CN118283361A

CN118283361A - Server and media asset recommendation method

Info

Publication number: CN118283361A
Application number: CN202310874143.4A
Authority: CN
Inventors: 袁丽; 杨梅; 林莉
Original assignee: Qingdao Jukanyun Technology Co ltd
Current assignee: Qingdao Jukanyun Technology Co ltd
Priority date: 2023-07-17
Filing date: 2023-07-17
Publication date: 2024-07-02

Abstract

The application provides a server and a media asset recommendation method, wherein the server acquires a media asset data search log and a media asset data access log of a current user according to a control instruction sent by a terminal device, and calculates recommendation weights according to the media asset data search log and the media asset data access log. The recommendation weights are used to rank historical search terms in the media asset data search logs to generate a search term recommendation queue. After generating the search word recommendation queue, the server sends the search word recommendation queue to the terminal device, so that the terminal device displays historical search words in the search word recommendation queue on the media resource search interface. The server combines the search frequency and the access frequency of the historical search words of the user to generate recommendation weights for sequencing the historical search words, and the recommendation weights are attached to the application requirements of the user, so that the recommendation values of the historical search words are improved.

Description

Server and media asset recommendation method

Technical Field

The application relates to the technical field of servers, in particular to a server and a media asset recommendation method.

Background

When the user uses the terminal equipment, a search keyword can be input into a media resource search interface of the terminal equipment so as to search a plurality of media resource data associated with the keyword, and then target media resource data is selected from the plurality of media resource data for viewing.

When the media resource searching interface is started, recommended contents such as historical searching words and popular searching words are generated in a preset area, so that a user can select the historical searching words according to interests, and searching steps are simplified. The terminal equipment can request data from the server when generating historical search words and popular search words so as to generate media recommendation data which better meets the requirements of users through the storage capacity and the computing capacity of the server.

When receiving the request data of the terminal device, the server can count the search time of the historical search words according to the search record of the user in a period of time, and display the historical search words according to the time axis of the historical search words. However, the ranking of the historical search words according to time only does not combine with the actual demands of the users, so that the reference value of the media resource recommendation results is low.

Disclosure of Invention

The application provides a server and a media resource recommendation method, which are used for solving the problem that when a user starts a media resource search interface, a terminal device/server does not recommend historical search words in combination with the actual demands of the user, so that the reference value of the historical search words is low.

In a first aspect, the present application provides a server comprising: a communication module configured to establish a communication connection with a terminal device; a processing module configured to:

responding to a control instruction sent by a terminal device and used for displaying a media resource searching interface, and acquiring a media resource data searching log and a media resource data access log of a current user; the media asset data search log comprises historical search words; the media asset data access log comprises record information of accessing media asset data according to the historical search word;

Calculating recommendation weight according to the media resource search log and the media resource data access log, wherein the recommendation weight is a weighted summation result of the search times of the historical search words in the media resource search log and the corresponding media resource data access times of the historical search words in the media resource data access log;

ranking the historical search terms using the recommendation weights to generate a search term recommendation queue;

and transmitting the search word recommendation queue to a terminal device through the communication module, so that the terminal device displays historical search words in the search word recommendation queue on a media resource search interface.

In some possible embodiments, the processing module performs generating recommendation weights from the media asset search log and the media asset data access log, and is further configured to:

extracting historical search word information from the media resource search log and the media resource data access log, wherein the historical search word information comprises historical search word texts, search time of the historical search words, search times of the historical search words and access times of the historical search words corresponding to the media resource data;

Calculating search weights according to the search times and the time attenuation coefficient of the historical search words; the time attenuation coefficient is set according to the interval time between the search time and the current time;

calculating click weight according to the access times and time attenuation coefficient of the historical search word corresponding to the media asset data;

And summing the searching weight and the clicking weight to obtain a recommendation weight.

In some possible embodiments, the processing module performs ranking of the historical search terms using the recommendation weights, and is further configured to:

Extracting periodic record information from the media resource search log and the media resource data access log;

and adjusting the arrangement sequence of the historical search words in the search word recommendation queue according to the periodic record information.

In some possible embodiments, the period record information includes a search record in a current period of the historical search word, an access record of the historical search word corresponding to the media asset data, and a finishing time of the historical search word corresponding to the media asset data; the processing module is used for adjusting the arrangement sequence of the historical search words in the search word recommendation queue according to the record information and is further configured to:

If the search record in the current period of the historical search word is not recorded in the media resource search log, and/or media resource data corresponding to the historical search word is accessed, and/or finishing time of the media resource data corresponding to the historical search word exceeds a first preset time, moving the historical search word in the search word recommendation queue backwards according to a preset distance.

In some possible embodiments, the processing module is further configured to:

extracting a user id in the control instruction;

querying a media asset data search log associated with the user id and a media asset data access log.

In some possible embodiments, the processing module is further configured to:

extracting searching times from media data searching logs associated with user ids in the control instruction;

Detecting the searching behavior of the media data of the current user in a second preset time according to the searching times;

if the fact that the current user has the media data searching behavior in the second preset time is detected, a new search word recommendation queue is generated based on the media data searching behavior of the current user.

In some possible embodiments, the system further comprises a storage module configured to store a search term recommendation queue associated with the user id according to the user id; the processing module is further configured to:

if the fact that the current user has the media data searching behavior in the second preset time is not detected, locating a storage space associated with the current user id;

And extracting a search word recommendation queue from a storage space associated with the current user id, and transmitting the extracted search word recommendation queue to the terminal device.

In a second aspect, the present application provides a terminal device, including: a display; a communicator configured to establish a communication connection with a server; a controller configured to:

responding to a control instruction input by a user and used for displaying a media resource searching interface, sending the control instruction to a server so that the server generates recommendation weights according to media resource data searching logs and media resource data access logs of the current user, and sequencing historical searching words in the media resource data searching logs according to the recommendation weights to generate a searching word recommendation queue;

Receiving a search word recommendation queue returned by the server;

And controlling a display to display a media resource searching interface, and displaying historical search words in a search word recommendation queue in a preset area of the media resource searching interface.

In a third aspect, the present application provides another terminal device, including: a display; a controller configured to: responding to a control instruction input by a user and used for displaying a media resource searching interface, and acquiring a media resource data searching log and a media resource data access log of the current user; the media asset data search log comprises historical search words; the media asset data access log comprises record information of accessing media asset data according to the historical search word;

And controlling the display to display historical search words in a search word recommendation queue in a preset area of the media resource search interface.

In a fourth aspect, the present application provides a media asset recommendation method, applied to a server, including:

transmitting the search word recommendation queue to a terminal device, so that the terminal device displays historical search words in the search word recommendation queue in a preset area of a media resource search interface.

According to the technical content, the application provides a server and a media asset recommendation method, wherein the server acquires a media asset data search log and a media asset data access log of a current user according to a control instruction sent by a terminal device, and calculates recommendation weights according to the media asset data search log and the media asset data access log. The recommendation weights are used to rank historical search terms in the media asset data search logs to generate a search term recommendation queue. After generating the search word recommendation queue, the server sends the search word recommendation queue to the terminal device, so that the terminal device displays historical search words in the search word recommendation queue on the media resource search interface. The server combines the search frequency and the access frequency of the historical search words of the user to generate recommendation weights for sequencing the historical search words, and the recommendation weights are attached to the application requirements of the user, so that the recommendation values of the historical search words are improved.

Drawings

In order to more clearly illustrate the technical solution of the present application, the drawings that are needed in the embodiments will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.

Fig. 1 is a schematic diagram of an operation scenario of a terminal device and a control device provided in an embodiment of the present application;

Fig. 2 is a schematic diagram of a hardware architecture of a terminal device according to an embodiment of the present application;

fig. 3 is a schematic diagram of a hierarchy used for playing data by a terminal device according to an embodiment of the present application;

Fig. 4 is a schematic diagram of an interaction structure of a terminal device update signal source list according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a media search interface provided by an embodiment of the present application;

FIG. 6 is a schematic flow chart of a server generating a search term recommendation queue according to an embodiment of the present application;

FIG. 7 is a diagram illustrating statistics of historical search terms according to an embodiment of the present application;

FIG. 8 is a schematic diagram of ranking historical search terms using recommendation weights provided by an embodiment of the present application;

FIG. 9 is a schematic diagram of determining whether to generate a new search term recommendation queue according to a user id according to an embodiment of the present application;

fig. 10 is a schematic diagram of displaying a search term by a terminal device according to an embodiment of the present application;

fig. 11 is a schematic diagram of displaying a search term by a terminal device according to an embodiment of the present application;

fig. 12 is a schematic diagram of displaying search terms by a terminal device according to an embodiment of the present application.

Detailed Description

For the purposes of making the objects and embodiments of the present application more apparent, an exemplary embodiment of the present application will be described in detail below with reference to the accompanying drawings in which exemplary embodiments of the present application are illustrated, it being apparent that the exemplary embodiments described are only some, but not all, of the embodiments of the present application.

It should be noted that the brief description of the terminology in the present application is for the purpose of facilitating understanding of the embodiments described below only and is not intended to limit the embodiments of the present application. Unless otherwise indicated, these terms should be construed in their ordinary and customary meaning.

The terms first, second, third and the like in the description and in the claims and in the above-described figures are used for distinguishing between similar or similar objects or entities and not necessarily for describing a particular sequential or chronological order, unless otherwise indicated. It is to be understood that the terms so used are interchangeable under appropriate circumstances.

The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a product or apparatus that comprises a list of elements is not necessarily limited to all elements explicitly listed, but may include other elements not expressly listed or inherent to such product or apparatus.

The terminal device provided by the embodiment of the application can have various implementation forms, for example, a television, a laser projection device, a display (monitor), an electronic whiteboard (electronic bulletin board), an electronic desktop (electronic table) and the like.

Fig. 1 is a schematic diagram of an operation scenario between a terminal device and a control apparatus according to an embodiment. As shown in fig. 1, a user can operate the terminal device 200 through the control device 300 or the control apparatus 100.

In some embodiments, the control device 100 may be a remote controller, and the communication between the remote controller and the terminal device 200 includes infrared protocol communication or bluetooth protocol communication, and other short-range communication modes, and the terminal device 200 is controlled by a wireless or wired mode. The user may control the terminal device 200 by inputting user instructions through keys on a remote controller, voice input, control panel input, etc.

In some embodiments, the control device 300 (e.g., mobile phone, tablet, computer, notebook, etc.) may also be used to control the terminal device 200. For example, the terminal device 200 is controlled using an application running on the control device 300.

In some embodiments, the terminal device 200 may receive the instruction not using the control device 300 or the control apparatus 100 described above, but by touching or gesture or the like.

In some embodiments, the terminal device 200 may also perform control in a manner other than the control apparatus 100 and the control device 300, for example, the voice instruction control of the user may be directly received through a module configured inside the terminal device 200 device to obtain the voice instruction, or the voice instruction control of the user may be received through a voice control device configured outside the terminal device 200 device.

In some embodiments, the terminal device 200 is also in data communication with the server 400. The terminal device 200 may be permitted to make communication connection through a Local Area Network (LAN), a Wireless Local Area Network (WLAN), and other networks. The server 400 may provide various contents and interactions to the terminal device 200. The server 400 may be a cluster, or may be multiple clusters, and may include one or more types of servers.

As shown in fig. 2, the terminal apparatus 200 may include at least one of a modem 210, a communicator 220, a detector 230, an external device interface 240, a controller 250, a display 260, an audio output interface 270, a memory, a power supply, and a user interface.

In some embodiments, the controller 250 as shown in fig. 3 and 4 may include a processor, a video processor, an audio processor, a graphic processor, a RAM, a ROM, and first to nth interfaces for input/output.

Display 260 may include the following components, namely: a display screen assembly for presenting a picture; a driving assembly driving the image display; a component for receiving an image signal outputted from the controller 250, performing display of video content, image content, and a menu manipulation interface, a component for manipulating a UI interface by a user, and the like.

The display 260 may be a liquid crystal display, an OLED display, a projection device, or a projection screen.

The communicator 220 is a component for communicating with external devices or servers according to various communication protocol types. For example: the communicator may include at least one of a Wifi module, a bluetooth module, a wired ethernet module, or other network communication protocol chip or a near field communication protocol chip, and an infrared receiver. The terminal device 200 may establish transmission and reception of control signals and data signals with the external control device 100 or the server 400 through the communicator 220.

A user interface, which may be used to receive control signals from the control device 100 (e.g., an infrared remote control, etc.).

The detector 230 is used to collect signals of the external environment or interaction with the outside. For example, detector 230 includes a light receiver, a sensor for capturing the intensity of ambient light; either the detector 230 comprises an image collector, such as a camera, which may be used to collect external environmental scenes, user attributes or user interaction gestures, or the detector 230 comprises a sound collector, such as a microphone or the like, for receiving external sounds.

The external device interface 240 may include, but is not limited to, the following: high Definition Multimedia Interface (HDMI), analog or data high definition component input interface (component), composite video input interface (CVBS), USB input interface (USB), RGB port, etc. The input/output interface may be a composite input/output interface formed by a plurality of interfaces.

The modem 210 receives broadcast television signals through a wired or wireless reception manner, and demodulates audio and video signals, such as EPG data signals, from a plurality of wireless or wired broadcast television signals. In some embodiments, the controller 250 and the modem 210 may be located in separate devices, i.e., the modem 210 may also be located in an external device to the main device in which the controller 250 is located, such as an external set-top box or the like.

The controller 250 controls the operation of the terminal device and responds to the user's operations through various software control programs stored in the memory. The controller 250 controls the overall operation of the terminal device 200. For example: in response to receiving a user command to select a UI object to be displayed on the display 260, the controller 250 may perform an operation related to the object selected by the user command.

In some embodiments, the controller 250 includes at least one of a central processing unit (Central Processing Unit, CPU), a video processor, an audio processor, a graphics processor (Graphics Processing Unit, GPU), RAM Random Access Memory, RAM), ROM (Read-Only Memory), first to nth interfaces for input/output, a communication Bus (Bus), and the like.

The user may initiate a media search interface on the terminal device 200 to obtain media search results, and select a target media from the media search results for viewing. As shown in FIG. 5, when a user starts a media resource search interface and does not input a search keyword, a history search word is generated in a preset area of the media resource search interface according to the search history of the user, so as to recommend keywords for searching media resource data for the user, simplify the operation of inputting keywords by the user, and save operation time.

The terminal device 200 may generate recommended history search words from the history keyword search records of the user, for example, form a time axis by search times of the history keywords, and sort the history search words according to the order of the time axis. And displaying the historical search words in a preset area of the media resource search interface according to the sequence of the historical search words. It is understood that the number of the displayed history search words may be set in the preset area, and if the number of the displayed history search words is set to 5, the first 5 history search words adjacent to the time of day on the time axis are displayed in the preset area.

In some embodiments, since the storage space of the terminal device 200 is limited, a search record of the user or a media data search log recording the search record of the user may be stored through the server 400. When the terminal device 200 receives a control instruction for the user to start the media asset search interface, the control instruction may be sent to the server 400, so as to obtain the recommendation result of the historical search word from the server 400, and display the recommendation result in the preset area of the media asset search interface.

However, in the above embodiment, the manner of ordering and displaying the historical search words according to the time axis is not combined with the actual needs of the user, so that the application value of the recommendation result of the historical search words is low, and when the user searches for the media data through the historical search words, it is difficult for the user to obtain the effective recommendation media data, resulting in poor use experience.

In some embodiments, as shown in fig. 6, the present application provides a server 400 comprising: a communication module and a processing module; wherein the communication module is configured to establish a communication connection with the terminal device 200. The processing module is configured to:

S100: responding to a control instruction sent by the terminal equipment 200 for displaying a media resource searching interface, and acquiring a media resource data searching log and a media resource data access log of the current user;

in some embodiments, the user may send a control instruction for displaying the media asset search interface to the terminal device 200 through various input modes such as voice, gesture, touch pad, remote controller, etc. After receiving the control instruction, the terminal device 200 sends the control instruction to the server 400. The server 400 queries a storage space corresponding to the user information in the control instruction according to the control instruction, and acquires the media asset data search log and the media asset data access log from the storage space.

The media asset data search logs comprise historical search words and also comprise search time of the historical search words, and the search times of the historical search words can be counted according to the media asset data search logs. The media asset data access log includes recorded information for accessing media asset data according to the historical search term. It can be understood that after the user inputs the keyword, a plurality of media data can be obtained through searching, and the media data access log comprises record information of each access to the media data. When recording information of accessing the media asset data through the historical search words is counted, the access times of the plurality of media asset data corresponding to the historical search words can be summed up, so that the total times of accessing the media asset data corresponding to the historical search words can be obtained.

Based on the characteristics of the media asset data search logs and the media asset data access logs, the media asset data search logs can be used for counting the search times, the search time and the search text of historical search words. Therefore, a historical search word ordering mode combining the influence of the search time can be formed according to the media resource data search logs. The media data access log may then form a historical search term ordering that incorporates the effects of the actual needs of the user. It can be understood that the historical search word ordering mode influenced by the search time and the historical search word ordering mode influenced by the actual requirement of the user are combined, so that the influence of the search time is considered, the actual application condition of the user is combined, and the practical value of the recommendation result of the historical search word can be improved.

In some embodiments, the user information in the control instructions includes a user id. In the storage space of the server 400, the media data search log and the media data access log corresponding to the user id may be stored according to different user ids. Thus, the server 400 may query the associated media asset data search log and media asset data access log by the user information in the control instructions, i.e. the processing module is further configured to: extracting a user id in the control instruction; querying a media asset data search log associated with the user id and a media asset data access log.

The terminal device 200 may add a user id to a control instruction sent to the server 400 according to an account number logged in by the user, and the server 400 may find a corresponding media data search log and a media data access log in the storage space according to the user id. It can be understood that the media data search logs corresponding to different user ids are different from the media data access logs, so that different recommendation weights can be formed based on the user ids to adapt to the use habits of different users, and the practicability of the recommended historical search words is improved.

S200: calculating recommendation weight according to the media resource search log and the media resource data access log;

And the recommendation weight is a weighted summation result of the searching times of the historical searching words in the media resource searching log and the media resource data access times corresponding to the historical searching words in the media resource data access log.

In some embodiments, the recommendation weight consists of a search weight and a click weight, i.e., recommendation weight = search weight + click weight. The searching weight is based on the searching times and searching time of the historical searching words, and can be used for representing the condition that a user searches media resource data through the historical searching words in a period of time, and the time characteristic is added on the basis of the searching times. The click weight is based on the access record corresponding to the media data corresponding to the historical search word, and can be used for representing the condition that the user accesses the media data corresponding to the historical search word in a period of time, and the demand (using habit) characteristics of the user are increased on the basis of the search times. Based on the characteristics of the search weight and the click weight, the recommendation weight considers the influence of the search time on the ordering of the historical search words and the influence of the user demand on the ordering of the historical search words, and is beneficial to improving the accuracy of recommending the historical search words.

In some embodiments, the processing module, when executing the generation of recommendation weights from the media asset search log and the media asset data access log, is further configured to: extracting historical search word information from the media resource search log and the media resource data access log, wherein the historical search word information comprises historical search word texts, search time of the historical search words, search times of the historical search words and access times of the historical search words corresponding to the media resource data; calculating search weights according to the search times and the time attenuation coefficient of the historical search words; the time attenuation coefficient is set according to the interval time between the search time and the current time; calculating click weight according to the access times and time attenuation coefficient of the historical search word corresponding to the media asset data; and summing the searching weight and the clicking weight to obtain a recommendation weight.

In some embodiments, it is noted in the media asset data search log that the user searches for "small x dynasty" multiple times a month ago, but did not search for "small x dynasty" in the last week, indicating that the user may not have been required to continue to view media asset data related to "small x dynasty". Therefore, based on the searching times of the historical search words, the demand degree of the user on the media data corresponding to the historical search words can be reflected according to the searching time of the historical search words.

The farther the search time is from the day's interval, the less it is able to affect the history of search term recommendations, i.e., the ability to be affected decays over time. The time attenuation coefficient can be used for describing the characteristic of the attenuation of influence capacity with time in the search weight and the click weight, so that the accuracy of the search weight and the click weight is improved, and the accuracy of the recommended weight is further improved.

As shown in fig. 7, in some embodiments, the search weight = Σ _word search times x 0.8 ⁿ; the word is a text corresponding to the historical search word, for example, the word is "small x dynasty". n is the time interval between the search time and the day, e.g., the search record seven days ago, and 7 days from the time the user initiates the display of the search interface on the day, n may be 7. Since 0.8 is smaller than 1, the larger n is, the smaller the time decay coefficient is, and the smaller the generated search weight is. It should be noted that the search weight is a sum of search weights of each history search word in each day within a certain period.

In the above embodiment, the click weight = Σ _word number of clicks x 0.8 ⁿ; it will be appreciated that the same historical search term has both search and click weights. Therefore, on the basis of the text of the historical search word, the click weight can be generated according to the click record of the user on the media data in the media data access log. The click record in the media asset data access log contains a process that the user obtains the media asset data through the keywords (historical search words), so that the number of times that the user accesses the media asset data through each historical search word can be obtained, and click weight is generated according to the number of times of access. Similar to the search weights, the click weights are also affected by the time decay, so that a time decay factor is also added when calculating the click weights.

It should be noted that "0.8" in the time attenuation coefficient may be adjusted according to practical situations, but based on the characteristic of time attenuation, the base number of the time attenuation coefficient should be smaller than 1 so as to conform to the rule that the statistical data far from the current period has less influence on the recommended data.

S300: ranking the historical search terms using the recommendation weights to generate a search term recommendation queue;

After the recommendation weights are calculated based on the media asset data search logs and the media asset data access logs, in some embodiments, the historical search terms may be ranked according to the recommendation weights, as shown in FIG. 8. For example, the recommendation weight of "large x cartoon" is 0.6, the recommendation weight of "small x dynasty" is 0.7, the recommendation weight of "music x" is 0.38, and the recommendation weight of "animal xx" is 0.45; the recommendation weight of "phase sound xx" is 0.62; according to the recommendation weight, search word recommendation queues which are arranged in a descending order can be obtained: "Small x dynasty" - "phase sound xx" - "big x cartoon" - "animal xx" - "music x".

And placing the historical search words with high recommendation weights at the front positions of the queues so as to display the historical search words with high recommendation weights preferentially. In a preset area of the media resource search interface, there may be a case where too many recommended search terms cannot be displayed due to insufficient space. At this time, based on the feature of descending order, several historical search words with higher recommendation weights can be selected from the search word recommendation queue and displayed in a preset area.

Media data such as television shows, movies, etc. have finalizable features. Even if the user searches and accesses the media data through the keywords in the adjacent time, the probability of revisiting the media data in a short time after the user finishes is low, and the search word recommendation queue is required to be optimized and adjusted according to the finishing condition of the media data. The processing module, when executing ranking the historical search terms using the recommendation weights, is therefore further configured to: extracting periodic record information from the media resource search log and the media resource data access log; and adjusting the arrangement sequence of the historical search words in the search word recommendation queue according to the periodic record information.

As can be seen from the time attenuation coefficient in the above embodiment, the influence of the historical search word generated according to the search result of the user on the same day in the recommendation weight is strongest, so that the search word recommendation queue needs to be optimized according to the search result of the user on the same day. The current search record of the user can be extracted through the media resource search log and compared with the historical search words in the search word recommendation queue.

Meanwhile, in the media asset data access record, the specific condition of the user accessing the media asset data can be recorded. For example, "small x dynasty" is a source of television drama, for a total of 35 sets. In the media asset data access log, the episode accessed by the user can be recorded, and when the user accesses the 35 th episode, the probability that the user is about to finish watching the 'small x dynasty' series episode, namely searching the 'small x dynasty' through the keyword is lower is characterized.

In addition, the server 400 may also determine whether the media asset data is completed in the network resource according to the name of the media asset data. Through whether the episode accessed by the user and the accessed media data are finished, the search word recommendation queue can be optimized and adjusted to increase the media resource characteristics in the search word recommendation queue, so that the fit degree of the search word recommendation queue and the user requirement is further improved, and the practical value of the search word recommendation queue is further improved.

The period record information comprises a search record in the current period of the historical search word, an access record of the historical search word corresponding to the media asset data and the finishing time of the historical search word corresponding to the media asset data; the processing module is used for adjusting the arrangement sequence of the historical search words in the search word recommendation queue according to the record information and is further configured to: if the search record in the current period of the historical search word is not recorded in the media resource search log, and/or media resource data corresponding to the historical search word is accessed, and/or finishing time of the media resource data corresponding to the historical search word exceeds a first preset time, moving the historical search word in the search word recommendation queue backwards according to a preset distance.

According to the embodiment, the search word recommendation queue can be optimized and adjusted by combining the current day search condition of the user, the media data ending condition corresponding to the historical search word and the viewing condition of the user on the media data.

Optimizing conditions for adjusting the search term recommendation queue may include: whether the search record in the current period of the historical search word is recorded in the media resource search log or not. The current period may be 1 day, and the weight ratio adjusted according to the operation of the user on the same day in the optimization adjustment process is higher. If the current period is 3 days, the weight ratio of the optimization adjustment process is higher according to the search operation in the user period, and it can be understood that the influence proportion of the search operation according to the user on the optimization adjustment can be adjusted by adjusting the current period so as to be suitable for more search word recommendation scenes.

Optimizing conditions for adjusting the search term recommendation queue may further include: whether the media data corresponding to the historical search word is accessed or not, and whether the finishing time of the media data corresponding to the historical search word exceeds a first preset time or not. Whether the media data has been accessed includes whether the last episode of the television episode has been accessed and whether a part of the movie/short video near the ending stage is played, so as to characterize whether the user ends the access to the media data, and further adjust the recommended position of the historical search word corresponding to the accessed media data.

The condition that whether the media asset data has been accessed or not can be combined is whether the ending time of the media asset data corresponding to the history search word exceeds a first preset time. The first preset time may be set to a plurality of time periods such as a week, a month, etc. for characterizing the ending time of the media asset data. The condition that the media asset data is finished and the condition that the media asset data is accessed by the user are combined, the probability that the user searches the related media asset data through the historical search word again can be reflected more clearly, and therefore the characteristic that the user actually views the media asset can be further increased when the search word recommendation queue is optimally adjusted, and the accuracy of the search word recommendation queue is improved.

The conditions for optimizing and adjusting the search word recommendation queue can be ' and ', or ' relation, so as to trigger adjustment of the search word queue. The matching of the optimization adjustment conditions can be selected according to the requirements of different recommended scenes so as to adapt to the different recommended scenes and improve the fit degree of the search word queue and the actual requirements of the user.

It can be understood that the execution target of the optimization adjustment is the history search word with the front position in the search word recommendation queue, namely the history search word with higher recommendation weight, and the corresponding recommendation probability is higher. Therefore, the matching degree of the historical search word and the use requirement of the user can be further improved in an optimization and adjustment mode.

In some embodiments, as shown in FIG. 8, where 10 historical search terms are included in the search term queue, optimization adjustments may be performed on the top 5 historical search terms. When the second recommended word meets the optimization adjustment condition, the position of the second recommended word is moved backwards by 5, the moved second recommended word is located at the seventh position in the queue, and the third recommended word to the seventh recommended word located behind the second recommended word are sequentially moved forwards by one position. And optimizing and adjusting the position of the recommended word with the maximum recommended probability in the search word recommendation queue screened by the recommendation weight, combining the specific condition of watching the media resource by the user, and being beneficial to improving the fit degree of the search word recommendation queue and the user.

S400: and transmitting the search word recommendation queue to the terminal equipment 200 through the communication module, so that the terminal equipment 200 displays historical search words in the search word recommendation queue on a media resource search interface.

After generating the search term recommendation queue, the server 400 may transmit the search term recommendation queue to the terminal device 200 through the communication module, and display the search term recommendation queue by the terminal device 200. It will be appreciated that the terminal device 200 requires a certain interaction time when requesting a search word recommendation queue from the server 400. In the interaction time, the recommended content may not be displayed in the preset area in the media resource search interface of the terminal device 200, or a control for representing that the search word recommendation queue is being loaded is displayed in the preset area.

To reduce the impact of interaction time on user latency, in some embodiments, as shown in fig. 9, the processing module is further configured to: extracting searching times from media data searching logs associated with user ids in the control instruction; detecting the searching behavior of the media data of the current user in a second preset time according to the searching times; if the fact that the current user has the media data searching behavior in the second preset time is detected, a new search word recommendation queue is generated based on the media data searching behavior of the current user.

The second preset time is a shorter time period than the first preset time, and is used for judging whether a new search word recommendation queue needs to be generated when the user starts the media data search interface, so as to reduce the interaction time of the terminal device 200 and the server 400, and further reduce the waiting time of the user.

In some embodiments, after receiving the control instruction of the terminal device 200, the server 400 queries the search record of the current user in the media data search log according to the user id of the current user, and finds that the current user has the search record within one hour. The server 400 performs the steps of calculating a recommendation weight, generating a search word recommendation queue, and optimally adjusting the search word recommendation queue based on the most recent search record of the current user. And transmits the newly generated search term recommendation queue to the terminal device 200 for display.

Wherein one hour corresponds to a second preset time, and the search record of the user is closest to the user's use requirement in a shorter period of time, which indicates that the user may have a new use requirement. Therefore, the search word recommendation queue needs to be regenerated to ensure the accuracy of the search word recommendation queue, namely the degree of agreement with the actual demands of the users. It will be appreciated that the second preset time may also be set to a half hour, three hours, etc. period to accommodate different recommended scenarios.

In other embodiments, the server 400 does not find that the current user has a search record within one hour, and cannot determine the current requirement type of the user, so that the current search term recommendation queue may be transmitted to the terminal device 200 for display. That is, the server 400 further includes a storage module configured to store a search term recommendation queue associated with a user id according to the user id. The processing module is further configured to: if the fact that the current user has the media data searching behavior in the second preset time is not detected, locating a storage space associated with the current user id; extracting a search word recommendation queue from a storage space associated with the current user id, and transmitting the extracted search word recommendation queue to the terminal device 200.

In the storage module, the user id is taken as a storage unit, and a search word recommendation queue associated with the user id can be stored. When the requirement type of the current user cannot be judged, the search word recommendation queue stored in the storage module can be called through the user id of the current user. It will be appreciated that when generating a new search term recommendation queue, the server 400 will also store the new search term recommendation queue in the storage module according to the user id.

On the basis of failing to identify the current user demand type, the interaction time between the terminal device 200 and the server 400 can be reduced by calling the search word recommendation queue in the storage module, so that the waiting time of the user is reduced, and the use experience of the user is improved.

In some embodiments, the present application provides a terminal device 200 comprising: a display 260; a communicator 220 configured to establish a communication connection with the server 400; a controller 250 configured to:

Responding to a control instruction input by a user and used for displaying a media resource searching interface, and sending the control instruction to a server 400, so that the server 400 generates recommendation weights according to a media resource data searching log and a media resource data access log of the current user, and orders historical searching words in the media resource data searching log according to the recommendation weights to generate a searching word recommendation queue;

Receiving a search word recommendation queue returned by the server 400;

It may be appreciated that, in some embodiments, as shown in fig. 10, in the control instruction sent by the terminal device 200 to the server 400, a preset area that may include the media resource search interface may display the number of recommended words, and the server 400 may select, according to the number of recommended words, a number of recommended words that matches the number of recommended words in the generated list of recommended search words, and send the recommended words to the terminal device 200 for display. For example, the server 400 obtains 3 historical recommended words that can be displayed on the preset area of the terminal device 200 according to the control instruction, and the server 400 selects "small x dynasty", "phase sound xx", and "large x animation" from the recommended queue of the recommended words, and sends the selected "small x dynasty", "phase sound xx", and the selected large x animation "to the terminal device 200 for display, so as to reduce the processing procedure of the terminal device 200.

In other embodiments, as shown in fig. 11, after receiving the search term recommendation queue sent by the server 400, the terminal device 200 may extract, according to the number of recommended terms displayable in the preset area, a number of recommended terms from the search term recommendation queue for display. For example, if the number of realistic recommended words in the preset area is 3, selecting "phase sound xx" and "large x cartoon" from the search word recommendation queue to display.

Based on the above embodiment, in order to further simplify the operation flow of the user, the number of displayable recommended words may be increased by setting the area of the preset area/the recommended word font size in the media searching interface of the terminal device 200. As shown in fig. 12, if the number of recommended words displayable in the adjusted preset area is 5, the terminal device 200 will increase and display "animal xx" and "x of music" in the preset area. It will be appreciated that the preset area may also be set as an expandable area, and when the user selects the focus frame for expanding the hidden portion, the hidden portion of the preset area expands, and "animal xx" and "x of music" are displayed.

In some embodiments, the present application provides another terminal device 200, comprising: a display 260; a controller 250 configured to:

responding to a control instruction input by a user and used for displaying a media resource searching interface, and acquiring a media resource data searching log and a media resource data access log of the current user; the media asset data search log comprises historical search words; the media asset data access log comprises record information of accessing media asset data according to the historical search word;

Some terminal devices 200 with high power and high computing power may perform functions similar to those performed by the server 400 in the above-described embodiment of the server 400. It will be appreciated that the terminal device 200 also has a related function of performing the adjustment of the preset area by the terminal device 200 to control the display of the recommended search term in the above-described embodiment of the terminal device 200.

In some embodiments, the present application provides a media recommendation method, including:

responding to a control instruction sent by the terminal equipment 200 for displaying a media resource searching interface, and acquiring a media resource data searching log and a media resource data access log of the current user; the media asset data search log comprises historical search words; the media asset data access log comprises record information of accessing media asset data according to the historical search word;

And transmitting the search word recommendation queue to the terminal equipment 200, so that the terminal equipment 200 displays the historical search words in the search word recommendation queue in a preset area of a media resource search interface.

The application provides a server 400 and a media asset recommendation method, wherein the server 400 acquires a media asset data search log and a media asset data access log of a current user according to a control instruction sent by a terminal device 200, and calculates recommendation weights according to the media asset data search log and the media asset data access log. The recommendation weights are used to rank historical search terms in the media asset data search logs to generate a search term recommendation queue. After generating the search term recommendation queue, the server 400 transmits the search term recommendation queue to the terminal device 200, so that the terminal device 200 displays the historical search terms in the search term recommendation queue on the media resource search interface. The server 400 combines the search frequency and the access frequency of the historical search words of the user to generate recommendation weights for ordering the historical search words, and the recommendation weights are attached to the application requirements of the user, so that the recommendation values of the historical search words are improved.

It will be apparent to those skilled in the art that the techniques of embodiments of the present invention may be implemented in software plus a necessary general purpose hardware platform. Based on such understanding, the technical solutions in the embodiments of the present invention may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, in essence or contributing to the prior art.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; the foregoing description, for purposes of explanation, has been presented in conjunction with specific embodiments. The illustrative discussions above are not intended to be exhaustive or to limit the embodiments to the precise forms disclosed above. Many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the present disclosure and to enable others skilled in the art to best utilize the embodiments.

Claims

1.A server, comprising:

A communication module configured to establish a communication connection with a terminal device;

a processing module configured to:

2. The server of claim 1, wherein the processing module performs generating recommendation weights from the media asset search log and the media asset data access log, further configured to:

3. The server of claim 1, wherein the processing module performs ranking the historical search terms using the recommendation weights, further configured to:

4. The server of claim 3, wherein the period record information includes a search record in a current period of the historical search term, an access record of the historical search term to the media asset data, and a closing time of the historical search term to the media asset data; the processing module is used for adjusting the arrangement sequence of the historical search words in the search word recommendation queue according to the record information and is further configured to:

5. The server of claim 1, wherein the processing module is further configured to:

extracting a user id in the control instruction;

6. The server of claim 1, wherein the processing module is further configured to:

7. The server of claim 6, further comprising a storage module configured to store a search term recommendation queue associated with a user id based on the user id; the processing module is further configured to:

8. A terminal device, comprising:

a display;

a communicator configured to establish a communication connection with a server;

A controller configured to:

Receiving a search word recommendation queue returned by the server;

9. A terminal device, comprising:

a display;

A controller configured to:

10. The media asset recommendation method is applied to a server and is characterized by comprising the following steps: