CN114201643B - Video stream channel wind control method, device and computer readable storage medium - Google Patents
Video stream channel wind control method, device and computer readable storage medium Download PDFInfo
- Publication number
- CN114201643B CN114201643B CN202210148692.9A CN202210148692A CN114201643B CN 114201643 B CN114201643 B CN 114201643B CN 202210148692 A CN202210148692 A CN 202210148692A CN 114201643 B CN114201643 B CN 114201643B
- Authority
- CN
- China
- Prior art keywords
- video
- characteristic value
- playback
- verification
- attribute information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012795 verification Methods 0.000 claims abstract description 44
- 238000009432 framing Methods 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims description 22
- 238000013507 mapping Methods 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 5
- 230000001276 controlling effect Effects 0.000 abstract description 7
- 230000002596 correlated effect Effects 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 230000006399 behavior Effects 0.000 description 7
- 230000000875 corresponding effect Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 238000013475 authorization Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002427 irreversible effect Effects 0.000 description 2
- 241000282412 Homo Species 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
- G06F16/784—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content the detected or recognised objects being people
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Library & Information Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The invention discloses a method, equipment and a computer readable storage medium for controlling the wind of a video stream channel, wherein the method comprises the following steps: after a video searching task is received, obtaining an incremental video, and framing the incremental video into video pictures; acquiring attribute information of the video picture, and converting the video picture into a characteristic value to be selected; storing the attribute information and the characteristic value to be selected in a preset characteristic value database in a correlated manner; converting the verification photos in the video searching task into verification characteristic values, and comparing the verification characteristic values in the characteristic value database to obtain target characteristic values; and acquiring target attribute information associated with the target characteristic value, and generating a visit record according to the target attribute information. The invention realizes the technical effect of improving the channel wind control efficiency.
Description
Technical Field
The present invention relates to the field of channel wind control, and in particular, to a method and apparatus for controlling a video stream channel wind, and a computer-readable storage medium.
Background
In the real estate industry, channel trading refers to trading between a purchasing customer and a real estate developer through an intermediary. Channel trading is high in developer's total volume, and therefore, the developer's brokerage costs are high. On the other hand, when a naturally visited customer and an intermediary communicate privately, the intermediary and the customer share a commission frequently occurs.
Generally, the time interval for each node may be in units of months or quarters, from the customer purchasing the house to the point of the building, to the final deal, and to the financial and auditor determining whether to issue the commission. The developer needs to obtain the possible first visit time of the house-purchasing client by means of the memory of the staff at the building, and inquires the monitoring video at the building to determine whether the fraud behavior exists in the channel transaction. Therefore, the channel wind control is carried out by means of the memory of staff at the building sales places, and the efficiency is extremely low.
Disclosure of Invention
The invention mainly aims to provide a method and equipment for controlling the wind of a video stream channel and a computer readable storage medium, aiming at solving the problem of low wind control efficiency of the channel.
In order to achieve the above object, the present invention provides a method for controlling a video stream channel, comprising:
after a video searching task is received, obtaining an incremental video, and framing the incremental video into video pictures;
acquiring attribute information of the video picture, and converting the video picture into a characteristic value to be selected;
storing the attribute information and the characteristic value to be selected in a preset characteristic value database in a correlated manner;
converting the verification photos in the video searching task into verification characteristic values, and comparing the verification characteristic values in the characteristic value database to obtain target characteristic values;
and acquiring target attribute information associated with the target characteristic value, and generating an access record according to the target attribute information.
Optionally, after receiving the video search task, the step of obtaining the incremental video includes:
after receiving a video searching task, acquiring a playback video analysis schedule in the characteristic value database;
and connecting a preset network video recorder, and taking the analysis time in the playback video analysis schedule as the starting time to obtain the incremental video in the network video recorder.
Optionally, after the step of obtaining an incremental video after receiving the video searching task and framing the incremental video into a video picture, the method further includes:
and taking the end time of the incremental video as a new resolution time to update the playback video resolution schedule.
