CN112256803B - Dynamic data category determination system - Google Patents
Dynamic data category determination system Download PDFInfo
- Publication number
- CN112256803B CN112256803B CN202011131982.XA CN202011131982A CN112256803B CN 112256803 B CN112256803 B CN 112256803B CN 202011131982 A CN202011131982 A CN 202011131982A CN 112256803 B CN112256803 B CN 112256803B
- Authority
- CN
- China
- Prior art keywords
- data
- time
- period
- sampling
- state
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a dynamic data category determination system which comprises a database, M time frames, a processor and a memory, wherein the memory is used for storing computer programs, each time frame corresponds to a unique data type, the M time frames correspond to the M data types, M is a positive integer, the database comprises a first data table, each record in the first data table is periodically sampled data, and fields of the first data table comprise periodically sampled data ID, G time-sampled value pairs and period identification. The method and the device determine the category of the dynamic data based on the plurality of time frames, and improve the efficiency and accuracy of dynamic data classification.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a dynamic data category determining system.
Background
The field of data processing is an important branch of the computer field. In the field of computers, data may include a variety of text data, image data, audio data, video data, and the like, depending on the manner of presentation; depending on the manner of storage, the data may be stored to a database, text file, a file of a particular format (e.g.,. doc/. Gls), etc.; depending on the manner in which the data is formed, static data and dynamic data, particularly data that changes over time, such as temperature data acquired by a temperature sensor, network traffic data acquired by a network device such as a router switch, device LBS data acquired by GPS or beidou, or the like, may be included.
Data classification is an important technology in the field of data processing, static data is classified relatively easily, dynamic data is mostly data that changes with time (particularly data that changes with time at a high frequency), and the influence of the time dimension on the association relationship needs to be considered, so how to classify dynamic data becomes a difficulty in data processing. The existing data classification method, for example, classifies data by matching two curves, but may calculate that the two curves are positively correlated but actually are negatively correlated, so that the classification accuracy is low, and the efficiency is low by fitting dynamic data by using a curve fitting method. Therefore, how to provide an efficient and accurate dynamic data classification technology becomes a technical problem to be solved urgently.
Disclosure of Invention
The invention aims to provide a dynamic data category determining system, which improves the efficiency and accuracy of dynamic data classification.
According to a first aspect of the present invention, there is provided a dynamic data category determining system, including a database, M time frames, a processor and a memory storing a computer program, wherein each time frame corresponds to a unique data type, the M time frames correspond to M data types, M is a positive integer, the database includes a first data table, each record in the first data table is periodically sampled data, and a field of the first data table includes periodically sampled data ID, G time-sampled value pairs and a period identifier, where G is a fixed sampling number in a sampling period;
when executed by a processor, the computer program implementing the steps of:
step S1, receiving a cycle sampling data ID to be tested and a cycle from y-z to y, wherein y and z are positive integers, and y is larger than z;
step S2, retrieving in the periodic sampling data ID of the first data table according to the periodic sampling data ID to be detected, acquiring a record corresponding to the periodic sampling data ID to be detected, retrieving in the period identifier of the record corresponding to the periodic sampling data ID to be detected according to the ith period, and acquiring the sampling value in G corresponding time-sampling value pairs, where i is y-z, y-z +1 … y;
step S3, acquiring sampling data of a to-be-detected period in the ith period according to sampling values in G time-sampling value pairs until the sampling data of the to-be-detected period from the y-z period to the y period are acquired, and forming a to-be-detected period sampling data sequence by the sampling data of the to-be-detected period from the y-z period to the y period according to a time sequence;
step S4, inputting the periodic sampling data sequence to be tested into the jth time frame, where j is 1,2 … M, respectively, matching the periodic sampling data sequence to be tested with the jth time frame, and obtaining the periodic sampling data sequence to be tested and the jth time frameDegree of matching QjUntil the matching degree of the periodic sampling data sequence to be detected and all M time frames is obtained;
and step S5, selecting the maximum matching degree from the obtained M matching degrees, and determining the data type corresponding to the time frame of the maximum matching degree as the data type of the periodic sampling data to be tested.
