CN112650952A - Search sorting method and device - Google Patents

Search sorting method and device Download PDF

Info

Publication number
CN112650952A
CN112650952A CN202011558715.0A CN202011558715A CN112650952A CN 112650952 A CN112650952 A CN 112650952A CN 202011558715 A CN202011558715 A CN 202011558715A CN 112650952 A CN112650952 A CN 112650952A
Authority
CN
China
Prior art keywords
multimedia content
operation behavior
characteristic
log
determining
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.)
Granted
Application number
CN202011558715.0A
Other languages
Chinese (zh)
Other versions
CN112650952B (en
Inventor
张志伟
林靖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Dajia Internet Information Technology Co Ltd
Original Assignee
Beijing Dajia Internet Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Dajia Internet Information Technology Co Ltd filed Critical Beijing Dajia Internet Information Technology Co Ltd
Priority to CN202011558715.0A priority Critical patent/CN112650952B/en
Publication of CN112650952A publication Critical patent/CN112650952A/en
Application granted granted Critical
Publication of CN112650952B publication Critical patent/CN112650952B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9538—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/10—File systems; File servers
    • G06F16/18—File system types
    • G06F16/1805—Append-only file systems, e.g. using logs or journals to store data
    • G06F16/1815—Journaling file systems
    • 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
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462—Approximate or statistical queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The application relates to the technical field of computers, and discloses a search ordering method and device, which are used for solving the problem of inaccurate ordering of newly uploaded multimedia contents due to less interactive data. The method comprises the following steps: searching to obtain a first multimedia content set matched with the input query information, and if the uploading time of any one first multimedia content X is lower than a set time threshold, determining operation behavior characteristics based on log data of a second multimedia content set, wherein the second multimedia content set is uploaded by an uploading object of the first multimedia content X; the first set of multimedia content is ordered based on the operational behavior characteristics. The multimedia contents uploaded by the same uploading object have the condition of similar preference, so that the data of other using objects for operating the first multimedia contents can be calculated according to the log data of the second multimedia content set, and the problem of inaccurate sequencing of newly uploaded multimedia contents due to less interactive data is solved.

Description

Search sorting method and device
Technical Field
The invention relates to the technical field of computers, in particular to a search sorting method and a search sorting device.
Background
With the arrival of the big data era, a large amount of multimedia contents are flooded on a network, in order to recommend interested multimedia contents to a user more accurately, a recommendation system adopts a mode of combining a recall model and a sequencing model, firstly, multimedia contents matched with keywords/words input by the user are screened out from a database, then, the multimedia contents are sequenced on the basis of interactive data of the multimedia contents, and finally, the sequenced multimedia contents are presented to the user.
However, when the traditional sorting model is adopted for sorting, the problem of inaccurate sorting is easily caused by less interactive data of newly uploaded multimedia contents.
In view of the above, a new search ranking method needs to be devised to overcome the above drawbacks.
Disclosure of Invention
The embodiment of the application provides a search ordering method and a search ordering device, which are used for solving the problem of inaccurate ordering of newly uploaded multimedia contents due to less interactive data.
The embodiment of the application provides the following specific technical scheme:
in a first aspect, an embodiment of the present application provides a search ranking method, including:
searching to obtain a first multimedia content set matched with the input query information;
performing the following operations respectively for each first multimedia content in the first set of multimedia content: if the uploaded time of any one first multimedia content is lower than a set time threshold, determining operation behavior characteristics based on log data of a second multimedia content set, wherein the second multimedia content set is uploaded by an uploaded object of any one first multimedia content;
ordering the first set of multimedia content based on the respective operational behavior characteristics.
Optionally, determining the operation behavior feature based on log data of the second multimedia content set includes:
determining a first statistical characteristic and a first proportional characteristic of the second multimedia content set based on a first log set of the second multimedia content set within a preset time period, wherein one first log is a log generated when any one second multimedia content is operated within the preset time period based on other using objects;
and splicing the first statistical characteristic and the first proportional characteristic to obtain the operation behavior characteristic.
Optionally, determining a first statistical characteristic and a first proportional characteristic of the second multimedia content set based on a first log set of the second multimedia content set within a preset time period includes:
and calculating a first daily average operation behavior and a first operation behavior ratio of the other using objects to a second multimedia content set in a preset time period based on the first log set, determining the first daily average operation behavior as the first statistical characteristic, and determining the first operation behavior ratio as the first proportional characteristic.
Optionally, further comprising:
and if the uploaded time of any one first multimedia content exceeds a set time threshold, determining the operation behavior characteristics based on the log data of any one first multimedia content.
Optionally, determining the operation behavior feature based on the log data of any one of the first multimedia contents includes:
determining a second statistical characteristic and a second proportional characteristic of any one first multimedia content based on a second log set of the any one first multimedia content in a preset time period, wherein one second log is a log generated when the any one first multimedia content is operated by other using objects in the preset time period;
and splicing the second statistical characteristic and the second proportional characteristic to obtain the operation behavior characteristic.
Optionally, determining a second statistical characteristic and a second proportional characteristic of the any one first multimedia content based on a second log set of the any one first multimedia content within a preset time period includes:
and calculating a second daily average operation behavior and a second operation behavior ratio of the other using objects to the any one first multimedia content in a preset time period based on the second log set, determining the second daily average operation behavior as the second statistical characteristic, and determining the second operation behavior ratio as the second proportional characteristic.
In a second aspect, an embodiment of the present application further provides a search ranking apparatus, including:
the searching unit is used for searching and obtaining a first multimedia content set matched with the input query information;
a processing unit, configured to perform the following operations for each first multimedia content in the first set of multimedia contents, respectively: if the uploaded time of any one first multimedia content is lower than a set time threshold, determining operation behavior characteristics based on log data of a second multimedia content set, wherein the second multimedia content set is uploaded by an uploaded object of any one first multimedia content;
a sorting unit configured to sort the first multimedia content set based on each operation behavior feature.
Optionally, the processing unit is configured to:
determining a first statistical characteristic and a first proportional characteristic of the second multimedia content set based on a first log set of the second multimedia content set within a preset time period, wherein one first log is a log generated when any one second multimedia content is operated within the preset time period based on other using objects;
and splicing the first statistical characteristic and the first proportional characteristic to obtain the operation behavior characteristic.
Optionally, the processing unit is configured to:
and calculating a first daily average operation behavior and a first operation behavior ratio of the other using objects to a second multimedia content set in a preset time period based on the first log set, determining the first daily average operation behavior as the first statistical characteristic, and determining the first operation behavior ratio as the first proportional characteristic.
Optionally, the processing unit is further configured to:
and if the uploaded time of any one first multimedia content exceeds a set time threshold, determining the operation behavior characteristics based on the log data of any one first multimedia content.
Optionally, the processing unit is configured to:
determining a second statistical characteristic and a second proportional characteristic of any one first multimedia content based on a second log set of the any one first multimedia content in a preset time period, wherein one second log is a log generated when the any one first multimedia content is operated by other using objects in the preset time period;
and splicing the second statistical characteristic and the second proportional characteristic to obtain the operation behavior characteristic.
Optionally, the processing unit is configured to:
and calculating a second daily average operation behavior and a second operation behavior ratio of the other using objects to the any one first multimedia content in a preset time period based on the second log set, determining the second daily average operation behavior as the second statistical characteristic, and determining the second operation behavior ratio as the second proportional characteristic.
In a third aspect, an embodiment of the present application further provides a computing device, including:
a memory for storing program instructions;
and the processor is used for calling the program instructions stored in the memory and executing any one of the search sorting methods according to the obtained program.
In a fourth aspect, an embodiment of the present application further provides a storage medium, which includes computer readable instructions, and when the computer readable instructions are read and executed by a computer, the computer is caused to execute any one of the search ranking methods described above.
The beneficial effect of this application is as follows:
in the embodiment of the present application, a first multimedia content set matched with input query information is obtained by searching, and the following operations are respectively performed for each first multimedia content in the first multimedia content set: if the uploaded time of any one first multimedia content X is lower than a set time threshold, determining operation behavior characteristics based on log data of a second multimedia content set, wherein the second multimedia content set is uploaded by an uploading object of the first multimedia content X; the first set of multimedia content is ordered based on the respective operational behavior characteristics. The newly uploaded first multimedia content has low confidence coefficient due to less interactive data, but the multimedia content uploaded by the same uploading object has the condition of similar preference, so that the data of other using objects for operating the first multimedia content can be calculated according to the log data of the second multimedia content set, and the problem of inaccurate sequencing of the newly uploaded multimedia content due to less interactive data is solved.
Drawings
Fig. 1 is a schematic flow chart of a sorting method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a sorting apparatus according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a computing device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments, but not all embodiments, of the technical solutions of the present application. All other embodiments obtained by a person skilled in the art without any inventive step based on the embodiments described in the present application are within the scope of the protection of the present application.
When newly uploaded multimedia contents are searched, the newly uploaded multimedia contents are not accurately sequenced due to the fact that interactive data of the newly uploaded multimedia contents are less and higher confidence coefficient is difficult to obtain, the newly uploaded multimedia contents are always sequenced at a later position and high exposure rate is difficult to obtain, interaction between the newly uploaded multimedia contents and a user is further reduced, vicious circle is formed, and the newly uploaded multimedia contents are more unfavorable for being sequenced at the front of a push list. Is beneficial to improving the viscosity of users and the product spreading degree.
Next, referring to fig. 1, a process of using the ranking model will be described.
S101: the search results in a first set of multimedia content that matches the input query information.
The first multimedia content is multimedia content matched with query information such as keywords or keywords input by a user, and the multimedia content can be one or any combination of audio, video, pictures and picture sets.
S102: performing the following operations respectively for each first multimedia content in the first set of multimedia content: and if the uploaded time of any one first multimedia content X is lower than a set time threshold, determining the operation behavior characteristics based on log data of a second multimedia content set, wherein the second multimedia content set is uploaded by the uploading object of the first multimedia content X.
If the uploaded time of the first multimedia content X is lower than the set time threshold, it is indicated that the first multimedia content X belongs to newly uploaded multimedia content, and there are few interactive data, and in order to improve the confidence of the first multimedia content X, an upload object for uploading the first multimedia content X may be determined first, and then the operation behavior characteristics may be determined according to the log data of the second multimedia content set uploaded by the upload object. The second multimedia content set may include some second multimedia contents with longer uploading time, and the interactive data of the second multimedia contents is richer than that of the newly uploaded first multimedia content X, so that the operation behavior characteristics of the newly uploaded first multimedia content X are calculated according to the log data of the second multimedia content set, and the problem of inaccurate sequencing caused by less interactive data is solved.
Optionally, the process of determining the operation behavior characteristic based on the log data of the second multimedia content set is as follows:
firstly, determining a first statistical characteristic and a first proportional characteristic of a second multimedia content set based on a first log set of the second multimedia content set within a preset time period, wherein one first log is a log generated when any one second multimedia content is operated within the preset time period based on other using objects;
and secondly, splicing the first statistic characteristics and the first proportion characteristics to obtain operation behavior characteristics.
The first statistical characteristic and the first proportional characteristic can reflect the heat degree of the second multimedia content set, although the confidence degree of the first multimedia content X is low due to less interactive data and low heat degree, the operation behaviors of other using objects on the first multimedia content X can be calculated according to the operation behaviors of the other using objects on the second multimedia content set in a preset time period because the multimedia contents manufactured and uploaded by the same uploading object have similar preference, so that the confidence degree of the first multimedia content X is influenced, and the problem of inaccurate sequencing of newly uploaded multimedia contents due to less interactive data is solved.
Specifically, based on the first log set, a first daily average operation behavior and a first operation behavior ratio of other usage objects to the second multimedia content set within a preset time period are calculated, the first daily average operation behavior is determined as a first statistical characteristic, and the first operation behavior ratio is determined as a first proportional characteristic. The first daily average operation behavior and the first operation behavior ratio are indexes for measuring the heat degree of the second multimedia content set, and generally the higher the heat degree is, the more the second multimedia content set is arranged in the push list, so the two indexes influence the confidence degree of the first multimedia content X and further influence the position of the first multimedia content X in the push list.
In fact, the operation behaviors in the embodiment of the present application include, but are not limited to, clicking, agreeing on, forwarding, and commenting, but the manner of calculating the first statistical characteristic and the first proportional characteristic of each type of operation behavior is the same, and for convenience of description, the calculation processes of the first statistical characteristic and the first proportional characteristic are introduced subsequently by taking the operation behavior that another user object clicks the second multimedia content as an example.
Assuming that a first log set of a second multimedia content set uploaded by an uploading object in the last week is obtained, calculating the average daily click rate by adopting a formula (1), and calculating the average daily click rate by adopting a formula (2). Wherein, feature of formula (1)clickRepresenting the average daily click times of a second multimedia content set uploaded by the uploading object, i representing the ith day, date representing the last day of the week, if _ click _ i representing a first log of each reading the ith day, when determining that other using objects click on the second multimedia content, counting and adding 1 until all the first logs in the week are read, and counting the total times of clicking on the second multimedia content by other using objects in the week; sigmaif date1 represents the sum of the number of days for which each second multimedia content is presented, and # photo represents the total number of second multimedia contents included in the second set of multimedia contents; feature of formula (2)click_ratioShowing the click-through rate, feature, of the second set of multimedia content that the upload object has uploadedclickShowing the average daily click times of the second multimedia content set uploaded by the uploading objectshowAnd the average daily showing times of the second multimedia content set uploaded by the uploading object are represented.
Figure BDA0002859618750000071
Figure BDA0002859618750000072
When the first multimedia content X belongs to newly uploaded multimedia content, the operation behavior feature is determined based on log data of the second multimedia content set, and then when the uploaded time of the first multimedia content X exceeds a set time threshold, it indicates that the first multimedia content X has been uploaded for a period of time, the interactive data of the first multimedia content X is more, and the operation behavior feature can be determined based on the log data of the first multimedia content X.
Optionally, the process of determining the operation behavior characteristic based on the log data of the first multimedia content X is as follows:
firstly, determining a second statistical characteristic and a second proportional characteristic of a first multimedia content X based on a second log set of the first multimedia content X in a preset time period, wherein one second log is a log generated when the first multimedia content X is operated in the preset time period based on other using objects;
and secondly, splicing the second statistical characteristic and the second proportional characteristic to obtain an operation behavior characteristic.
The second statistical characteristic and the second scale characteristic may reflect the popularity of the first multimedia content X that has been uploaded for a period of time, and generally the higher the popularity, the more the first multimedia content X is ranked ahead in the push list.
Specifically, based on the second log set, a second daily average operation behavior and a second operation behavior ratio of other usage objects to the first multimedia content within a preset time period are calculated, the second daily average operation behavior is determined as a second statistical characteristic, and the second operation behavior ratio is determined as a second proportional characteristic. The second daily average operation behavior and the second operation behavior ratio are indexes for measuring the heat degree of the first multimedia content X which has been uploaded for a period of time, and the heat degree affects the confidence degree of the first multimedia content X and further affects the position of the first multimedia content in the push list. Therefore, for the first multimedia content X that has been uploaded for a period of time, the two indexes need to be calculated according to the interactive data (i.e. the second log set) of the first multimedia content X within a preset period of time.
In fact, the operation behaviors in the embodiment of the present application include, but are not limited to, clicking, commenting, forwarding, and commenting, but the manner of calculating the second statistical characteristic and the second proportional characteristic of each type of operation behavior is the same, and for convenience of description, the calculation processes of the second statistical characteristic and the second proportional characteristic are introduced subsequently by taking the operation behavior that another user object clicks the first multimedia content X as an example.
Assuming that a second log set of the first multimedia content X in the last week is obtained, the average daily click number of the first multimedia content X is calculated by adopting formula (3), and the click rate of the first multimedia content X is calculated by adopting formula (4). Wherein, feature of formula (3)clickThe method comprises the steps of ' representing the average daily click number of first multimedia content X, i ' representing the ith ' day, date representing the last day of a week, and if _ click _ i ' representing a second log of each ith ' day, wherein when the operation behavior that other using objects click on the first multimedia content X is recorded in the second log, the count is increased by 1 until all second logs in the week are read, and the total number of times that other using objects click on the first multimedia content X in the week is determined; sigmaif date1 denotes the sum of the days of presentation of the first multimedia content X, in this example Σif date1 is 7 days; feature of formula (4)click_ratio' denotes a click-through rate, feature of the first multimedia content Xclick' representing the daily average number of clicks of the first multimedia content X, featureshow' denotes the number of daily average presentations of the first multimedia content X.
Figure BDA0002859618750000091
Figure BDA0002859618750000092
S103: the first set of multimedia content is ordered based on the respective operational behavior characteristics.
And calculating the confidence corresponding to each first multimedia content by using the operation behavior characteristics of each first multimedia content, and sequencing each first multimedia content according to the sequence from high confidence to low confidence.
Based on the same inventive concept, in the embodiment of the present invention, a search sorting apparatus is provided, as shown in fig. 2, which at least includes a search unit 201, a processing unit 202, and a sorting unit 203, wherein,
a searching unit 201, configured to search for a first multimedia content set matching the input query information;
a processing unit 202, configured to perform the following operations for each first multimedia content in the first set of multimedia contents, respectively: if the uploaded time of any one first multimedia content is lower than a set time threshold, determining operation behavior characteristics based on log data of a second multimedia content set, wherein the second multimedia content set is uploaded by an uploaded object of any one first multimedia content;
a sorting unit 203, configured to sort the first multimedia content set based on each operation behavior characteristic.
Optionally, the processing unit 202 is configured to:
determining a first statistical characteristic and a first proportional characteristic of the second multimedia content set based on a first log set of the second multimedia content set within a preset time period, wherein one first log is a log generated when any one second multimedia content is operated within the preset time period based on other using objects;
and splicing the first statistical characteristic and the first proportional characteristic to obtain the operation behavior characteristic.
Optionally, the processing unit 202 is configured to:
and calculating a first daily average operation behavior and a first operation behavior ratio of the other using objects to a second multimedia content set in a preset time period based on the first log set, determining the first daily average operation behavior as the first statistical characteristic, and determining the first operation behavior ratio as the first proportional characteristic.
Optionally, the processing unit 202 is further configured to:
and if the uploaded time of any one first multimedia content exceeds a set time threshold, determining the operation behavior characteristics based on the log data of any one first multimedia content.
Optionally, the processing unit 202 is configured to:
determining a second statistical characteristic and a second proportional characteristic of any one first multimedia content based on a second log set of the any one first multimedia content in a preset time period, wherein one second log is a log generated when the any one first multimedia content is operated by other using objects in the preset time period;
and splicing the second statistical characteristic and the second proportional characteristic to obtain the operation behavior characteristic.
Optionally, the processing unit 202 is configured to:
and calculating a second daily average operation behavior and a second operation behavior ratio of the other using objects to the any one first multimedia content in a preset time period based on the second log set, determining the second daily average operation behavior as the second statistical characteristic, and determining the second operation behavior ratio as the second proportional characteristic.
Based on the same inventive concept, in the embodiment of the present invention, a computing device is provided, as shown in fig. 3, which at least includes a memory 301 and at least one processor 302, where the memory 301 and the processor 302 complete communication with each other through a communication bus;
the memory 301 is used to store program instructions;
the processor 302 is configured to call the program instructions stored in the memory 401, and execute the aforementioned search ranking method according to the obtained program.
Based on the same inventive concept, in the embodiments of the present invention, a storage medium is provided, which at least includes computer readable instructions, and when the computer reads and executes the computer readable instructions, the computer is caused to execute the aforementioned search ranking method.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made in the embodiments of the present invention without departing from the spirit or scope of the embodiments of the invention. Thus, if such modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to encompass such modifications and variations.

Claims (10)

1. A search ranking method, comprising:
searching to obtain a first multimedia content set matched with the input query information;
performing the following operations respectively for each first multimedia content in the first set of multimedia content: if the uploaded time of any one first multimedia content is lower than a set time threshold, determining operation behavior characteristics based on log data of a second multimedia content set, wherein the second multimedia content set is uploaded by an uploaded object of any one first multimedia content;
ordering the first set of multimedia content based on the respective operational behavior characteristics.
2. The method of claim 1, wherein determining operational behavior characteristics based on log data for the second set of multimedia content comprises:
determining a first statistical characteristic and a first proportional characteristic of the second multimedia content set based on a first log set of the second multimedia content set within a preset time period, wherein one first log is a log generated when any one second multimedia content is operated within the preset time period based on other using objects;
and splicing the first statistical characteristic and the first proportional characteristic to obtain the operation behavior characteristic.
3. The method of claim 2, wherein determining the first statistical characteristic and the first proportional characteristic of the second set of multimedia content based on the first set of journals within the second set of multimedia content within the preset time period comprises:
and calculating a first daily average operation behavior and a first operation behavior ratio of the other using objects to a second multimedia content set in a preset time period based on the first log set, determining the first daily average operation behavior as the first statistical characteristic, and determining the first operation behavior ratio as the first proportional characteristic.
4. The method of claim 1, further comprising:
and if the uploaded time of any one first multimedia content exceeds a set time threshold, determining the operation behavior characteristics based on the log data of any one first multimedia content.
5. The method of claim 4, wherein determining operational behavior characteristics based on log data of the arbitrary one of the first multimedia content comprises:
determining a second statistical characteristic and a second proportional characteristic of any one first multimedia content based on a second log set of the any one first multimedia content in a preset time period, wherein one second log is a log generated when the any one first multimedia content is operated by other using objects in the preset time period;
and splicing the second statistical characteristic and the second proportional characteristic to obtain the operation behavior characteristic.
6. The method of claim 5, wherein determining the second statistical characteristic and the second scale characteristic of the arbitrary one of the first multimedia contents based on a second log set of the arbitrary one of the first multimedia contents within a preset time period comprises:
and calculating a second daily average operation behavior and a second operation behavior ratio of the other using objects to the any one first multimedia content in a preset time period based on the second log set, determining the second daily average operation behavior as the second statistical characteristic, and determining the second operation behavior ratio as the second proportional characteristic.
7. A search ranking apparatus, comprising:
the searching unit is used for searching and obtaining a first multimedia content set matched with the input query information;
a processing unit, configured to perform the following operations for each first multimedia content in the first set of multimedia contents, respectively: if the uploaded time of any one first multimedia content is lower than a set time threshold, determining operation behavior characteristics based on log data of a second multimedia content set, wherein the second multimedia content set is uploaded by an uploaded object of any one first multimedia content;
a sorting unit configured to sort the first multimedia content set based on each operation behavior feature.
8. The apparatus of claim 7, wherein the processing unit is to:
determining a first statistical characteristic and a first proportional characteristic of the second multimedia content set based on a first log set of the second multimedia content set within a preset time period, wherein one first log is a log generated when any one second multimedia content is operated within the preset time period based on other using objects;
and splicing the first statistical characteristic and the first proportional characteristic to obtain the operation behavior characteristic.
9. A computing device, comprising:
a memory for storing program instructions;
a processor for calling program instructions stored in said memory to execute the method of any one of claims 1 to 6 in accordance with the obtained program.
10. A storage medium comprising computer readable instructions which, when read and executed by a computer, cause the computer to perform the method of any one of claims 1 to 6.
CN202011558715.0A 2020-12-25 2020-12-25 Search ordering method and device Active CN112650952B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011558715.0A CN112650952B (en) 2020-12-25 2020-12-25 Search ordering method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011558715.0A CN112650952B (en) 2020-12-25 2020-12-25 Search ordering method and device

Publications (2)

Publication Number Publication Date
CN112650952A true CN112650952A (en) 2021-04-13
CN112650952B CN112650952B (en) 2023-07-25

Family

ID=75363450

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011558715.0A Active CN112650952B (en) 2020-12-25 2020-12-25 Search ordering method and device

Country Status (1)

Country Link
CN (1) CN112650952B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170220575A1 (en) * 2016-01-28 2017-08-03 Shutterstock, Inc. Identification of synthetic examples for improving search rankings
CN109508394A (en) * 2018-10-18 2019-03-22 青岛聚看云科技有限公司 A kind of training method and device of multi-medium file search order models
CN110633376A (en) * 2019-08-22 2019-12-31 北京奇艺世纪科技有限公司 Media object sorting method, device, equipment and storage medium
CN111444380A (en) * 2020-03-26 2020-07-24 腾讯音乐娱乐科技（深圳）有限公司 Music search sorting method, device, equipment and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170220575A1 (en) * 2016-01-28 2017-08-03 Shutterstock, Inc. Identification of synthetic examples for improving search rankings
CN109508394A (en) * 2018-10-18 2019-03-22 青岛聚看云科技有限公司 A kind of training method and device of multi-medium file search order models
CN110633376A (en) * 2019-08-22 2019-12-31 北京奇艺世纪科技有限公司 Media object sorting method, device, equipment and storage medium
CN111444380A (en) * 2020-03-26 2020-07-24 腾讯音乐娱乐科技（深圳）有限公司 Music search sorting method, device, equipment and storage medium

Also Published As

Publication number Publication date
CN112650952B (en) 2023-07-25

Similar Documents

Publication Publication Date Title
CN110149540B (en) Recommendation processing method and device for multimedia resources, terminal and readable medium
CN109657138B (en) Video recommendation method and device, electronic equipment and storage medium
CN110929052B (en) Multimedia resource recommendation method and device, electronic equipment and storage medium
US9092549B2 (en) Recommendation of search keywords based on indication of user intention
US8893012B1 (en) Visual indicator based on relative rating of content item
TW202007178A (en) Method, device, apparatus, and storage medium of generating features of user
CN111126495B (en) Model training method, information prediction device, storage medium and equipment
WO2018121700A1 (en) Method and device for recommending application information based on installed application, terminal device, and storage medium
CN108460082B (en) Recommendation method and device and electronic equipment
US20160285672A1 (en) Method and system for processing network media information
CN109889891B (en) Method, device and storage medium for acquiring target media file
US20070219994A1 (en) Methods and systems for displaying media utilizing user-generated data
US20150339700A1 (en) Method, apparatus and system for processing promotion information
CN109274987A (en) A kind of video collection sort method, server and readable storage medium storing program for executing
CN106354867A (en) Multimedia resource recommendation method and device
CN111061954A (en) Search result sorting method and device and storage medium
US20160247078A1 (en) Identifying content appropriate for children algorithmically without human intervention
WO2016149051A1 (en) Enhanced template curating
CN112561636A (en) Recommendation method, recommendation device, terminal equipment and medium
CN110569447B (en) Network resource recommendation method and device and storage medium
CN108764021B (en) Cheating video identification method and device
CN111311015A (en) Personalized click rate prediction method, device and readable storage medium
CN112650952B (en) Search ordering method and device
CN109033050B (en) article generation method, article generation device and storage medium
WO2022247671A1 (en) User recall method and apparatus, and computer device and 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