Optionally, the step of obtaining the attribute information of the video picture and converting the video picture into the feature value to be selected includes:
acquiring playback time and playback video file name of the video picture in the incremental video;
and modeling the video picture through a preset modeling algorithm, and converting the video picture into a characteristic value to be selected.
Optionally, the step of storing the attribute information and the to-be-selected feature value in a preset feature value database in an associated manner includes:
and establishing a mapping relation between the attribute information and the characteristic values to be selected, and storing the attribute information and the characteristic values to be selected into a playback video mapping relation table in the characteristic value database.
Optionally, the step of converting the check picture in the video search task into a check feature value, and comparing the check feature value with the feature value database according to the check feature value to obtain a target feature value includes:
obtaining a check photo in the video searching task, and carrying out modeling processing on the check photo through the modeling algorithm to generate a check characteristic value;
and comparing the verification characteristic value with a characteristic value to be selected in a characteristic value database, and screening out a target characteristic value which is higher than a preset similarity threshold value in the characteristic value to be selected.
Optionally, the step of acquiring target attribute information associated with the target feature value and generating an access record according to the target attribute information includes:
searching target attribute information associated with the target characteristic value in the characteristic value database according to the target characteristic value;
acquiring a playback video according to the playback video file name, and intercepting visited videos in the playback video within a period of time before and after the playback time;
and performing mosaic processing on the visiting video, taking the visiting video after mosaic processing as a video to be reviewed, associating the playback time with the video to be reviewed, and generating a visiting record.
Optionally, after the step of obtaining the target attribute information associated with the target feature value and generating the visit record according to the target attribute information, the method further includes:
and uploading the visit record to a preset cloud server to complete the video searching task and receive a new video searching task.
In addition, to achieve the above object, the present invention also provides an electronic device including: a memory, a processor, and a video stream channel wind control program stored on the memory and executable on the processor, the video stream channel wind control program configured to implement the steps of the video stream channel wind control method as described above.
Furthermore, to achieve the above object, the present invention also provides a computer readable storage medium having stored thereon a video stream channel wind control program, which when executed by a processor, implements the steps of the video stream channel wind control method as described above.
After receiving a video searching task, obtaining an incremental video, framing the incremental video, processing the incremental video to avoid repeated operation, reducing the performance pressure of hardware, obtaining the attribute information of a video picture, converting the video picture into a feature value to be selected, storing the feature value to be selected and the attribute information into a feature value database in an associated manner, storing the feature value information by using the feature value database to improve the safety of face data, converting a check photo in the video searching task into a check feature value, searching in the feature value database according to the check feature value to obtain a target feature value, searching through the feature value database to shorten the searching time, obtaining target attribute information associated with the target feature value, generating a visiting record according to the target attribute information, wherein the visiting record can be used as a basis for judging whether fraud and fraud behaviors exist in a transaction channel by a case field auditor not, by analyzing the incremental video and searching in the characteristic value database, the channel wind control period is shortened, and the channel wind control efficiency is improved.
Drawings
Fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a video stream channel wind control method according to a first embodiment of the present invention;
FIG. 3 is a flowchart illustrating a second embodiment of a method for controlling a channel of a video stream according to the present invention;
FIG. 4 is a flowchart illustrating a video stream channel scheduling method according to a third embodiment of the present invention;
fig. 5 is a flowchart illustrating a video stream channel wind control method according to a fourth embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In general, techniques related to channel scheduling may require the use of facial information of unauthorized clients. For example, an intelligent face snapshot camera with a face recognition function is installed in a building selling place, the camera can automatically recognize that a person passes under a lens, the face part of a visiting client can be extracted in real time, and pictures containing face information of the client and snapshot time are transmitted to a local intelligent analysis server. When the flow of people at the building is large, some customers may not successfully obtain the approval authorization, and at this time, the snapshot images of the customers need to be deleted from the cloud, which is tedious in process.
The main technical scheme of the invention is as follows: after a video searching task is received, obtaining an incremental video, and framing the incremental video into video pictures; acquiring attribute information of the video picture, and converting the video picture into a characteristic value to be selected; storing the attribute information and the characteristic value to be selected in a preset characteristic value database in a correlated manner; converting the verification photos in the video searching task into verification characteristic values, and comparing the verification characteristic values in the characteristic value database to obtain target characteristic values; and acquiring target attribute information associated with the target characteristic value, and generating an access record according to the target attribute information.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the electronic device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to implement connection communication among these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001 described previously.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a video stream channel-scheduling program.
In the electronic device shown in fig. 1, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the electronic device of the present invention may be disposed in the electronic device, and the electronic device calls the video stream channel wind control program stored in the memory 1005 through the processor 1001 and executes the following steps:
after a video searching task is received, obtaining an incremental video, and framing the incremental video into video pictures;
acquiring attribute information of the video picture, and converting the video picture into a characteristic value to be selected;
storing the attribute information and the characteristic value to be selected in a preset characteristic value database in a correlated manner;
converting the verification photos in the video searching task into verification characteristic values, and comparing the verification characteristic values in the characteristic value database to obtain target characteristic values;
and acquiring target attribute information associated with the target characteristic value, and generating an access record according to the target attribute information.
In an embodiment, the electronic device, through the processor 1001 calling the video stream channel scheduling program stored in the memory 1005, may further perform the following steps:
after receiving a video searching task, acquiring a playback video analysis schedule in the characteristic value database;
and connecting a preset network video recorder, and taking the analysis time in the playback video analysis schedule as the starting time to obtain the incremental video in the network video recorder.
In an embodiment, the electronic device, through the processor 1001 calling the video stream channel scheduling program stored in the memory 1005, may further perform the following steps:
and taking the end time of the incremental video as a new resolution time to update the playback video resolution schedule.
In an embodiment, the electronic device, by calling the video stream channel scheduling program stored in the memory 1005 through the processor 1001, may further perform the following steps:
acquiring playback time and playback video file name of the video picture in the incremental video;
and modeling the video picture through a preset modeling algorithm, and converting the video picture into a characteristic value to be selected.
In an embodiment, the electronic device, through the processor 1001 calling the video stream channel scheduling program stored in the memory 1005, may further perform the following steps:
and establishing a mapping relation between the attribute information and the characteristic values to be selected, and storing the attribute information and the characteristic values to be selected into a playback video mapping relation table in the characteristic value database.
In an embodiment, the electronic device, through the processor 1001 calling the video stream channel scheduling program stored in the memory 1005, may further perform the following steps:
obtaining a verification photo in the video searching task, and carrying out modeling processing on the verification photo through the modeling algorithm to generate a verification characteristic value;
and comparing the verification characteristic value with a characteristic value to be selected in a characteristic value database, and screening out a target characteristic value higher than a preset similarity threshold value in the characteristic value to be selected.
In an embodiment, the electronic device, through the processor 1001 calling the video stream channel scheduling program stored in the memory 1005, may further perform the following steps:
searching target attribute information associated with the target characteristic value in the characteristic value database according to the target characteristic value;
acquiring a playback video according to the playback video file name, and intercepting visited videos in the playback video within a period of time before and after the playback time;
and performing mosaic processing on the visiting video, taking the visiting video after mosaic processing as a video to be reviewed, associating the playback time with the video to be reviewed, and generating a visiting record.
In an embodiment, the electronic device, through the processor 1001 calling the video stream channel scheduling program stored in the memory 1005, may further perform the following steps:
and uploading the visit record to a preset cloud server to complete the video searching task and receive a new video searching task.
An embodiment of the present invention provides a method for controlling a video stream channel, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the method for controlling a video stream channel according to the present invention.
In this embodiment, the video stream channel wind control method includes:
step S10, after receiving the video searching task, obtaining an incremental video, and framing the incremental video into video pictures;
when the house purchasing transaction is achieved at the house selling place, the house selling place can acquire the identity card information and the face information of the house purchasing client through the people-card all-in-one machine so as to check the real identity of the house purchasing client. The identity card information and the face information can be uploaded to a cloud server to be stored. If the house purchasing client achieves the transaction in a channel mode, a task of searching videos by using the check photos of the house purchasing client can be established by the cloud server so as to carry out wind control judgment on the transaction behaviors of the channel.
In the building selling places, such as gates, sand tables, negotiation areas and other areas, common security cameras can be installed to collect monitoring videos. The common security camera does not have the face recognition function and can not collect the face information of the house purchasing client.
The incremental video may be the monitoring video in the period in which the time when the previous analysis is finished is the start time and the time when the video searching task is received at this time is the end time. For example, the recording time of the full-volume surveillance video is from 1/2021/2/15/2021, the local server receives the video searching task at 2/15/2021, the last analysis end time is from 2/1/2021, and then the incremental video is the surveillance video from 2/1/2021/2/15/2021.
Typically, a sales floor is after opening a sales floor and may be subject to one or more peak periods of transaction. When the video is in the peak period of the transaction, the time interval between the incremental videos is shortened, so that the hardware performance pressure for unframing the incremental videos is small.
Step S20, acquiring attribute information of the video picture, and performing face analysis on the video picture to obtain a feature value to be selected;
the video picture is obtained by frame splitting of the incremental video, so that the video picture and the incremental video have an association relation. And obtaining the attribute information of the video picture through the association relationship between the video picture and the incremental video. A human face may be included in the video picture. And the video picture is subjected to face analysis, and the face picture is converted into an irreversible characteristic value to be selected, so that the privacy information of a client can be protected.
Step S30, storing the attribute information and the characteristic value to be selected in a preset characteristic value database in a correlated manner;
the characteristic value to be selected is generated by converting the video picture, so that the incidence relation between the attribute information of the video picture and the characteristic value to be selected can be established, the attribute information and the characteristic value to be selected are stored in the characteristic value database, and the video picture cannot be stored. Specifically, the characteristic value database may be preset in a local server of a machine room at a building. The characteristic value data has sensitivity as one of the traffic data. The characteristic value data is stored locally, so that the isolation of the characteristic value data can be enhanced, and the network security and the physical security of the characteristic value data are improved. When the floors of the building sales places are sold and the channel wind control work is finished, the developers can format or seal the local server in the machine room of the building sales places, namely the storage of the characteristic value data is independently controllable for the developers.
Step S40, converting the verification photos in the video searching task into verification characteristic values, and comparing the verification characteristic values in the characteristic value database to obtain target characteristic values;
the video searching task comprises a check photo of the house-buying client, the check photo comprises face information of the house-buying client, the check photo can be converted into a check characteristic value, and the check characteristic value is compared with a characteristic value to be selected in the characteristic value database. Before the comparison, a comparison condition may be set, and the comparison result satisfying the comparison condition may be a plurality of target feature values.
Step S50, acquiring target attribute information associated with the target characteristic value, and generating an access record according to the target attribute information.
The target characteristic value is a candidate characteristic value meeting the comparison condition, so that target attribute information associated with the target characteristic value in the characteristic value database can be acquired according to the target characteristic value. And acquiring an incremental video corresponding to the video picture according to the target attribute information, processing a part related to the target characteristic value in the incremental video, and generating a visiting record of the house purchasing client.
In this embodiment, after receiving a video search task, obtaining an incremental video, framing the incremental video into a video picture, parsing the incremental video through the video picture, obtaining attribute information of the video picture, converting the video picture into a feature value to be selected, storing the attribute information and the feature value to be selected in a related manner in a preset feature value database, converting a check photo in the video search task into a check feature value, comparing the check feature value in the feature value database to obtain a target feature value, obtaining target attribute information related to the target feature value, generating a visit record according to the target attribute information, wherein the visit record can be used as a visit certificate of a customer in a house, and is used as a basis for judging whether fraud behaviors exist in channel transactions, obtaining the feature value by parsing the incremental video, and then performing feature value comparison to obtain a visit record of the customer, the characteristic value obtained by analyzing the incremental video at each time can be stored in the characteristic value database, and repeated analysis is avoided, so that the period of channel wind control is shortened, and the efficiency of channel wind control is improved.