Compared with the prior art, the invention has obvious advantages and beneficial effects. By means of the technical scheme, the dynamic data category determining system provided by the invention can achieve considerable technical progress and practicability, has wide industrial utilization value and at least has the following advantages:
the method and the device determine the category of the dynamic data based on the plurality of time frames, and improve the efficiency and accuracy of dynamic data classification.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly understood, the present invention may be implemented in accordance with the content of the description, and in order to make the above and other objects, features, and advantages of the present invention more clearly understood, the following preferred embodiments are described in detail with reference to the accompanying drawings.
Drawings
Fig. 1 is a schematic diagram of a dynamic data category determining system according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description will be given to an embodiment of a dynamic data type determination system and its effects according to the present invention with reference to the accompanying drawings and preferred embodiments.
The embodiment of the invention provides a dynamic data category determining system, which comprises a database, M time frames, a processor and a memory, wherein the memory is used for storing a computer program, each time frame corresponds to a unique data type, the M time frames correspond to M data types, M is a positive integer, the database comprises a first data table (table), each record in the first data table is periodic sampling data, a field (field) of the first data table comprises a periodic sampling data ID, G time-sampling value pairs and a period identifier, G is a fixed sampling frequency in a sampling period, and the period identifier is determined according to a time range formed by the earliest time and the latest time in the G time-sampling value pairs;
when executed by a processor, the computer program implementing the steps of:
step S1, receiving a cycle sampling data ID to be tested and a cycle from y-z to y, wherein y and z are positive integers, and y is larger than z;
step S2, retrieving in the periodic sampling data ID of the first data table according to the periodic sampling data ID to be detected, acquiring a record corresponding to the periodic sampling data ID to be detected, retrieving in the period identifier of the record corresponding to the periodic sampling data ID to be detected according to the ith period, and acquiring the sampling value in G corresponding time-sampling value pairs, where i is y-z, y-z +1 … y;
step S3, acquiring sampling data of a to-be-detected period in the ith period according to sampling values in G time-sampling value pairs until the sampling data of the to-be-detected period from the y-z period to the y period are acquired, and forming a to-be-detected period sampling data sequence by the sampling data of the to-be-detected period from the y-z period to the y period according to a time sequence;
step S4, inputting the periodic sampling data sequence to be tested into the jth time frame, where j is 1,2 … M, respectively, matching the periodic sampling data sequence to be tested with the jth time frame, and obtaining a matching degree Q of the periodic sampling data sequence to be tested and the jth time framejUntil the matching degree of the periodic sampling data sequence to be detected and all M time frames is obtained;
and step S5, selecting the maximum matching degree from the obtained M matching degrees, and determining the data type corresponding to the time frame of the maximum matching degree as the data type of the periodic sampling data to be tested.
The system of the embodiment of the invention determines the category of the dynamic data based on a plurality of time frames, and improves the efficiency and accuracy of dynamic data classification.
The system of the invention can be physically realized as a server, and also can be realized as a server group comprising a plurality of servers; all users can input or receive information through terminals, and the terminals comprise desktop computers, notebook computers, tablet computers, mobile phones and the like. Those skilled in the art will appreciate that the model, specification, etc. of the server and the terminal do not affect the scope of the present invention.
As an embodiment, in step S3, the sample data of the cycle to be measured in the i-th cycle is an average value, a median, a maximum value, a minimum value, a last time sample value or a first time sample value of the sample values in the corresponding G time-sample pairs. The mean value may be a weighted mean value, and preferably, the period result data is a weighted mean value of G time-sample values.
As an embodiment, the database further includes a second data table, each record in the second data table is periodically sampled data, and a field of the second data table includes a data type ID, time-sampled value pairs of G key variables, and a period identifier; the M time frames may be built in the system in advance based on the data table, and in particular, when the computer program is executed by a processor, the computer program further realizes:
step S10, constructing each time frame, specifically including:
s101, receiving a data type ID input by a user and a period from a p-q to a p-q, wherein p and q are positive integers, p is larger than q, y-z is larger than p-q, and y is smaller than p;
step S102, retrieving in the data type ID in the second data table according to the data type ID input by the user, and acquiring a record corresponding to the data type ID input by the user;
step 103, searching in records corresponding to the data type ID input by the user according to the r-th period, and acquiring sampling values in time-sampling value pairs of corresponding G key variables, wherein r is p-q, and p-q +1 … p;
step S104, acquiring key variable data of the r-th period according to sampling values in time-sampling value pairs of G key variables until the key variable data from the p-q period to the p-th period are acquired, and forming the key variable data from the p-q period to the p-th period into a time sequence of key variables;
step S105, determining corresponding first state intervals and corresponding second state intervals … & ltth & gt state intervals according to the time sequence of the key variables, wherein N is a positive integer greater than or equal to 2;
step S106, dividing the time from the p-q cycle to the p cycle into different state time periods based on the first state interval and the second state interval …, and obtaining a time frame corresponding to the data type ID input by the user.
Through the steps S101 to S106, a corresponding time frame is constructed based on the time sequence of the key variable of each type of data, so that the time frame is used as a classification basis of the dynamic data, and the accuracy of dynamic data classification is improved.
As an embodiment, in step S104, the critical variable data of the r-th period is a mean value, a median value, a maximum value, a minimum value, a last time sample value or a first time sample value of the time-sample values of the G corresponding critical variables, where the mean value may be a weighted average value, and preferably, the period result data is a weighted average value of the G time-sample values.
It will be appreciated that N may be set according to specific classification parameters, classification requirements, etc., and as an example, N equals 3,
the step S105 includes:
s115, acquiring the mean value and the standard deviation of the time sequence of the key variables;
step S125, determining three state intervals based on the mean value and the standard deviation of the time series of the key variables:
determining a period of time-series values > (mean + W standard deviation) of the key variable as the first state interval,
determining a period of the time series value of the key variable less than or equal to (mean + W standard deviation) as the second state interval,
and determining the period of the time series value < (mean-W standard deviation) of the key variable as the third state interval.
It is understood that the value of W may be specifically set according to parameters such as classification accuracy, and as an embodiment, the value range of W may be set to (0.3,1), and preferably, W is 0.5.
As an example, the step S4 includes:
step S41, inputting the periodic sampling data sequence to be tested into the jth time frame, and acquiring the total number X of all state intervals of the jth time framejThe number x of the nth state intervals with the end value larger than the initial value of the to-be-detected periodic sampling data sequence interval corresponding to all the nth state intervalsnj1The number x of the nth state intervals with the end value smaller than the initial value of the to-be-detected periodic sampling data sequence interval corresponding to all the nth state intervalsnj2；
Step S42, based on Xj、xnj1、xnj2Obtaining the matching degree Q of the matching degree of the periodic sampling data sequence to be detected and the jth time framej：
Wherein, XnjThe number X of all the nth state intervals of the jth time framenj。
In order to further improve the accuracy of data classification, after the maximum matching degree is selected from M matching degrees that can be obtained again, determining whether the data type of the periodic sampling data to be measured is the data type corresponding to the time frame of the maximum matching degree based on the predicted parameter characteristics of the nth state data sequence, as an embodiment, the field of the second data table further includes preset parameter characteristic condition information, and in the step S5, after the maximum matching degree is selected from the M matching degrees that are obtained, the method further includes:
step S51, acquiring a data type ID corresponding to the time frame with the maximum matching degree;
step S52, retrieving the data type ID of the second data table according to the data type ID corresponding to the time frame with the maximum matching degree, and acquiring the preset parameter characteristic condition corresponding to the time frame with the maximum matching degree;
step S53, serially connecting the data of the periodic sampling data sequence to be tested in the time periods corresponding to all the nth state intervals of the time frame with the maximum matching degree to form an nth state data sequence;
step S54, obtaining the corresponding prediction parameter characteristics of the nth state data sequence until all N state data sequences are obtained;
and step S55, judging whether the predicted parameter characteristics of the first state data sequence and the predicted parameter characteristics of the … th state data sequence of the predicted parameter characteristics of the second state data sequence meet the preset parameter characteristic conditions corresponding to the time frame with the maximum matching degree or not, and if so, determining the data type corresponding to the time frame with the maximum matching degree as the data type of the periodic sampling data to be detected.
Still taking N-3 as an example, the preset parameter characteristic condition may be: the prediction parameter characteristic of the first state data sequence, the prediction parameter characteristic of the second state data sequence and the prediction parameter characteristic value of the third state data sequence are sequentially decreased progressively; or the prediction parameter switched to the third state data sequence is minimum. It is understood that other preset parameter characteristic conditions may be set, and different data type IDs may correspond to the same or different preset parameter characteristic conditions.
Although the present invention has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (7)
1. A dynamic data class determination system, characterized in that,
the system comprises a database, M time frames, a processor and a memory, wherein the memory is used for storing computer programs, each time frame corresponds to a unique data type, the M time frames correspond to the M data types, M is a positive integer, the database comprises a first data table, each record in the first data table is periodic sampling data, fields of the first data table comprise periodic sampling data ID, G time-sampling value pairs and a period identifier, and G is the fixed sampling times in a sampling period;
when executed by a processor, the computer program implementing the steps of:
step S1, receiving a cycle sampling data ID to be tested and a cycle from y-z to y, wherein y and z are positive integers, and y is larger than z;
step S2, retrieving in the periodic sampling data ID of the first data table according to the periodic sampling data ID to be detected, acquiring a record corresponding to the periodic sampling data ID to be detected, retrieving in the period identifier of the record corresponding to the periodic sampling data ID to be detected according to the ith period, and acquiring the sampling value in G corresponding time-sampling value pairs, where i is y-z, y-z +1 … y;
step S3, acquiring sampling data of a to-be-detected period in the ith period according to sampling values in G time-sampling value pairs until the sampling data of the to-be-detected period from the y-z period to the y period are acquired, and forming a to-be-detected period sampling data sequence by the sampling data of the to-be-detected period from the y-z period to the y period according to a time sequence;
step S4, inputting the periodic sampling data sequence to be tested into the jth time frame, where j is 1,2 … M, respectively, matching the periodic sampling data sequence to be tested with the jth time frame, and obtaining a matching degree Q of the periodic sampling data sequence to be tested and the jth time framejUntil the matching degree of the periodic sampling data sequence to be detected and all M time frames is obtained;
step S5, selecting the maximum matching degree from the M obtained matching degrees, and determining the data type corresponding to the time frame of the maximum matching degree as the data type of the periodic sampling data to be tested;
the database also comprises a second data table, each record in the second data table is periodically sampled data, and the fields of the second data table comprise data type IDs, time-sampling value pairs of G key variables and period identifications;
the computer program, when executed by a processor, further implements:
step S10, constructing each time frame, specifically including:
s101, receiving a data type ID input by a user and a period from a p-q to a p-q, wherein p and q are positive integers, p is larger than q, y-z is larger than p-q, and y is smaller than p;
step S102, retrieving in the data type ID in the second data table according to the data type ID input by the user, and acquiring a record corresponding to the data type ID input by the user;
step 103, searching in records corresponding to the data type ID input by the user according to the r-th period, and acquiring sampling values in time-sampling value pairs of corresponding G key variables, wherein r is p-q, and p-q +1 … p;
step S104, acquiring key variable data of the r-th period according to sampling values in time-sampling value pairs of G key variables until the key variable data from the p-q period to the p-th period are acquired, and forming the key variable data from the p-q period to the p-th period into a time sequence of key variables;
step S105, determining corresponding first state intervals and corresponding second state intervals … & ltth & gt state intervals according to the time sequence of the key variables, wherein N is a positive integer greater than or equal to 2;
step S106, dividing the time from the p-q cycle to the p cycle into different state time periods based on the first state interval and the second state interval … N state interval to obtain a time frame corresponding to the data type ID input by the user;
the step S4 includes:
step S41, inputting the periodic sampling data sequence to be tested into the jth time frame, and acquiring the total number X of all state intervals of the jth time framejThe number x of the nth state intervals with the end value larger than the initial value of the to-be-detected periodic sampling data sequence interval corresponding to all the nth state intervalsnj1The number x of the nth state intervals with the end value smaller than the initial value of the to-be-detected periodic sampling data sequence interval corresponding to all the nth state intervalsnj2；
Step S42, based on Xj、xnj1、xnj2Obtaining the matching degree Q of the matching degree of the periodic sampling data sequence to be detected and the jth time framej：
Wherein, XnjThe number X of all the nth state intervals of the jth time framenj。
2. The system of claim 1,
in step S3, the sampling data of the cycle to be measured in the i-th cycle is the average, median, maximum, minimum, last or first of the sampling values in the corresponding G time-sampling value pairs.
3. The system of claim 1,
in step S104, the key variable data of the r-th period is a mean value, a median, a maximum value, a minimum value, a last time sampling value or a first time sampling value of sampling values in time-sampling values of the corresponding G key variables.
4. The system of claim 1,
n is equal to 3, the step S105 includes:
s115, acquiring the mean value and the standard deviation of the time sequence of the key variables;
step S125, determining three state intervals based on the mean value and the standard deviation of the time series of the key variables:
determining a period of time-series values > (mean + W standard deviation) of the key variable as the first state interval,
determining a period of the time series value of the key variable less than or equal to (mean + W standard deviation) as the second state interval,
and determining the period of the time series value < (mean-W standard deviation) of the key variable as a third state interval.
5. The system of claim 4,
the value range of W is (0.3, 1).
6. The system of claim 1,
the fields of the second data table further include preset parameter characteristic condition information, and after selecting the maximum matching degree from the M obtained matching degrees in step S5, the method further includes:
step S51, acquiring a data type ID corresponding to the time frame with the maximum matching degree;
step S52, retrieving the data type ID of the second data table according to the data type ID corresponding to the time frame with the maximum matching degree, and acquiring the preset parameter characteristic condition information corresponding to the time frame with the maximum matching degree;
step S53, serially connecting the data of the periodic sampling data sequence to be tested in the time periods corresponding to all the nth state intervals of the time frame with the maximum matching degree to form an nth state data sequence;
step S54, obtaining the corresponding prediction parameter characteristics of the nth state data sequence until all N state data sequences are obtained;
and step S55, judging whether the predicted parameter characteristics of the first state data sequence and the second state data sequence … the Nth state data sequence conform to the preset parameter characteristic condition information corresponding to the time frame with the maximum matching degree, and if so, determining the data type corresponding to the time frame with the maximum matching degree as the data type of the periodic sampling data to be detected.
7. The system of claim 6,
and N is 3, and the preset parameter characteristic conditions are as follows:
the prediction parameter characteristic of the first state data sequence, the prediction parameter characteristic of the second state data sequence and the prediction parameter characteristic value of the third state data sequence are sequentially decreased progressively; alternatively, the first and second electrodes may be,
the prediction parameter switched to the third state data sequence is minimum.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011131982.XA CN112256803B (en) | 2020-10-21 | 2020-10-21 | Dynamic data category determination system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011131982.XA CN112256803B (en) | 2020-10-21 | 2020-10-21 | Dynamic data category determination system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112256803A CN112256803A (en) | 2021-01-22 |
| CN112256803B true CN112256803B (en) | 2021-09-14 |
Family
ID=74263885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011131982.XA Active CN112256803B (en) | 2020-10-21 | 2020-10-21 | Dynamic data category determination system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112256803B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104636493A (en) * | 2015-03-04 | 2015-05-20 | 浪潮电子信息产业股份有限公司 | Dynamic data grading method based on multi-classifier fusion |
| CN104657469A (en) * | 2015-02-13 | 2015-05-27 | 罗悦 | Self-adapting dynamic data processing method |
| CN110321940A (en) * | 2019-06-24 | 2019-10-11 | 清华大学 | The feature extraction of aircraft telemetry and classification method and device |
| CN110334811A (en) * | 2019-06-28 | 2019-10-15 | 西安理工大学 | Dynamic dataflow classification method based on Bayesian network |
| CN110765267A (en) * | 2019-10-12 | 2020-02-07 | 大连理工大学 | Dynamic incomplete data classification method based on multi-task learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160306870A1 (en) * | 2015-04-14 | 2016-10-20 | Algoscent | System and method for capture, classification and dimensioning of micro-expression temporal dynamic data into personal expression-relevant profile |
-
2020
- 2020-10-21 CN CN202011131982.XA patent/CN112256803B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104657469A (en) * | 2015-02-13 | 2015-05-27 | 罗悦 | Self-adapting dynamic data processing method |
| CN104636493A (en) * | 2015-03-04 | 2015-05-20 | 浪潮电子信息产业股份有限公司 | Dynamic data grading method based on multi-classifier fusion |
| CN110321940A (en) * | 2019-06-24 | 2019-10-11 | 清华大学 | The feature extraction of aircraft telemetry and classification method and device |
| CN110334811A (en) * | 2019-06-28 | 2019-10-15 | 西安理工大学 | Dynamic dataflow classification method based on Bayesian network |
| CN110765267A (en) * | 2019-10-12 | 2020-02-07 | 大连理工大学 | Dynamic incomplete data classification method based on multi-task learning |
Non-Patent Citations (2)
| Title |
|---|
| 传感器网络时间序列数据的事件分类研究;叶李;《重庆邮电大学学报(自然科学版)》;20160615(第03期);第421-425页 * |
| 大坝变形观测数据的动态聚类分析;陈继光;《水电能源科学》;20001230(第04期);第22-24页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112256803A (en) | 2021-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020207074A1 (en) | Information pushing method and device | |
| US9053386B2 (en) | Method and apparatus of identifying similar images | |
| CN107451832B (en) | Method and device for pushing information | |
| CN107861981B (en) | Data processing method and device | |
| CN106951527B (en) | Song recommendation method and device | |
| CN111708942B (en) | Multimedia resource pushing method, device, server and storage medium | |
| US20110119270A1 (en) | Apparatus and method for processing a data stream | |
| CN112016623B (en) | Face clustering method, device, equipment and storage medium | |
| CN107766467B (en) | Information detection method and device, electronic equipment and storage medium | |
| CN110717806B (en) | Product information pushing method, device, equipment and storage medium | |
| WO2019120007A1 (en) | Method and apparatus for predicting user gender, and electronic device | |
| CN111159563A (en) | Method, device and equipment for determining user interest point information and storage medium | |
| TW202217597A (en) | Image incremental clustering method, electronic equipment, computer storage medium thereof | |
| WO2020253369A1 (en) | Method and device for generating interest tag, computer equipment and storage medium | |
| CN114003636A (en) | Multivariate time sequence similarity searching method based on variable correlation | |
| CN113449132A (en) | Vector retrieval method and device | |
| CN111488479B (en) | Hypergraph construction method and device, computer system and medium | |
| TWI754515B (en) | Image detection and related model training method, equipment and computer readable storage medium | |
| CN112256803B (en) | Dynamic data category determination system | |
| CN110377721B (en) | Automatic question answering method, device, storage medium and electronic equipment | |
| CN112115281A (en) | Data retrieval method, device and storage medium | |
| CN113315851A (en) | Domain name detection method, device and storage medium | |
| CN115225308A (en) | Attack group identification method and related equipment for large-scale group attack traffic | |
| CN110059272B (en) | Page feature recognition method and device | |
| CN108052503B (en) | Confidence coefficient calculation method and device |
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 |