receives the other search result again, the client displays the other search result.

2. The method according to claim 1, characterized in that The method further comprises: Generate an object retrieval request including description information of the object to be retrieved; Send the object retrieval request to the device to be retrieved, and obtain the object retrieval result generated by the device to be retrieved for the object retrieval request, wherein the object retrieval result includes: video retrieval information of the first video and first object description information of the first object in the stored object description information, the first video is: a video containing the first object retrieved from the second video based on the video retrieval information of the second video, if the device to be retrieved is the retrieval server, then the second video is: a video corresponding to the first retrieval result, if the device to be retrieved is the video acquisition device, then the second video is: a video corresponding to the second retrieval result, and the first object is: an object appearing in the first video and matching the object description information to be retrieved.

3. A video retrieval method, characterized in that: Applied to a search server, the method comprises: In response to the video inspection indication, obtaining video retrieval information of the video captured by the video acquisition device within the inspection period indicated by the video inspection indication, and storing the obtained video retrieval information; In response to a first video retrieval request from a client, based on the stored video retrieval information, a video satisfying the first video retrieval request is retrieved to obtain a first retrieval result of the retrieved video, wherein the first video retrieval request is: a first sub-time period in the retrieval time period of the client starting from a first time forward, the first time being: the end time of the latest inspection cycle that has completed the inspection or a preset time period from the moment when the client obtains the retrieval time period, the preset time period being greater than the time period of the inspection cycle; The first search result is used as the search result to be sent, and the search result to be sent is sent to the client, so that after the client obtains the search result to be sent, the first search result and the video auxiliary information generated based on the first search result are displayed, and when the client also obtains the second search result sent by the video acquisition device, the client displays each search result and the video auxiliary information generated based on each search result in batches according to the order in which each search result is obtained; If the client first receives the first search result fed back by the search server and then receives the second search result fed back by the video acquisition device, the client first displays the first search result and then displays the second search result; If the client first receives the second search result fed back by the video acquisition device and then receives the first search result fed back by the search server, the client first displays the second search result and then displays the first search result; When the client receives one of the first and second search results, the client displays the search result, and when the client receives the other search result, the client displays the other search result; The video auxiliary information includes at least one of the following information: The collection time distribution information of the video corresponding to the search result; Attribute value selection items of objects in the video corresponding to the search results; In the case where the video auxiliary information includes collection period distribution information, after receiving the search result, the client counts the video collection time periods included in each video search information in the search result, generates collection period distribution information according to the statistically obtained video collection time periods, and displays the collection period distribution information; In the case where the video auxiliary information includes attribute value selection items, after receiving the search results, the client integrates the attribute value distribution of the same type of attributes in the object description information corresponding to each video in the search results, and generates attribute value selection items corresponding to the integrated attribute type; The client integrates the object description information corresponding to the video, obtains the attribute type, and displays the attribute value selection items of the obtained attribute type. When the user selects one of the attribute value selection items, the client displays the attribute value of the attribute type corresponding to the attribute value selection item selected by the user. The user further selects one of the displayed attribute values, and the client filters the results containing the attribute value selected by the user in the search results, and displays the filtered results.

4. The method according to claim 3, characterized in that The video retrieval information obtained by storing includes: If the video retrieval information has been stored, then the newly added information in the obtained video retrieval information is stored; If the video retrieval information has not been stored, all the obtained video retrieval information is stored.

5. The method according to claim 4, characterized in that The method further comprises: Based on the obtained video retrieval information, determining invalid retrieval information in the stored video retrieval information; Add an invalidation mark to the invalidation retrieval information or delete the invalidation retrieval information.

6. The method according to claim 3, characterized in that The obtaining of video retrieval information of the video captured by the video capture device within the inspection period indicated by the video inspection indication includes: Retrieving the video collected within the inspection period indicated by the video inspection indication stored in the storage server to obtain video retrieval information, wherein the storage server is used to store the video uploaded by the video acquisition device; and / or The video captured in the inspection period indicated by the video inspection indication and cached by the video acquisition device is retrieved to obtain video retrieval information.

7. The method according to any one of claims 3 to 6, characterized in that: The method further comprises: If no video satisfying the video retrieval request is found based on the stored video retrieval information, sending the video retrieval request to a video acquisition device; A first search result of the video acquisition device searching for the video search request is obtained.

8. The method according to any one of claims 3 to 6, characterized in that: The method further comprises: Receiving a second search result for a second video search request sent by a video acquisition device, wherein the second video search request is a request for video search for a second sub-time period, and the second sub-time period is: a time period in the search time period of the client that is located after the first time period; The second search result is used as the search result to be sent, the search result to be sent is sent to the client, and video search information of the video in the second search result is obtained, and the locally stored video search information is updated based on the obtained video search information.

9. The method according to claim 8, characterized in that In a case where the retrieval results to be sent include the first retrieval result and the second retrieval result, sending the retrieval results to be sent to the client includes: The search results to be sent are sent to the client in batches according to the order in which the search results to be sent are obtained.

10. The method according to any one of claims 3 to 5, characterized in that: The method further comprises: Get object description information; Storing the object description information; The object description information includes at least one of the following information: The video acquisition device performs object detection on the acquired video to obtain the attributes of the object and the description information of the object's behavior; The object behavior description information and object attributes collected by the auxiliary information collection device, wherein the auxiliary information collection device includes: information collection devices other than the video collection device.

11. The method according to claim 8, characterized in that The method further comprises: In response to an object retrieval request including description information of an object to be retrieved, based on the retrieval information of a second video, a first video including a first object is retrieved from the second video, and first object description information of the first object is retrieved from the stored object description information, wherein the second video is: a video corresponding to the first retrieval result and / or the second retrieval result, and the first object is: an object matching the description information of the object to be retrieved; Generate an object retrieval result including the video retrieval information of the first video and the first object description information.

12. A video retrieval device, characterized in that: Applied to a client, the device comprises: A time acquisition module is used to obtain a search time period; A first retrieval module is configured to generate a first video retrieval request for searching a first sub-time period if there is a first sub-time period from the first time forward in the retrieval time period, send the first video retrieval request to a retrieval server, and obtain a first retrieval result obtained by the retrieval server in response to the first video retrieval request based on the stored video retrieval information, wherein the video retrieval information is obtained by the retrieval server inspecting the videos collected by the video acquisition device in each inspection cycle, the first time is a preset time period from the current moment forward or an end time of the latest inspection cycle that the retrieval server has completed inspection, and the preset time period is greater than the time period of the inspection cycle; A second retrieval module is configured to generate a second video retrieval request for searching the second sub-time period if there is a second sub-time period after the first time period in the retrieval time period, send the second video retrieval request to the video acquisition device, and obtain a second retrieval result fed back by the video acquisition device for the second video retrieval request; The device further comprises: a result display module, which is used to display the first search result and the video auxiliary information generated based on the first search result when the first search result is obtained; and to display the second search result and the video auxiliary information generated based on the second search result when the second search result is obtained; wherein the video auxiliary information comprises at least one of the following information: the acquisition time period distribution information of the video corresponding to the search result; and the attribute value selection items of the object in the video corresponding to the search result; In the case where the video auxiliary information includes collection period distribution information, after receiving the search result, the client counts the video collection time periods included in each video search information in the search result, generates collection period distribution information according to the statistically obtained video collection time periods, and displays the collection period distribution information; In the case where the video auxiliary information includes attribute value selection items, after receiving the search results, the client integrates the attribute value distribution of the same type of attributes in the object description information corresponding to each video in the search results, and generates attribute value selection items corresponding to the integrated attribute type; The client integrates the object description information corresponding to the video to obtain the attribute type, and displays the attribute value selection items of the obtained attribute type. When the user selects one of the attribute value selection items, the client displays the attribute value of the attribute type corresponding to the attribute value selection item selected by the user. The user further selects one of the displayed attribute values. The client filters the search results for results containing the attribute value selected by the user, and displays the filtered results. The device further includes: a batch display module, which is used to display each search result and video auxiliary information generated based on each search result in batches according to the order in which each search result is obtained when the first search result and the second search result are obtained; If the client first receives the first search result fed back by the search server and then receives the second search result fed back by the video acquisition device, the client first displays the first search result and then displays the second search result; If the client first receives the second search result fed back by the video acquisition device and then receives the first search result fed back by the search server, the client first displays the second search result and then displays the first search result; When the client receives one of the first and second search results, the client displays the search result. When the client receives the other search result again, the client displays the other search result.

13. The device according to claim 12, characterized in that The device also includes: a request generation module, which is used to generate an object retrieval request containing description information of the object to be retrieved; an object retrieval module, which is used to send the object retrieval request to the device to be retrieved, and obtain the object retrieval result generated by the device to be retrieved for the object retrieval request, wherein the object retrieval result includes: video retrieval information of the first video and first object description information of the first object in the stored object description information, the first video is: a video containing the first object retrieved from the second video based on the video retrieval information of the second video, if the device to be retrieved is the retrieval server, then the second video is: a video corresponding to the first retrieval result, if the device to be retrieved is the video acquisition device, then the second video is: a video corresponding to the second retrieval result, and the first object is: an object appearing in the first video and matching the description information of the object to be retrieved.

14. A video retrieval device, characterized in that: Applied to a search server, the device comprises: An indication response module, used to obtain, in response to a video inspection indication, video retrieval information of a video captured by a video acquisition device within an inspection period indicated by the video inspection indication, and store the obtained video retrieval information; A request response module, used to respond to a first video retrieval request from a client, retrieve videos satisfying the first video retrieval request based on stored video retrieval information, and obtain a first retrieval result of the retrieved video, wherein the first video retrieval request is: a first sub-time period in the retrieval time period of the client starting from a first time forward, the first time being: the end time of the latest inspection cycle that has completed the inspection or a preset time period forward from the moment when the client obtains the retrieval time period or the time when the retrieval server last retrieved the video collected by the video acquisition device, and the preset time period is greater than the time period of the inspection cycle; A result sending module, used to use the first search result as the search result to be sent, and send the search result to be sent to the client, so that after the client obtains the search result to be sent, the first search result and the video auxiliary information generated based on the first search result are displayed, and when the client also obtains the second search result sent by the video acquisition device, the client displays each search result and the video auxiliary information generated based on each search result in batches according to the order in which each search result is obtained; If the client first receives the first search result fed back by the search server and then receives the second search result fed back by the video acquisition device, the client first displays the first search result and then displays the second search result; If the client first receives the second search result fed back by the video acquisition device and then receives the first search result fed back by the search server, the client first displays the second search result and then displays the first search result; When the client receives one of the first and second search results, the client displays the search result, and when the client receives the other search result, the client displays the other search result; The video auxiliary information includes at least one of the following information: The collection time distribution information of the video corresponding to the search result; Attribute value selection items of objects in the video corresponding to the search results; In the case where the video auxiliary information includes collection period distribution information, after receiving the search result, the client counts the video collection time periods included in each video search information in the search result, generates collection period distribution information according to the statistically obtained video collection time periods, and displays the collection period distribution information; In the case where the video auxiliary information includes attribute value selection items, after receiving the search results, the client integrates the attribute value distribution of the same type of attributes in the object description information corresponding to each video in the search results, and generates attribute value selection items corresponding to the integrated attribute type; The client integrates the object description information corresponding to the video, obtains the attribute type, and displays the attribute value selection items of the obtained attribute type. When the user selects one of the attribute value selection items, the client displays the attribute value of the attribute type corresponding to the attribute value selection item selected by the user. The user further selects one of the displayed attribute values, and the client filters the results containing the attribute value selected by the user in the search results, and displays the filtered results.

15. The device according to claim 14, characterized in that The indication response module is specifically used to: if the video retrieval information has been stored, store the newly added information in the obtained video retrieval information; if the video retrieval information has not been stored, store all the obtained video retrieval information; and / or The device further comprises: an information determination module, for determining invalid retrieval information in the stored video retrieval information based on the obtained video retrieval information; an information processing module, for adding an invalidation mark to the invalid retrieval information or deleting the invalid retrieval information; and / or The indication response module is specifically used to retrieve the video collected within the inspection period indicated by the video inspection indication stored in the storage server to obtain video retrieval information, wherein the storage server is used to store the video uploaded by the video acquisition device; and / or The indication response module is specifically used to: retrieve the video captured in the inspection cycle indicated by the video inspection indication and cached by the video acquisition device to obtain video retrieval information; and / or The device further comprises: a request resending module, configured to send the video search request to the video acquisition device if no video satisfying the video search request is found based on the stored video search information; a first result obtaining module, configured to obtain a first search result of the video acquisition device searching for the video search request; and / or The device further includes: a second result obtaining module, configured to receive a second search result for a second video search request sent by a video acquisition device, wherein the second video search request is a request for video search for a second sub-time period, and the second sub-time period is a time period after the first time period in the search time period of the client; a result processing module, configured to use the second search result as a search result to be sent, send the search result to be sent to the client, obtain video search information of the video in the second search result, and update the locally stored video search information based on the obtained video search information; and / or The result sending module is specifically used to: when the search results to be sent include the first search result and the second search result, send the search results to be sent to the client in batches according to the order in which the search results to be sent are obtained; and / or The device further comprises: an information acquisition module for acquiring object description information; an information storage module for storing the object description information, wherein the object description information comprises at least one of the following information: object attributes and object behavior description information obtained by performing object detection on the collected video by the video acquisition device; object behavior description information and object attributes collected by the auxiliary information acquisition device, wherein the auxiliary information acquisition device comprises: information acquisition devices other than the video acquisition device; and / or The device also includes: An information retrieval module is used to respond to an object retrieval request containing description information of an object to be retrieved, retrieve a first video containing a first object from the second video based on the retrieval information of the second video, and retrieve the first object description information of the first object from the stored object description information, wherein the second video is: a video corresponding to the first retrieval result and / or the second retrieval result, and the first object is: an object that matches the description information of the object to be retrieved; a retrieval result generation module is used to generate an object retrieval result containing the video retrieval information of the first video and the first object description information.

16. A client, characterized in that: include: Memory, used to store computer programs; A processor, used to implement the method described in any one of claims 1-2 when executing a program stored in a memory.

17. A server, characterized in that: include: Memory, used to store computer programs; A processor, for implementing any of the methods described in claims 3-11 when executing a program stored in a memory.

18. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1-2 or 3-11 is implemented.

Images