Further, in a second embodiment of the video stream channel wind control method according to the present invention, referring to fig. 3, the video stream channel wind control method according to the present invention includes:
step S11, after receiving the video searching task, acquiring a playback video analysis schedule in the characteristic value database;
the embodiment adopts an incremental analysis mode to process the monitoring playback video at the building sales places. After the video frame splitting and the conversion of the video pictures into the characteristic values are completed each time, the analysis process of the playback video can be regarded as completed, and the end time of the playback video which is analyzed at this time can be stored in the characteristic value database. Specifically, the above-described end time is saved using a playback video resolution schedule in the feature value database. The content in the playback video parsing schedule may include the end time of the playback video, and may also include the playback video file name and the end time of the playback video.
Step S12, connecting a preset network video recorder, taking the analysis time in the playback video analysis schedule as the starting time, and acquiring the incremental video in the network video recorder;
the Network Video Recorder (NVR) has the function of storing and forwarding Video streams, monitoring videos in common security cameras at a selling building can be pushed to the NVR, and the NVR stores the monitoring videos in a hard disk of the NVR. The NVR can start a human body detection mode when acquiring the monitoring video, namely based on a human body detection algorithm, if the monitoring video picture contains a human body, recording is carried out, and if the monitoring video picture does not contain the human body, recording is not carried out, so that the effect of minimum acquisition is realized, storage resources are saved, and the time for subsequently analyzing the incremental video is saved.
The resolution time in the playback video resolution schedule, i.e., the end time of the playback video for which the resolution has been completed. The playback video may be a surveillance video recorded and stored in the NVR. The incremental video can be regarded as playback video which is not analyzed in the NVR until the video searching task is received at the present time after the last analysis is finished.
And step S13, taking the end time of the incremental video as a new resolution time so as to update the playback video resolution schedule.
In a preferred embodiment, the operation of updating the playback video parsing schedule may be performed after the incremental video parsing is completed. After updating, when the incremental video is analyzed next time, the new analysis time can be used as the starting time to obtain the incremental video.
In this embodiment, the playback video parsing schedule is saved through the playback video parsing schedule, so that the incremental video which is not parsed can be obtained before parsing each time, the efficiency of obtaining the incremental video is improved, the monitoring video is minimally acquired by using a human detection algorithm, and storage resources and time can be saved.
Further, in a third embodiment of the video stream channel wind control method according to the present invention, referring to fig. 4, the video stream channel wind control method according to the present invention includes:
step S21, obtaining the playback time and the playback video file name of the video picture in the incremental video;
video can be viewed as continuously playing pictures, each picture being a frame. The playback time may be the time in the delta video for the number of frames corresponding to the video picture. The playback video file name may be a delta video file name corresponding to the video picture.
Step S22, modeling the video picture through a preset modeling algorithm, and converting the video picture into a feature value to be selected;
the eigenvalues can be considered as an algorithm-specific data format, and the eigenvalue data is poorly readable relative to humans. The feature values obtained by performing the algorithm modeling on the video picture are irreversible, i.e., the video picture cannot be restored by the feature values. The characteristic value data format has no uniform industry standard, the video pictures are completely the same, the obtained characteristic values are different under different modeling algorithms, and the mutual analysis is not supported.
In an embodiment, a preset modeling algorithm may perform face detection on a video picture, and if a face is detected, obtain a position of the face picture in the video picture, extract the face picture in the video picture, and then perform modeling processing on the face picture to generate a feature value to be selected.
In another embodiment, a preset modeling algorithm can directly acquire the position of a face picture in a video picture, perform modeling processing on the face picture, and generate a feature value to be selected.
When the video pictures contain a plurality of face pictures, different face pictures can generate different feature values to be selected. After the video picture is converted into the feature value to be selected, the video picture is not reserved.
Step S23, establishing the mapping relation between the attribute information and the characteristic value to be selected, and storing the attribute information and the characteristic value to be selected into the playback video mapping relation table in the characteristic value database;
the characteristic value to be selected is obtained by converting a face picture, and the face picture is contained in the video picture, so that the mapping relation between the attribute information of the video picture and the characteristic value to be selected can be established. After the incremental video is analyzed each time to obtain the feature value to be selected, the attribute information and the feature value to be selected can be stored in a playback video mapping relation table in an associated mode. Note that the above saving may adopt an additional saving manner, that is, the feature value already saved in the playback video mapping relationship table may be regarded as the candidate feature value. The attribute information may include playback time of the video picture and a playback video file name.
Step S24, obtaining the verification photo in the video searching task, and carrying out modeling processing on the verification photo through the modeling algorithm to generate a verification characteristic value;
when a house purchasing client makes a transaction at a building selling place, the real identity can be verified by using face information under the authorization of the people and card integrated machine at the building selling place. The witness all-in-one machine can upload the verification photos of the house purchasing clients to the cloud server, and the cloud server builds the video searching task by the verification photos.
The same modeling algorithm as that used for processing the video picture can be used for processing the verification picture, and the embodiment for modeling the verification picture can refer to the embodiment for processing the video picture, which is not described herein again.
And step S25, comparing the verification characteristic value with a candidate characteristic value in a characteristic value database, and screening out a target characteristic value which is higher than a preset similarity threshold value in the candidate characteristic value.
When the verification characteristic value is compared with the characteristic value to be selected, the screening range can be determined in a mode of presetting a similarity threshold. For example, if the similarity threshold is set to 95, the probability that the selected target feature value can accurately correspond to the verification photo is high, and omission may also exist. The similarity threshold can be reduced to 90, and if a new target characteristic value is obtained, whether the new target characteristic value can also be correspondingly checked to obtain a more accurate screening result can be checked.
In the embodiment, the video picture is converted into the feature value to be selected through a preset modeling algorithm, the verification picture is converted into the verification feature value, the target feature value is screened out according to the verification feature value, the face data is not used in the screening process, the face picture cannot be restored through the feature value, and the effect of protecting the privacy of a client can be achieved.
Further, in a fourth embodiment of the video stream channel wind control method according to the present invention, referring to fig. 5, the video stream channel wind control method according to the present invention includes:
step S31, according to the target characteristic value, searching the target attribute information associated with the target characteristic value in the playback video mapping relation table;
the screened target feature values may be one or more. According to the target characteristic value, target attribute information in the playback video mapping relation table can be obtained.
Step S32, obtaining a playback video according to the playback video file name, and capturing the visited video in the playback video within a period of time before and after the playback time;
and according to the playback video file name in the target attribute information, the playback video stored in the NVR can be acquired. Each playback video saved by the NVR may have a long time span, and the visiting behavior of the house-purchasing client in the building sales place can be recorded by intercepting part of the video clip. When the video clip is captured, the playback time can be used as a reference, the playback videos of a period of time before and a period of time after the playback time are captured, and the captured playback videos are used as visited videos. The time interval between the previous time and the subsequent time may be consistent, for example, 5 seconds, 10 seconds, or 15 seconds, and the length of the capturing time may affect the integrity of the visiting video record.
Step S33, mosaic processing is carried out on the visiting video, the visiting video after mosaic processing is used as a video to be reviewed, the playback time is associated with the video to be reviewed, and a visiting record is generated;
in one embodiment, the visiting video may be first subjected to a frame dropping process to obtain a video picture. The video pictures comprise face pictures, and the face pictures can correspond to characteristic values to be selected in the characteristic value database. Determining a face picture corresponding to a target characteristic value in each frame of video picture, then carrying out mosaic processing on the face picture corresponding to a non-target characteristic value in each frame of video picture, and finally synthesizing all the mosaic-processed video pictures into a video to be examined. And the playback time corresponding to the target characteristic value in the characteristic value database can be used as the visit time of the house purchasing client, the visit time is associated with the video to be reviewed, and a visit record is generated, so that an auditor can only see the face image of the house purchasing client when viewing the visit record. Thus, the privacy information of irrelevant personnel such as non-house-purchasing clients is further protected.
And step S34, uploading the visit record to a preset cloud server to complete the video searching task and receive a new video searching task.
The video searching task can be constructed by the cloud server, the visiting record of the house purchasing client is obtained by the check photo in the video searching task, and the cloud server receives the visiting record and then can see that the video searching task is completed. When a new house purchasing client makes a deal at the building selling place, a new verification photo is uploaded, and a new video searching task can be received.
In the embodiment, the playback video is obtained according to the screened target characteristic value, the visiting video in the playback video is intercepted, the visiting record is generated, and through the visiting record, an auditor can compare the visiting time with the preparation time of a house-buying client so as to judge whether channel fraud behaviors exist or not, and if the fraud behaviors exist, intermediary commission can be deducted, so that the sale cost is saved.
An embodiment of the present invention further provides an electronic device, where the electronic device includes: a memory, a processor, and a video stream channel wind control program stored on the memory and executable on the processor, the video stream channel wind control program configured to implement the steps of the video stream channel wind control method as described above.
An embodiment of the present invention further provides a computer-readable storage medium, where a video stream channel wind control program is stored on the computer-readable storage medium, and when being executed by a processor, the video stream channel wind control program implements the steps of the video stream channel wind control method described above.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (6)
1. A video stream channel wind control method is characterized by comprising the following steps:
after receiving a video searching task, acquiring a playback video analysis schedule in a preset characteristic value database;
connecting a preset network video recorder, taking the analysis time in the playback video analysis schedule as the starting time, acquiring the incremental video in the network video recorder, and framing the incremental video into video pictures, wherein the incremental video is collected by a common security camera, and the network video recorder records the video based on a human body detection algorithm;
acquiring attribute information of the video picture in the incremental video, wherein the attribute information comprises playback time and a playback video file name;
modeling the video picture through a preset modeling algorithm, and converting the video picture into a feature value to be selected, wherein the video picture is deleted after being converted into the feature value to be selected;
establishing a mapping relation between the attribute information and the characteristic value to be selected, and storing the attribute information and the characteristic value to be selected to a playback video mapping relation table in the characteristic value database;
converting the verification photos in the video searching task into verification characteristic values, and comparing in the characteristic value database according to the verification characteristic values to obtain target characteristic values, wherein when the comparison is carried out in the characteristic value database, the comparison conditions comprise preset similarity threshold values;
searching target attribute information associated with the target characteristic value in the characteristic value database according to the target characteristic value;
acquiring a playback video according to the playback video file name, and capturing the visited video in the playback video within a period of time before and after the playback time;
and performing mosaic processing on the visiting video, taking the visiting video after mosaic processing as a video to be reviewed, associating the playback time with the video to be reviewed, and generating a visiting record.
2. The video streaming channel scheduling method of claim 1, wherein the step of unframing the delta video into video pictures is followed by further comprising:
and taking the end time of the incremental video as a new resolution time to update the playback video resolution schedule.
3. The method as claimed in claim 1, wherein the step of converting the verification photos in the video searching task into verification feature values, and comparing the verification feature values in the feature value database to obtain target feature values comprises:
obtaining a verification photo in the video searching task, and carrying out modeling processing on the verification photo through the modeling algorithm to generate a verification characteristic value;
and comparing the verification characteristic value with a characteristic value to be selected in a characteristic value database, and screening out a target characteristic value which is higher than a preset similarity threshold value in the characteristic value to be selected.
4. The video streaming channel wind control method according to any one of claims 1-3, wherein after the steps of mosaic-processing the visited video, using the mosaic-processed visited video as a pending video, associating the playback time with the pending video, and generating a pending record, further comprising:
and uploading the visit record to a preset cloud server to complete the video searching task and receive a new video searching task.
5. An electronic device, characterized in that the electronic device comprises: a memory, a processor, and a video stream channel wind control program stored on the memory and executable on the processor, the video stream channel wind control program configured to implement the steps of the video stream channel wind control method of any of claims 1 to 4.
6. A computer readable storage medium, characterized in that a video stream channel wind-control program is stored on the computer readable storage medium, which when executed by a processor implements the steps of the video stream channel wind-control method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210148692.9A CN114201643B (en) | 2022-02-18 | 2022-02-18 | Video stream channel wind control method, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210148692.9A CN114201643B (en) | 2022-02-18 | 2022-02-18 | Video stream channel wind control method, device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114201643A CN114201643A (en) | 2022-03-18 |
| CN114201643B true CN114201643B (en) | 2022-06-17 |
Family
ID=80645676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210148692.9A Active CN114201643B (en) | 2022-02-18 | 2022-02-18 | Video stream channel wind control method, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114201643B (en) |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108513094B (en) * | 2017-02-24 | 2020-02-07 | 腾讯科技（深圳）有限公司 | Video monitoring method and device |
| JP7039409B2 (en) * | 2018-07-18 | 2022-03-22 | 株式会社日立製作所 | Video analysis device, person search system and person search method |
| CN110971857B (en) * | 2018-09-28 | 2021-04-27 | 杭州海康威视系统技术有限公司 | Video playback method and device and computer readable storage medium |
| CN110162665B (en) * | 2018-12-28 | 2023-06-16 | 腾讯科技（深圳）有限公司 | Video searching method, computer device and storage medium |
| CN111445252A (en) * | 2019-01-16 | 2020-07-24 | 阿里巴巴集团控股有限公司 | Method, device and equipment for establishing biological feature library |
| CN110321834A (en) * | 2019-06-28 | 2019-10-11 | 深圳市商汤科技有限公司 | A kind of identity determines method and device, storage medium |
| CN110866491B (en) * | 2019-11-13 | 2023-11-24 | 腾讯科技（深圳）有限公司 | Target retrieval method, apparatus, computer-readable storage medium, and computer device |
| CN111612657A (en) * | 2020-05-22 | 2020-09-01 | 创新奇智(重庆)科技有限公司 | Client type identification method and device, electronic equipment and storage medium |
| CN111782835B (en) * | 2020-06-30 | 2024-02-27 | 公安部第三研究所 | Face test database management system and method for face recognition equipment detection |
| CN113821780A (en) * | 2021-09-26 | 2021-12-21 | 深圳市商汤科技有限公司 | Video analysis method and device, electronic equipment and storage medium |
-
2022
- 2022-02-18 CN CN202210148692.9A patent/CN114201643B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114201643A (en) | 2022-03-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105306884B (en) | Monitoring device, monitoring system and monitoring method | |
| JP5747116B1 (en) | Security system | |
| US10372995B2 (en) | System and method for previewing video | |
| KR20200098875A (en) | System and method for providing 3D face recognition | |
| JP5344547B2 (en) | POS terminal device, POS system, attribute information acquisition method, and attribute information acquisition program for acquiring human attribute information | |
| CN109191635B (en) | Passenger judging method and device based on face recognition technology and storage medium | |
| CN114387548A (en) | Video and liveness detection method, system, device, storage medium and program product | |
| US11537639B2 (en) | Re-identification of physical objects in an image background via creation and storage of temporary data objects that link an object to a background | |
| JP6515852B2 (en) | Information processing apparatus, personal identification system, control method thereof, personal identification method, program thereof | |
| CN112183408A (en) | Case image-based customer portrait system and method | |
| CN117412070A (en) | Merchant live time confidence policy operating system | |
| EP3035225B1 (en) | Information processing device, authentication system, authentication method, and program | |
| CN110795980A (en) | Network video-based evasion identification method, equipment, storage medium and device | |
| CN114201643B (en) | Video stream channel wind control method, device and computer readable storage medium | |
| US12046075B2 (en) | Information processing apparatus, information processing method, and program | |
| CN112687044A (en) | Method, system, medium, and apparatus for managing staying person | |
| US11676439B2 (en) | Face authentication system and face authentication method | |
| CN112149451B (en) | Affinity analysis method and device | |
| JP7451170B2 (en) | Information processing device, information processing method and program | |
| CN114038025A (en) | Data processing method, service providing method, device, equipment and storage medium | |
| CN112203049B (en) | Case field old client visiting message notification service system and method | |
| JP7093037B2 (en) | Information processing equipment, face recognition system, its control method and program | |
| EP4296996A1 (en) | Secure search method, secure search system, secure search device, encryption device, searcher terminal, and program | |
| KR102162337B1 (en) | Art auction system using data on visitors and art auction method using the same | |
| CN114066489A (en) | Channel fraud identification method, equipment and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |