CN109408727B - Intelligent user attention information recommendation method and system based on multidimensional perception data - Google Patents
Intelligent user attention information recommendation method and system based on multidimensional perception data Download PDFInfo
- Publication number
- CN109408727B CN109408727B CN201811407539.3A CN201811407539A CN109408727B CN 109408727 B CN109408727 B CN 109408727B CN 201811407539 A CN201811407539 A CN 201811407539A CN 109408727 B CN109408727 B CN 109408727B
- Authority
- CN
- China
- Prior art keywords
- retrieval
- user
- target object
- information
- records
- 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
Images
Abstract
The invention provides a method and a system for intelligently recommending user attention information based on multidimensional sensing data, wherein the method comprises the following steps: s1, writing multidimensional data collected by front-end equipment into an information recommendation library; s2, recording retrieval information of a user and storing the retrieval information into a data analysis base to form a plurality of retrieval records, wherein each retrieval record comprises a user name, a characteristic value of a retrieval target object, retrieval times and retrieval time; s3, inquiring the retrieval records in the data analysis base according to the user name, sequencing the retrieval records according to the attention degree of the user to the target object in each retrieval record, and taking a part of the retrieval records in the front of the sequencing; and S4, according to the characteristic value of the target object in the selected retrieval record, correlating the related information in the information recommendation library and pushing the related information to the user. The method and the device can push the relevant information of the target object with high user attention in real time, reduce the user operation amount and improve the retrieval efficiency.
Description
Technical Field
The invention relates to the field of smart city management, in particular to a user attention information intelligent recommendation method and system based on multi-dimensional perception data.
Background
Along with the rapid development of the internet of things technology, the construction of smart cities is a necessary trend, more and more public security systems construct an internet of things management and control platform, multi-dimensional sensing data collected by front-end equipment are collected, case handling and investigation have greater and greater dependence on social security points, but the information on the internet of things management and control platform is basically inquired by manual retrieval.
Disclosure of Invention
The invention aims to provide a method and a system for intelligently recommending user attention information based on multidimensional sensing data, and aims to solve the problems that a large amount of public security point location data are searched and inquired manually by a user, the searching speed is slow, and the efficiency is low.
The invention is realized by the following steps:
on one hand, the invention provides a user attention information intelligent recommendation method based on multidimensional perception data, which comprises the following steps:
s1, writing multidimensional data collected by front-end equipment into an information recommendation library;
s2, recording retrieval information of a user and storing the retrieval information into a data analysis base to form a plurality of retrieval records, wherein each retrieval record comprises a user name, a characteristic value of a retrieval target object, retrieval times and retrieval time, the retrieval times are the total times of the user for retrieving the target object, and the retrieval time is the time of the user for retrieving the target object for the last time;
s3, searching the retrieval records in the data analysis base according to the user name, sequencing the retrieval records according to the attention degree of the user to the target object in each retrieval record, and taking a part of the retrieval records in the front of the sequencing;
and S4, according to the characteristic value of the target object in the selected retrieval record, correlating the related information in the information recommendation library and pushing the related information to the user.
Further, in step S1, the multidimensional data collected by the front-end device includes portrait capture data, vehicle capture data, and MAC capture data.
Further, the step S1 further includes:
and analyzing the data acquired by the front-end equipment in real time according to the deployment and control information to generate alarm or abnormal data, and writing the alarm or abnormal data into an information recommendation library.
Further, in step S2, if the search target object is a face object, the feature value is the PERSONID of the face after passing through the face algorithm, if the search target object is a vehicle object, the feature value is the license plate number, and if the search target object is an MAC object, the feature value is the corresponding MAC value.
Further, the sorting the search records according to the attention degree of the user to the target object in each search record in step S3 specifically includes:
s3.1, sorting the retrieval records according to a rule that the retrieval time is from near to far and the retrieval times are in descending order, and acquiring M1 retrieval records which are sorted in the front;
and S3.2, calculating the user attention Q of each target object of the M1 retrieval records obtained in the step S3.1 through an attention analysis model, sorting the M1 retrieval records according to the user attention Q in a descending order, and then taking the M2 retrieval records which are sorted in front.
Further, the attention degree analysis model in step S3.2 is:
wherein D N The difference in the number of days from the current time of the time at which the target object was last retrieved, N N S is a coefficient, which is the number of times of retrieval of the target object.
Further, the information pushed to the user in the step S4 includes snapshot, alarm, and abnormal data information.
On the other hand, the invention also provides a system for intelligently recommending the user attention information based on the multidimensional perception data, which comprises a data writing module, a retrieval record collecting module, a retrieval record sequencing module and an information pushing module;
the data writing module is used for writing the multidimensional data acquired by the front-end equipment into the information recommendation library;
the retrieval record collection module is used for recording retrieval information of a user and storing the retrieval information into a data analysis base to form a plurality of retrieval records, wherein each retrieval record comprises a user name, a characteristic value of a retrieval target object, retrieval times and retrieval time, the retrieval times are the total times of the user for retrieving the target object, and the retrieval time is the time of the user for retrieving the target object last time;
the retrieval record ordering module is used for inquiring retrieval records in the data analysis base according to the user name, ordering the retrieval records according to the attention degree of the user to the target object in each retrieval record, and taking a part of the retrieval records in the front of the ordering;
and the information pushing module is used for associating the related information in the information recommendation library according to the characteristic value of the target object in the selected retrieval record and pushing the related information to the user.
Further, the retrieval record ordering module is specifically configured to:
sorting the retrieval records according to a rule that the retrieval time is from near to far and the retrieval times are descending, and acquiring M1 retrieval records which are sorted in the front;
and calculating the user attention Q of each target object of the M1 retrieval records through an attention analysis model, sorting the M1 retrieval records according to the user attention Q in a descending order, and then taking the M2 retrieval records which are sorted in the front.
Further, the attention analysis model is as follows:
wherein D N Time-to-current time day difference, N, for the last retrieval of the target object N S is a coefficient, which is the number of times of retrieval of the target object.
Compared with the prior art, the invention has the following beneficial effects:
the intelligent recommendation method and system for the user attention information based on the multidimensional sensing data can push the related information of the target object with high user attention in real time, avoid the condition that the user searches one by one, reduce the user operation amount, improve the search efficiency, judge the attention of the target object according to the historical search record of the user, and have strong referential property and high accuracy.
Drawings
Fig. 1 is a flowchart of a method for intelligently recommending user attention information based on multidimensional sensing data according to an embodiment of the present invention;
fig. 2 is a block diagram of an intelligent user attention information recommendation system based on multidimensional sensing data according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a method for intelligently recommending user attention information based on multidimensional sensing data, including the following steps:
s1, writing multidimensional data collected by front-end equipment into an information recommendation library;
s2, recording retrieval information of a user and storing the retrieval information in a data analysis base to form a plurality of retrieval records, wherein each retrieval record comprises a user name, a characteristic value of a retrieval target object, retrieval times and retrieval time, the retrieval times are the total times of the user for retrieving the target object, and the retrieval time is the time of the user for retrieving the target object for the last time;
s3, inquiring the retrieval records in the data analysis base according to the user name, sequencing the retrieval records according to the attention degree of the user to the target object in each retrieval record, and taking a part of the retrieval records in the front of the sequencing;
and S4, according to the characteristic value of the target object in the selected retrieval record, correlating the related information in the information recommendation library and pushing the related information to the user.
According to the technical scheme, the related information of the target object with high user attention can be pushed in real time, the condition that the user searches one by one is avoided, the user operation amount can be reduced, the searching efficiency is improved, the attention of the target object is judged according to the historical searching record of the user, the reference is high, and the accuracy is high.
The above steps will be described in detail below.
In an embodiment, in step S1, the front-end device may be an electronic fence, a WIFI fence, a vehicle gate, and the like deployed in a target area, the target area may be a city or an area of other range, the multidimensional data collected by the front-end device includes portrait capture data, vehicle capture data, MAC capture data, and the like, and the collected data is received and written into the information recommendation library through kafka.
In one embodiment, the step S1 further includes: the data collected by the front-end equipment is analyzed in real time according to the control information to generate alarm or abnormal data, and the alarm or abnormal data is written into the information recommendation library together, so that a user can obtain corresponding alarm or abnormal data during retrieval, and analysis is facilitated.
In one embodiment, in the step S2, when a user searches for a target object for the first time, a target object feature value V is recorded, the search time T, the number of search times N (N = 1), and the user name P is written into the information recommendation library, where if the target object is a face object, the feature value V is a PERSONID of the face after the face passes through a face algorithm, if the target object is a vehicle object, the feature value V is a license plate number, and if the target object is a MAC object, the feature value V is a corresponding MAC value, and the feature value can facilitate distinguishing the target object. When a user searches a target object N +1 times, updating the corresponding N value in the information recommendation library according to the characteristic value V of the search target object and the user name P to be N +1,T and the N +1 time of search.
In an embodiment, the sorting the search records according to the attention of the user to the target object in each search record in step S3 specifically includes:
s3.1, sorting the retrieval records according to a rule that the retrieval time is from near to far and the retrieval times are in descending order, specifically, sorting according to the retrieval time T from near to far, and then sorting according to the retrieval times N in descending order to obtain M1 retrieval records in the front of the order;
and S3.2, calculating the user attention Q of each target object of the M1 retrieval records obtained in the step S3.1 through an attention analysis model, sorting the M1 retrieval records according to the user attention Q in a descending order, and then taking the M2 retrieval records which are sorted at the front, wherein M1 and M2 are natural numbers, M1 is larger than M2, and the rest data as overdue data are not in a pushing considered range.
Further, the attention degree analysis model in step S3.2 is:
wherein D N Time-to-current time day difference, N, for the last retrieval of the target object N The number of searches for the target object, S is a coefficient, and takes a decimal between 0 and 1, preferably 0.6.
According to the embodiment, the target objects with higher user attention can be accurately obtained through two times of sorting and screening, and the calculation workload of the second step can be reduced and the calculation efficiency can be improved through the first screening.
In one embodiment, the information pushed to the user in step S4 includes snapshot, alarm and abnormal data information, and the alarm and abnormal data is pushed to the user, so that the user can know the relevant data condition conveniently, even if useful information is captured.
The above embodiments will be specifically described below by way of examples.
Assume that the following information recommendation libraries exist, including: vehicle snapshot storage:
| license plate number | Time of taking a snapshot | Point location name | Color of car body | Speed per hour of vehicle | ........... |
| a | Time1 | Name1 | Color1 | Speed1 | ........... |
| a | Time2 | Name2 | Color1 | Speed2 | ........... |
| a | Time3 | Name3 | Color1 | Speed3 | ........... |
| b | Time4 | Name4 | Color2 | Speed4 | ........... |
| c | Time5 | Name5 | Color3 | Speed5 | ........... |
Vehicle control alarm bank:
| license plate number | Time of taking a candid photograph | Point location name | Color of car body | Vehicle speed per hour | ........... |
| a | Time1 | Name1 | Color1 | Speed1 | ........... |
| a | Time2 | Name2 | Color1 | Speed2 | ........... |
| a | Time3 | Name3 | Color1 | Speed3 | ........... |
| b | Time4 | Name4 | Color2 | Speed4 | ........... |
| c | Time5 | Name5 | Color3 | Speed5 | ........... |
A face information recommendation library:
| PERSONID | time of taking a snapshot | Sex | Age (age) | ........... |
| ID1 | Time1 | For male | Age1 | ........... |
| ID2 | Time2 | For male | Age2 | ........... |
| ID3 | Time3 | For male | Age3 | ........... |
A face alarm information recommendation library:
| PERSONID | time of alarm | Sex | Age (age) | ........... |
| ID1 | Time1 | For male | Age1 | ........... |
| ID2 | Time2 | For male | Age2 | ........... |
| ID3 | Time3 | For male | Age3 | ........... |
MAC information base:
| MAC | time of acquisition | Field intensity | Site name | ........... |
| Mac1 | Time1 | Power1 | Name1 | ........... |
| Mac2 | Time2 | Power2 | Name2 | ........... |
| Mac3 | Time3 | Power3 | Name3 | ........... |
| Mac4 | Time4 | Power4 | Name4 | ........... |
And (4) MAC alarm information recommendation library:
| MAC | time of alarm | Field intensity | Site name | ........... |
| Mac1 | Time1 | Power1 | Name1 | ........... |
| Mac2 | Time2 | Power2 | Name2 | ........... |
| Mac3 | Time3 | Power3 | Name3 | ........... |
| Mac4 | Time4 | Power4 | Name4 | ........... |
Recording the retrieval record of the user P1 in the data analysis library:
| SEQ | P | V | N | T |
| 1 | P1 | V1 | N1 | T1 |
| 2 | P1 | V2 | N2 | T2 |
| 3 | P1 | V3 | N3 | T3 |
| 4 | P1 | V4 | N4 | T4 |
| 5 | P1 | V5 | N5 | T5 |
| 6 | P1 | V6 | N6 | T6 |
| 7 | P1 | V7 | N7 | T7 |
| 8 | ||||
| ... | ... | ... | ... | ... |
| 88 | P1 | V8 | N8 | T8 |
| 89 | P1 | V9 | N9 | T9 |
| 90 | P1 | V10 | N10 | T10 |
the data are firstly arranged from near to far according to the retrieval time T and then are arranged in a descending order according to the retrieval times N to obtain the first M1 (M1 = 30) pieces of data:
according to the attention model
Calculating attention, and obtaining the first M2 (M2 = 10) pieces of data according to the attention descending order:
| SEQ | P | V | N | T |
| 9 | P1 | V9 | N9 | T9 |
| 2 | P1 | V2 | N2 | T2 |
| 8 | P1 | V8 | N8 | T8 |
| 4 | P1 | V4 | N4 | T4 |
| 23 | P1 | V23 | N23 | T23 |
| 6 | P1 | V6 | N6 | T6 |
| 1 | P1 | V1 | N1 | T1 |
| 20 | P1 | V20 | N20 | T20 |
| 16 | P1 | V16 | N16 | T16 |
| 7 | P1 | V7 | N7 | T7 |
and finally, respectively associating the license plate number in the vehicle information recommendation library and the vehicle alarm information recommendation library in the information recommendation library, the PERSIONID in the face information recommendation library and the face alarm information recommendation library, and the recommendation information corresponding to the MAC query in the MAC information recommendation library and the MAC alarm information recommendation library by using the characteristic value V in the result, and pushing the recommendation information to the user.
Based on the same inventive concept, the invention also provides a system for intelligently recommending the user attention information based on the multidimensional sensing data, and as the problem solving principle of the system is similar to that of the method for intelligently recommending the user attention information based on the multidimensional sensing data in the embodiment, the implementation of the system can refer to the implementation of the method, and repeated parts are not repeated.
As shown in fig. 2, the system for intelligently recommending user attention information based on multidimensional sensing data according to an embodiment of the present invention is configured to execute the foregoing method embodiment, and includes a data writing module 11, a retrieval record collecting module 12, a retrieval record sorting module 13, and an information pushing module 14.
The data writing module 11 is configured to write multidimensional data acquired by the front-end device into an information recommendation library;
the retrieval record collection module 12 is configured to record retrieval information of a user and store the retrieval information in a data analysis library to form a plurality of retrieval records, where each retrieval record includes a user name, a feature value of a retrieval target object, retrieval times and retrieval time, where the retrieval times are total times for the user to retrieve the target object, and the retrieval time is the time for the user to retrieve the target object last time;
the retrieval record sorting module 13 is configured to query the retrieval records in the data analysis library according to the user name, sort the retrieval records according to the attention of the user to the target object in each retrieval record, and take a part of the retrieval records sorted in the front;
the information pushing module 14 is configured to associate the relevant information in the information recommendation library according to the feature value of the target object in the selected retrieval record, and push the associated information to the user.
In one embodiment, the multi-dimensional data collected by the front-end device includes portrait capture data, vehicle capture data, and MAC capture data.
Preferably, the data writing module 11 is further configured to analyze data collected by the front-end device in real time according to the deployment and control information to generate alarm or abnormal data, and write the alarm or abnormal data into the information recommendation library together.
In one embodiment, if the search target object is a face object, the feature value is PERSONID after the face passes through a face algorithm, if the search target object is a vehicle object, the feature value is a license plate number, and if the search target object is an MAC object, the feature value is a corresponding MAC value.
In an embodiment, the retrieval record sorting module 13 is specifically configured to:
sorting the retrieval records according to a rule that the retrieval time is from near to far and the retrieval times are descending, and acquiring M1 retrieval records which are sorted in the front;
and calculating the user attention Q of each target object of the M1 search records through an attention analysis model, sorting the M1 search records according to the user attention Q in a descending order, and then taking the M2 search records which are sorted in the front.
Further, the attention analysis model is as follows:
wherein D N Time-to-current time day difference, N, for the last retrieval of the target object N S is a coefficient, which is the number of times of retrieval of the target object.
In one embodiment, the information pushed to the user by the information pushing module 14 includes snapshot, alarm and abnormal data information.
Those of ordinary skill in the art will appreciate that all or part of the steps of the various methods of the embodiments may be performed by associated hardware as instructed by a program, which may be stored on a computer-readable storage medium, which may include: a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic or optical disk, or the like.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (6)
1. A user attention information intelligent recommendation method based on multidimensional perception data is characterized by comprising the following steps:
s1, writing multidimensional data collected by front-end equipment into an information recommendation library;
s2, recording retrieval information of a user and storing the retrieval information into a data analysis base to form a plurality of retrieval records, wherein each retrieval record comprises a user name, a characteristic value of a retrieval target object, retrieval times and retrieval time, the retrieval times are the total times of the user for retrieving the target object, and the retrieval time is the time of the user for retrieving the target object for the last time;
s3, inquiring the retrieval records in the data analysis base according to the user name, sequencing the retrieval records according to the attention degree of the user to the target object in each retrieval record, and taking a part of the retrieval records in the front of the sequencing;
the step S3 of sorting the search records according to the attention of the user to the target object in each search record specifically includes:
s3.1, sorting the retrieval records according to a rule that the retrieval time is from near to far and the retrieval times are in descending order, and acquiring M1 retrieval records in the front of the sorting;
s3.2, calculating the user attention Q of each target object of the M1 retrieval records obtained in the step S3.1 through an attention analysis model, sorting the M1 retrieval records according to the user attention Q in a descending order, and then taking the M2 retrieval records which are sorted in front;
the attention degree analysis model in the step S3.2 is as follows:
wherein D N Time-to-current time day difference, N, for the last retrieval of the target object N The retrieval times of the target object are set, and S is a coefficient;
and S4, according to the characteristic value of the target object in the selected retrieval record, correlating the related information in the information recommendation library and pushing the related information to the user.
2. The intelligent recommendation method for user attention information based on multi-dimensional perception data as claimed in claim 1, wherein: in the step S1, the multidimensional data collected by the front-end device includes portrait capture data, vehicle capture data, and MAC capture data.
3. The method for intelligently recommending user attention information based on multidimensional perception data according to claim 1, wherein said step S1 further comprises:
and analyzing the data collected by the front-end equipment in real time according to the deployment and control information to generate alarm or abnormal data, and writing the alarm or abnormal data into the information recommendation library.
4. The intelligent recommendation method for user attention information based on multi-dimensional perception data as claimed in claim 1, wherein: in step S2, if the retrieval target object is a face object, the feature value is the PERSONID of the face after passing through the face algorithm, if the retrieval target object is a vehicle object, the feature value is the license plate number, and if the retrieval target object is an MAC object, the feature value is the corresponding MAC value.
5. The intelligent recommendation method for user attention information based on multi-dimensional perception data as claimed in claim 1, wherein: the information pushed to the user in the step S4 includes snapshot, alarm and abnormal data information.
6. A user attention information intelligent recommendation system based on multidimensional perception data is characterized in that: the system comprises a data writing module, a retrieval record collecting module, a retrieval record sequencing module and an information pushing module;
the data writing module is used for writing the multidimensional data acquired by the front-end equipment into the information recommendation library;
the retrieval record collection module is used for recording retrieval information of a user and storing the retrieval information into a data analysis base to form a plurality of retrieval records, wherein each retrieval record comprises a user name, a characteristic value of a retrieval target object, retrieval times and retrieval time, the retrieval times are the total times of the user for retrieving the target object, and the retrieval time is the time of the user for retrieving the target object last time;
the retrieval record ordering module is used for inquiring retrieval records in the data analysis base according to the user name, ordering the retrieval records according to the attention degree of the user to the target object in each retrieval record, and taking a part of the retrieval records in the front of the ordering;
the retrieval record ordering module is specifically configured to:
sorting the retrieval records according to a rule that the retrieval time is from near to far and the retrieval times are descending, and acquiring M1 retrieval records which are sorted in the front;
calculating the user attention Q of each target object of the M1 retrieval records through an attention analysis model, sorting the M1 retrieval records according to the user attention Q in a descending order, and then taking M2 retrieval records which are sorted in the front;
the attention degree analysis model is as follows:
wherein D N Time-to-current time day difference, N, for the last retrieval of the target object N The retrieval times of the target object are S is a coefficient;
and the information pushing module is used for associating the related information in the information recommendation library according to the characteristic value of the target object in the selected retrieval record and pushing the related information to the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811407539.3A CN109408727B (en) | 2018-11-23 | 2018-11-23 | Intelligent user attention information recommendation method and system based on multidimensional perception data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811407539.3A CN109408727B (en) | 2018-11-23 | 2018-11-23 | Intelligent user attention information recommendation method and system based on multidimensional perception data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109408727A CN109408727A (en) | 2019-03-01 |
| CN109408727B true CN109408727B (en) | 2022-11-22 |
Family
ID=65455308
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811407539.3A Active CN109408727B (en) | 2018-11-23 | 2018-11-23 | Intelligent user attention information recommendation method and system based on multidimensional perception data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109408727B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111800446B (en) * | 2019-04-12 | 2023-11-07 | 北京沃东天骏信息技术有限公司 | Scheduling processing method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102693223A (en) * | 2011-03-21 | 2012-09-26 | 潘燕辉 | Search method |
| CN105868332A (en) * | 2016-03-28 | 2016-08-17 | 百度在线网络技术（北京）有限公司 | hot topic recommendation method and device |
| CN106301866A (en) * | 2015-05-12 | 2017-01-04 | 杭州海康威视数字技术股份有限公司 | The statistical method of destination object and device |
-
2018
- 2018-11-23 CN CN201811407539.3A patent/CN109408727B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102693223A (en) * | 2011-03-21 | 2012-09-26 | 潘燕辉 | Search method |
| CN106301866A (en) * | 2015-05-12 | 2017-01-04 | 杭州海康威视数字技术股份有限公司 | The statistical method of destination object and device |
| CN105868332A (en) * | 2016-03-28 | 2016-08-17 | 百度在线网络技术（北京）有限公司 | hot topic recommendation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109408727A (en) | 2019-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107180056B (en) | Method and device for matching segments in video | |
| JP2010537585A (en) | Detect and classify matches between time-based media | |
| US9773058B2 (en) | Methods and systems for arranging and searching a database of media content recordings | |
| US9390170B2 (en) | Methods and systems for arranging and searching a database of media content recordings | |
| CN110737821B (en) | Similar event query method, device, storage medium and terminal equipment | |
| CN110110325B (en) | Repeated case searching method and device and computer readable storage medium | |
| Al-asadi et al. | Object based image retrieval using enhanced SURF | |
| CN111368867B (en) | File classifying method and system and computer readable storage medium | |
| CN109408727B (en) | Intelligent user attention information recommendation method and system based on multidimensional perception data | |
| CN106959960B (en) | Data acquisition method and device | |
| CN109828991B (en) | Query ordering method, device, equipment and storage medium under multi-space-time condition | |
| CN110876090B (en) | Video abstract playback method and device, electronic equipment and readable storage medium | |
| CN112131215B (en) | Bottom-up database information acquisition method and device | |
| CN113139379B (en) | Information identification method and system | |
| US11429616B2 (en) | Data recording and analysis system | |
| CN110795425B (en) | Customs data cleaning and merging method, device, equipment and medium | |
| CN107273389A (en) | The querying method and device of trial video | |
| CN114911685A (en) | Sensitive information marking method, device, equipment and computer readable storage medium | |
| Danisch et al. | Unfolding ego-centered community structures with “a similarity approach” | |
| Liu et al. | A computationally efficient algorithm for large scale near-duplicate video detection | |
| Robles et al. | Towards a content-based video retrieval system using wavelet-based signatures | |
| CN111191119A (en) | Neural network-based scientific and technological achievement self-learning method and device | |
| CN111666432B (en) | Image storage method, device and equipment and storage medium | |
| CN110765263B (en) | Display method and device for search cases | |
| US10585934B2 (en) | Method and system for populating a concept database with respect to user identifiers |
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 | ||
| CB02 | Change of applicant information |
Address after: 430074 No. 546, Luoyu Road, Donghu New Technology Development Zone, Wuhan City, Hubei Province Applicant after: Wuhan Zhongzhi Digital Technology Co.,Ltd. Address before: 430074, No. 88, postal academy road, Hongshan District, Hubei, Wuhan Applicant before: WUHAN FIBERHOME DIGITAL TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221010 Address after: 430074, No. 88, postal academy road, Hongshan District, Hubei, Wuhan Applicant after: Wuhan Fiberhome Zhongzhi Software Technology Co.,Ltd. Address before: 430074 No. 546, Luoyu Road, Donghu New Technology Development Zone, Wuhan City, Hubei Province Applicant before: Wuhan Zhongzhi Digital Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |