CN117540046A - Search library construction method and device, search method and device and electronic equipment - Google Patents

Abstract

The application discloses a method and a device for constructing a search library, a method and a device for searching, and electronic equipment, and relates to the technical field of searching. The construction method of the search library comprises the following steps: in the full-scale search library, first music information used in the media content is identified. And identifying second music information newly added in the first time period in the full-quantity search library. A target search library is constructed based on the first music information and the second music information.

Description

Search library construction method and device, search method and device and electronic equipment

Technical Field

The present invention relates to the field of search technologies, and in particular, to a method and an apparatus for constructing a search library, a method and an apparatus for searching, and an electronic device.

Background

Aiming at the audio corresponding to the media content, the retrieval scanning is directly carried out in a full-volume retrieval library, the music information corresponding to the audio is obtained, the full-volume retrieval library at least comprises a large amount of music information, and the retrieval cost is very high. If the materials in the full search library are directly reduced, a large amount of media contents cannot be identified, and therefore downstream copyright reporting and settlement are affected.

Disclosure of Invention

An object of embodiments according to the present application is to provide a method and an apparatus for constructing a search library, a method and an apparatus for searching, and an electronic device, which can solve the problem of reducing search cost without reducing UGC identification coverage.

In a first aspect, according to an embodiment of the present application, there is provided a method for constructing a search library, including: in the full-scale search library, first music information used in the media content is identified. And identifying second music information newly added in the first time period in the full-quantity search library. A target search library is constructed based on the first music information and the second music information.

In a second aspect, according to an embodiment of the present application, there is provided a retrieval method, including: based on the media content, audio is acquired. And carrying out real-time retrieval in a target retrieval library based on the audio frequency. And under the condition that the result is retrieved, obtaining the music information corresponding to the audio.

In a third aspect, according to an embodiment of the present application, there is provided a construction apparatus for a search library, including a first identification module, a second identification module, and a construction module. The first identification module is used for identifying the first music information used in the media content in the full search library. The second identification module is used for identifying second music information newly added in the first time period in the full search library. The construction module is used for constructing a target retrieval library based on the first music information and the second music information.

In a fourth aspect, according to an embodiment of the present application, there is provided a retrieval device including a first acquisition module, a retrieval module, and a second acquisition module. The first acquisition module is used for acquiring audio based on the media content. The retrieval module is used for carrying out real-time retrieval in the target retrieval library based on the audio frequency. The second acquisition module is used for obtaining music information corresponding to the audio under the condition that the result is retrieved.

In a fifth aspect, according to an embodiment of the present application, there is provided an electronic device including a processor and a memory storing a program or instructions executable on the processor, the program or instructions implementing steps of a construction method of a search pool as in the first aspect or steps of a search method as in the second aspect when executed by the processor.

In a sixth aspect, according to an embodiment of the present application, there is provided a readable storage medium on which a program or an instruction is stored, which when executed by a processor, implements steps of a method of constructing a search pool as in the first aspect or steps of a method of searching as in the second aspect.

In some embodiments of the present application, a target search library is generated by identifying first music information used in media content, identifying second music information newly added within a first time period. For media content, real-time retrieval is performed through a target retrieval library, so that the retrieval cost can be reduced under the condition that the media content identification coverage is not affected, and meanwhile, the fact that the media content identification coverage is not negative is realized.

Drawings

FIG. 1 shows one of the flow diagrams of the method for constructing a search pool provided according to an embodiment of the present application;

FIG. 2 shows a second flow diagram of a method of constructing a search pool according to an embodiment of the present application;

FIG. 3 is a third flow chart of a method for constructing a search pool according to an embodiment of the present application;

FIG. 4 shows a fourth flow diagram of a method of constructing a search pool provided in accordance with an embodiment of the present application;

FIG. 5 shows a fifth flow diagram of a method of constructing a search pool provided in accordance with an embodiment of the present application;

FIG. 6 shows one of the flow diagrams of the retrieval method provided according to an embodiment of the present application;

FIG. 7 shows a second flow diagram of a search method provided according to an embodiment of the present application;

FIG. 8 illustrates a third flow diagram of a retrieval method provided in accordance with an embodiment of the present application;

FIG. 9 shows a fourth flow diagram of a retrieval method provided in accordance with an embodiment of the present application;

FIG. 10 shows a block diagram of a construction apparatus of a search pool provided according to an embodiment of the present application;

FIG. 11 shows a block diagram of a retrieval device provided in accordance with an embodiment of the present application;

FIG. 12 shows a block diagram of an electronic device provided in accordance with an embodiment of the present application;

fig. 13 shows a hardware configuration diagram of an electronic device according to an embodiment of the present application;

FIG. 14 is a flow chart of a method for creating, updating, or deleting a library according to an embodiment of the present application;

FIG. 15 shows a schematic flow chart of a compensation scanning method provided according to an embodiment of the present application;

FIG. 16 illustrates a framework diagram of the construction and retrieval of a target retrieval library provided in accordance with an embodiment of the present application.

The correspondence between the reference numerals and the component names in fig. 10 to 16 is:

100: a search library constructing device; 110: a first identification module; 120: a second identification module; 130: constructing a module; 200: a search device; 210: a first acquisition module; 220: a retrieval module; 230: a second acquisition module; 300: a full-quantity search library; 302: a target search library; 304: UGC contribution; 306: newly warehousing songs; 308: history is associated; 310: historical postings; 312: a special copyright party; 314: high quality; 316: the new song is a hot song; 318: compensating and searching; 320: high heat flyback; 1000: an electronic device; 1002: a processor; 1004: a memory; 1100: an electronic device; 1101: a radio frequency unit; 1102: a network module; 1103: an audio output unit; 1104: a first input unit; 11041: a graphics processor; 11042: a microphone; 1105: a sensor; 1106: a display unit; 11061: a display panel; 1107: a second input unit; 11071: a touch panel; 11072: other input devices; 1108: an interface unit; 1109: a memory; 1110: a processor.

Detailed Description

Technical solutions according to embodiments of the present application will be clearly described below with reference to the drawings in embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application are within the scope of the protection of the present application.

The terms first, second and the like in the description and in the claims, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type and not limited to the number of objects, e.g., the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.

The method and apparatus for constructing the search library, the method and apparatus for searching, and the electronic device provided in the embodiments of the present application are described in detail below with reference to fig. 1 to 16 through specific embodiments and application scenarios thereof.

According to an embodiment of the present application, there is provided a method for constructing a search library, and fig. 1 shows one of flow diagrams of the method for constructing a search library according to the embodiment of the present application, as shown in fig. 1, the method for constructing a search library includes:

step S102, in the full search library, the first music information used in the media content is identified.

Step S104, identifying second music information newly added in the first time period in the full-quantity search library.

Step S106, a target retrieval library is constructed based on the first music information and the second music information.

It can be understood that in the short video application scenario, after the short video is acquired, the sound in the short video is extracted to obtain the corresponding audio, and based on the audio, the full search library is scanned to acquire the music information contained in the audio, so that the search cost of the scanning mode is very high. If the materials in the search library are reduced, the search cost can be reduced, but many multimedia contents (which can be understood as short videos obtained) have no corresponding recognition results, and the reporting and settlement of copyrights are directly affected.

In some embodiments of the present application, in the full-scale search library, the first music information used in the media content is identified, for example, the media content may include user generated content (User Generated Content, abbreviated as UGC) or professional produced content (Professional Generated Content, abbreviated as PGC), specifically, UGC refers to that music is included in the video itself, the first music information used by UGC may also be understood as that the first music information is consumed by UGC, if the UGC includes only a certain segment of music, the whole music information is obtained by searching through a certain segment, and it may be understood as that the UGC history is associated. The PGC refers to selecting specific music to be added into the video, and the first music information used in the PGC can also be understood as that the first music information is consumed by the PGC, i.e. the history is posted. For example, when uploading a video on a short video platform, if the video itself contains music, the corresponding UGC corresponds to the PGC if the music is selected for addition. Through historical consumption, screening is carried out in a full-scale search library to obtain consumed music information, and the consumed music information is added into a target search library, so that a part of frequently consumed music information can be added into the target search library, and the search cost is effectively reduced.

In some embodiments of the present application, in the full-scale search library, the second music information newly added in the first period is identified, the second music information is added to the target search library, and whether the newly added music is used or not cannot be judged in the first period, and from the perspective of risk control, the new song is added to the target search library, so that the probability that the new song is not searched can be reduced, and the search coverage rate is improved.

In some embodiments of the present application, the specific time length of the first time period may be set according to the service scenario requirement. For example, the time unit may be day, and the selection is performed after the combination of the factors such as the accuracy requirement, the cost requirement, the risk control requirement, and the like of the service.

In some embodiments of the present application, it is understood that the music information in the target search pool is contained in the full search pool. The target search library and the full search library can be applied in different application scenarios. For example, in the case of requiring a large amount of search services, the search can be performed through the target search library, so that the search cost is effectively reduced. For the case of a small amount of search services, the search can also be directly performed through a full-scale search library.

In some embodiments of the present application, by identifying first music information used in media content, identifying second music information newly added in a first period of time, and generating a target search library, search cost can be reduced without affecting media content identification coverage, and no negative UGC identification coverage is achieved.

In some embodiments of the present application, it may be understood that the first music information and the second music information process the stock portion of the full-scale search pool, so as to obtain the target search pool, and for the increment portion, update the target search pool is required.

In some embodiments of the present application, optionally, fig. 2 shows a second flowchart of a method for constructing a search pool according to an embodiment of the present application, as shown in fig. 2, and the method for constructing a target search pool based on the first music information and the second music information includes:

in step S202, third music information that does not meet the target requirement is identified among the first music information and the second music information.

Step S204, deleting the third music information in the first music information and the second music information, and constructing a target retrieval library.

In some embodiments of the present application, for the first music information and the second music information having historical consumption, it is identified whether they meet the target requirement, and if they do not meet the target requirement, the music information cannot enter the target search library even if there is historical consumption. For example, the target requirement may be a preset copyright requirement set for the aspect of copyright, specifically, for the first music information and the second music information having history of consumption, the copyright condition is identified, and if the copyright does not meet the target requirement (i.e., the preset copyright requirement), the music information cannot enter the target retrieval library even if the history of consumption has occurred. The method comprises the steps of setting a copyright tag for music information, judging whether the music information meets the copyright requirement or not by identifying the copyright tag, and further judging whether the music information can enter a target retrieval library or not. By the method, the target search library can be adjusted based on the business requirement and the copyright requirement, so that the search precision is improved.

In some embodiments of the present application, an exemption policy may exist for the copyright party, and music information with the exemption policy may be preferentially added to the target search library.

In some embodiments of the present application, optionally, fig. 3 shows a third flowchart of a method for constructing a search pool according to an embodiment of the present application, where, as shown in fig. 3, a target search pool is constructed based on the first music information and the second music information, and further includes:

step S302, identifying blank segment proportion in the audio according to the audio corresponding to the first music information and the second music information.

Step S304, fourth music information of which the blank segment proportion does not accord with the preset proportion requirement is obtained.

Step S306, deleting fourth music information in the first music information and the second music information, and constructing a target retrieval library.

In some embodiments of the present application, according to information such as a service requirement and an accuracy requirement, a ratio requirement may be preset, and corresponding unsatisfactory music information in the first music information and the second music information may be identified and deleted from the target search library. For example, for a piece of a-minute audio, where B-minute has music and the remaining C-minutes are blank segments, the blank segments are in an excessive proportion, and if they are added to the target search library, a large amount of music-free video will be matched to the audio, and the matching will be remembered as abnormal, thus decreasing the search accuracy.

In some embodiments of the present application, high-quality music information meeting the service requirement can be preferentially added to the target retrieval library.

In some embodiments of the present application, optionally, fig. 4 shows a fourth flow chart of a method for constructing a search pool according to an embodiment of the present application, where, as shown in fig. 4, the method for constructing a search pool further includes:

step S402, every second time period, obtaining fifth music information newly added in the second time period by the full-quantity search library.

Step S404, updating the target retrieval library based on the fifth music information.

In some embodiments of the present application, based on the full-scale search library, for the stock portion, the first music information and the second music information are acquired, and the target search library is constructed, and for the incremental portion of the full-scale search library, identification is performed once every second time period, and newly added music information in the second time period is identified, and is added to the target search library, so that updating of the target search library is achieved. The newly added music in the second time period cannot be judged whether to be used or not, and from the perspective of risk control, the newly added music is added to the target retrieval library, so that the probability that a new song is not retrieved can be reduced, and the retrieval coverage rate is improved.

In some embodiments of the present application, the specific time length of the second time period may be set according to the service scenario requirement. For example, the time unit may be day, and the selection is performed after the combination of the factors such as the accuracy requirement, the cost requirement, the risk control requirement, and the like of the service.

In some embodiments of the present application, optionally, fig. 5 shows a fifth flow chart of a method for constructing a search pool according to an embodiment of the present application, where, as shown in fig. 5, the method for constructing a search pool further includes:

in step S502, in the target search pool, sixth music information that has not been used by the media content in the third period of time is identified.

Step S504, deleting the sixth music information from the target retrieval library.

In some embodiments of the present application, every second time period, newly added fifth music information is identified and added to the target search pool, which means that every second time period, a part of music information may be added to the target search pool, which may cause more and more music information in the target search pool to cause continuous expansion of the target search pool, and for the above situation, dynamic logic is adopted to identify sixth music information which is not consumed or associated in the third time period in the target search pool, delete the sixth music information from the target search pool, and enter the full search pool. Through the operation, the number of music information in the target search library can be dynamically adjusted, and the media content identification coverage rate is ensured under the condition of ensuring the search cost.

In some embodiments of the present application, the specific time length of the third time period may be set according to the service scenario requirement. For example, the time unit may be day, and the selection is performed after the combination of the factors such as the accuracy requirement, the cost requirement, the risk control requirement, and the like of the service.

In some embodiments of the present application, optionally, the method for constructing the search library further includes:

when the audio corresponding to the media content retrieves the seventh music information in the full-scale retrieval library, the target retrieval library is updated based on the seventh music information.

In some embodiments of the present application, every second time period, newly added fifth music information is identified and added to a target search library, in the target search library, sixth music information which is not consumed or associated in a third time period is identified and deleted from the target search library, and the above process adopts dynamic logic to dynamically adjust the target search library, wherein the method further includes, when the seventh music information is searched in the full search library by media content, adding the seventh music information to the target search library, so as to realize interaction between the full search library and the target search library, and ensure the identification coverage rate of the media content under the condition of ensuring the search cost. For example, for media content (media content may be UGC), firstly, searching is performed in a target search library, if no search result is found, searching is performed in a full search library under a certain condition, that is, compensation search is performed, and after the search result is found, the searched music information is added to the target search library, so as to realize dynamic adjustment of the target search library.

In some embodiments of the present application, for example, for cold music, there is in the full search pool, but not in the target search pool, if there is media content using this music, it is possible to retrieve the music information in the full search pool at the time of the compensation search, at which time the music information matches the media content, and the above music information is added to the target search pool in conformity with the used condition.

In some embodiments of the present application, optionally, the method for constructing the search library further includes:

and constructing, deleting or updating the full search library or the target search library through the service and the interface.

In some embodiments of the present application, the full search pool or the target search pool may be considered a single repository. For example, as shown in fig. 14, the method for creating, updating or deleting the library may include:

in step S1002, each audio is provided with a clip.

The clip includes a clip and a full-track clip, for example, for a piece of music, the full-track clip may be the whole piece of music, and the clip may be the climax of the piece of music.

Step S1004, determining whether creation, update or deletion of a fragment occurs.

If the creation, update or deletion of the fragment occurs, the process advances to step S1006.

In step S1006, the change service is multiplexed to extract all the music related to the clip.

The music is metaong, and the metaong only contains information, and the metaong may contain a clip and a clip, for example, for a piece of music, it corresponds to a metaong, and the metaong includes the clip and the clip.

Step S1008, calling a service interface to acquire music information and audio connection.

Step S1010, calling an audio fingerprint service to create, update or delete the material library.

According to an embodiment of the present application, a search method is provided, and fig. 6 shows one of flow diagrams of the search method provided according to the embodiment of the present application, as shown in fig. 6, the search method includes:

step S602, based on the media content, acquires audio.

Step S604, performing real-time search in the target search library based on the audio.

Step S606, when the result is retrieved, the music information corresponding to the audio is obtained.

It can be understood that in the short video application scenario, after the short video is acquired, the sound in the short video is extracted to obtain the corresponding audio, and based on the audio, the full search library is scanned to acquire the music information contained in the audio, so that the search cost of the scanning mode is very high. If materials in the search library are reduced, the search cost can be reduced, but a plurality of UGC cannot have corresponding identification results, and the reporting and settlement of copyrights are directly affected.

In some embodiments of the present application, audio is acquired through media content, real-time retrieval is performed in a target retrieval library based on the audio, and music information corresponding to the audio is obtained when a result is retrieved. For real-time retrieval of media content, the media content is retrieved in a target retrieval library, the cost is greatly reduced without affecting the media content identification coverage, and meanwhile, the media content identification coverage is not negative, for example, the media content can comprise UGC.

In some embodiments of the present application, for media content, real-time retrieval through a target retrieval library may reduce retrieval costs without affecting media content identification coverage.

In some embodiments of the present application, optionally, fig. 7 shows a second flowchart of a search method provided according to an embodiment of the present application, as shown in fig. 7, where the search method further includes:

step S702, under the condition that the result is not retrieved, a first data index corresponding to the audio in the first time dimension is obtained.

In step S704, when the first data index meets the first requirement, the search is performed in the full-scale search library.

It will be appreciated that an increasing amount of video is being retrieved daily, with UGC, through the target retrieval library, possibly covering a substantial portion, and a small portion not covering, with respect to the non-covering situation, a portion, possibly without music, and a portion, possibly with history of non-consumed cool songs, which may present a business risk if not handled for such a situation.

In some embodiments of the present application, to avoid cold music that has never been consumed in the history, a sudden use is made at a time, resulting in an unrecognizable risk, a compensation search is proposed. The method specifically comprises the following steps: in order to search UGC in a target search library in real time, under the condition that a result is not searched, acquiring a first data index corresponding to the audio in a first time dimension, and if the first data index meets a first requirement, performing compensation search, namely searching in a full search library, thereby guaranteeing the identification coverage rate.

In some embodiments of the present application, the first time dimension may include year, month, day, hour, minute, second, and the like, and the first time dimension may be set according to the business scenario requirements. For example, the time unit may be day, and the selection is performed after the combination of the factors such as the accuracy requirement, the cost requirement, the risk control requirement, and the like of the service.

In some embodiments of the present application, the first data index may include a browsing amount, a praise amount, a collection amount, a forwarding amount, a comment amount, and the like. For example, when the first time dimension is a day, the first data index is a browsing amount, and the browsing amount in the day dimension (in the day dimension) is larger than D, compensation search is performed for no search result.

In some embodiments of the present application, for the browsing amount of the video, the browsing amount of most of the video days does not exceed E, and a percentage value of E may be selected as the first data index, so that the identification coverage rate of UGC is ensured by setting the first data index, and then the search cost is reduced without affecting the identification coverage of UGC.

In some embodiments of the present application, optionally, fig. 8 shows a third flowchart of a search method provided according to an embodiment of the present application, where, as shown in fig. 8, in a case where the first data index meets the first requirement, searching in the full-scale search repository includes:

step S802, under the condition that the first data index meets the first requirement, acquiring an audio retrieval tag.

In step S804, when the search tag does not include the full search pool search tag, the full search pool is searched.

In some embodiments of the present application, in a case where the first data index meets the first requirement, as shown in fig. 15, the compensation scanning method may include, for audio corresponding to the video:

step S1102, obtaining audio corresponding to the video, identifying the audio, and obtaining music corresponding to the audio.

The audio corresponding to the video may be music ID, and the music may be meta.

Step S1104, determining whether three constraint conditions are satisfied.

Three constraints include: firstly, the video needs to be UGC, secondly, the creation time needs to be on line in the requirement (namely after the compensation search is on line), and thirdly, the compensation scanning strategy can be hit without the full-scale search library mark (namely without the full-scale search library search label) and meeting the three conditions.

Step S1106, a full search library scan is performed.

Scan links that compensate for scan and high thermal retrace can be multiplexed. By compensating the scanning, the traffic risk can be reduced to a very low level.

In some embodiments of the present application, optionally, fig. 9 shows a fourth flow chart of a search method provided according to an embodiment of the present application, as shown in fig. 9, where the search method further includes:

step S902, under the condition that the result is not retrieved, acquiring a second data index corresponding to the audio in a second time dimension.

In step S904, if the second data index meets the second requirement, the target search library is searched.

In step S906, when the target search library does not search the result, the search is performed in the full-scale search library.

In some embodiments of the present application, the second time dimension may include year, month, day, hour, minute, second, and the like, and the second time dimension may be set according to the business scenario requirements. For example, the time unit may be a week, and is selected according to various factors such as accuracy requirement, cost requirement, risk control requirement, etc. of the service in combination with the judgment.

In some embodiments of the present application, the second data index may include a browsing amount, a praise amount, a collection amount, a forwarding amount, a comment amount, and the like. For example, when the second time dimension is a week, the second data index is a browsing amount, and when there is no search result and the browsing amount in the week dimension (in the week dimension) is greater than F, the whole search is performed again, and the search is performed first in the target search pool, and if there is no search result, the search is performed in the whole search pool, and the above process may also be called high-heat retrace.

In some embodiments of the present application, the high-heat retrace refers to a video that is not identified and retrieved when sent, but, through the display of the second data index, the heat of the video in the second time dimension is relatively high, if there is no identification result, a relatively large influence may be brought, and for this case, UGC needs to be retrieved once again, and since the full-scale search library and the target search library are updated, the retrieval result of each retrieval may be different, and through the high-heat retrace, it can be ensured that the retrieval result of the hot video is retrieved in the latest search library.

In some embodiments of the present application, the search of most UGC is solved by real-time search, and for the case of few results, the recognition coverage rate of UGC can be ensured by compensating scanning and high-heat flyback, so that the search cost is reduced without affecting the recognition coverage of UGC.

In some embodiments of the present application, the construction of the target search pool and the search of a specific framework are shown in fig. 16, and first, the construction of the target search pool 302 includes the following aspects:

(1) Establishing a target retrieval library 302: the original content of the circled target search library 302 includes:

in the full-scale search library 300, the full-scale songs (songs contained in the first music information) identified by the historical UGC enter the target search library 302. Where songs refer to UGC consumption, history is associated 308.

In the full-scale search library 300, songs used by the history PGC (songs contained in the first music information) enter the target search library 302. Where songs refer to PGC consumption, histories have contribution 310.

In the full-volume search library 300, for a new song hot song 316 (Release Time), a new song (new song, i.e., second music information) newly put in storage in the first period of Time enters the target search library 302.

For music of a special copyright party 312 (Label Pool), songs meeting the copyright demand are put in storage (target search Pool 302) according to the copyright demand, and songs not meeting the copyright demand are deleted (target search Pool 302).

For High-Quality 314 (High-Quality) music, songs meeting the Quality requirements (target search library 302) are put in storage according to the Quality requirements (i.e., blank segment proportion), and songs not meeting the copyright requirements are deleted (target search library 302).

The corresponding stock part.

(2) Dynamic adjustment of the target search library 302, including:

the incremental songs are all put in storage, and every second time period, songs (newly put in storage 306, here, songs newly put in the full-size search library 300) newly added in the full-size search library 300 in the second time period are acquired, and enter the target search library 302.

In the target search library 302, songs that are not associated with UGC in the third time period are deleted from the target search library 302 and enter the full search library 300.

Songs identified by UGC in the compensation search 318 are added to the target search library 302, i.e., songs that result in a match are added to the target search library 302.

The corresponding increment portion.

Second, the search includes the following aspects:

(1) The real-time retrieval includes:

for UGC contribution 304, real-time retrieval is performed through target retrieval library 302, which can greatly reduce cost.

(2) The compensation search 318 includes:

when the real-time search of UGC contribution 304 does not have a search result, when the first data index corresponding to the first time dimension meets the requirement, scanning a full-scale search library 300, namely compensating search 318, and performing full-scale search at the moment to ensure UGC identification coverage. Wherein the compensation retrieval 318 may be real-time or near real-time.

(3) The high heat flyback 320 includes:

when the real-time search of the UGC contribution 304 does not have a search result, the search is performed again when the second data index corresponding to the second time dimension meets the requirement, the target search library 302 is scanned first, and if no result is found, the full-scale search library 300 is scanned again, so that the influence caused by the fact that the high-heat UGC contribution 304 does not have a search result can be reduced.

In some embodiments of the present application, the target retrieval library 302 dynamically adjusts policies including: the non-consumption database establishment refers to target core database establishment of stock part, the dynamic database storage refers to incremental song database storage of incremental part, and the dynamic database storage according to consumption behavior refers to deletion of songs which are not correlated by UGC in a third time period and generation of matched songs to be added to target retrieval database 302. The search strategy comprises the following steps: real-time retrieval, compensation scanning, and high heat retrace 320. Some embodiments of the present application greatly reduce retrieval costs without reducing on-line UGC identification coverage, while having no negative going on UGC identification coverage.

According to the method for constructing the search library provided by the embodiment of the application, the execution subject can be a device for constructing the search library. In the embodiments of the present application, a method for constructing a search library is described by taking an example in which a search library constructing apparatus executes a search library constructing method.

There is provided a construction apparatus of a search library according to an embodiment of the present application, and fig. 10 shows a block diagram of a construction apparatus of a search library according to an embodiment of the present application, and as shown in fig. 10, a construction apparatus 100 of a search library includes a first identification module 110, a second identification module 120, and a construction module 130. The first identifying module 110 is configured to identify, in the full search library, first music information that has been used in the media content. The second identifying module 120 is configured to identify, in the full-scale search library, the second music information newly added in the first period. The construction module 130 is configured to construct a target search library based on the first music information and the second music information.

In some embodiments of the present application, in the full-scale search library, the second music information newly added in the first period is identified, the second music information is added to the target search library, and whether the newly added music is used or not cannot be judged in the first period, and from the perspective of risk control, the new song is added to the target search library, so that the probability that the new song is not searched can be reduced, and the search coverage rate is improved.

The device 100 for constructing a search library according to the embodiment of the present application may implement each process of the above embodiment of the method for constructing a search library, and may achieve the same technical effects, so that repetition is avoided and no description is repeated here.

According to the retrieval method provided by the embodiment of the application, the execution subject can be a retrieval device. In the embodiments according to the present application, a search method performed by a search device is taken as an example, and the search device provided in the embodiments according to the present application is described.

There is provided a retrieval device according to an embodiment of the present application, and fig. 11 shows a block diagram of a retrieval device according to an embodiment of the present application, and as shown in fig. 11, a retrieval device 200 includes a first acquisition module 210, a retrieval module 220, and a second acquisition module 230. The first acquisition module 210 is configured to acquire audio based on media content. The retrieval module 220 is configured to perform real-time retrieval in the target retrieval library based on the audio. The second obtaining module 230 is configured to obtain music information corresponding to the audio when the result is retrieved.

In some embodiments of the present application, audio is acquired through media content, real-time retrieval is performed in a target retrieval library based on the audio, and music information corresponding to the audio is obtained when a result is retrieved. And the real-time search of the UGC is performed in a target search library, so that the cost is greatly reduced under the condition that the UGC identification coverage rate is not influenced, and meanwhile, the UGC identification coverage is not negative.

The retrieving apparatus 200 provided according to the embodiments of the present application may implement each process of the foregoing retrieving method embodiments, and may achieve the same technical effects, and for avoiding repetition, a detailed description is omitted herein.

The construction device or the search device of the search library according to the embodiment of the present application may be an electronic device, or may be a component in an electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal, or may be other devices than a terminal. By way of example, the electronic device may be a cell phone, tablet computer, notebook computer, palm computer, vehicle mounted electronic device, mobile internet appliance (Mobile Internet Device, MID), augmented reality (augmented reality, AR)/Virtual Reality (VR) device, robot, wearable device, ultra-mobile personal computer, UMPC, netbook or personal digital assistant (personal digital assistant, PDA), etc., but may also be a server, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (TV), teller machine or self-service machine, etc., without specific limitation according to embodiments of the present application.

The construction device or the retrieval device of the retrieval library in the embodiment according to the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited according to the embodiments of the present application.

Optionally, as shown in fig. 12, according to an embodiment of the present application, there is further provided an electronic device 1000, where the electronic device 1000 includes a processor 1002 and a memory 1004, and a program or an instruction that can be executed on the processor 1002 is stored in the memory 1004, and when the program or the instruction is executed by the processor 1002, the program or the instruction implements each step of the above-mentioned method for constructing the search library or the method for searching an embodiment, and the same technical effects can be achieved, so that repetition is avoided, and no further description is given here.

It should be noted that, the electronic device in the embodiment according to the present application includes the mobile electronic device and the non-mobile electronic device described above.

Fig. 13 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application.

The electronic device 1100 includes, but is not limited to: radio frequency unit 1101, network module 1102, audio output unit 1103, first input unit 1104, sensor 1105, display unit 1106, second input unit 1107, interface unit 1108, memory 1109, and processor 1110.

Those skilled in the art will appreciate that the electronic device 1100 may further include a power source (e.g., a battery) for powering the various components, which may be logically connected to the processor 1110 by a power management system, such as to perform functions such as managing charging, discharging, and power consumption by the power management system. The electronic device structure shown in fig. 13 does not constitute a limitation of the electronic device, and the electronic device may include more or less components than shown, or may combine certain components, or may be arranged in different components, which are not described in detail herein.

Wherein, for the method of constructing the search pool, the processor 1110 is configured to identify, in the full-scale search pool, the first music information used in the media content.

A processor 1110 is configured to identify, in the full search pool, second music information that is newly added in the first period.

A processor 1110 for constructing a target search library based on the first music information and the second music information.

Wherein, for the retrieval method, the processor 1110 is configured to obtain audio based on the media content.

A processor 1110 for performing real-time retrieval in a target retrieval library based on the audio.

And a processor 1110 for obtaining music information corresponding to the audio when the result is retrieved.

The processor 1110 provided according to the embodiments of the present application may implement the above-mentioned method for constructing a search library or each process of the search method embodiment, and may achieve the same technical effects, so that repetition is avoided and no further description is given here.

It should be appreciated that, in accordance with an embodiment of the present application, the first input unit 1104 may include a graphics processor (Graphics Processing Unit, GPU) 11041 and a microphone 11042, the graphics processor 11041 processing image data of still pictures or video obtained by an image capturing device (e.g., a camera) in a video capturing mode or an image capturing mode. The display unit 1106 may include a display panel 11061, and the display panel 11061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The second input unit 1107 includes at least one of a touch panel 11071 and other input devices 11072. The touch panel 11071 is also referred to as a touch screen. The touch panel 11071 may include two parts, a touch detection device and a touch controller. Other input devices 11072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and so forth, which are not described in detail herein.

The memory 1109 may be used to store software programs as well as various data. The memory 1109 may mainly include a first memory area storing programs or instructions and a second memory area storing data, wherein the first memory area may store an operating system, application programs or instructions (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like. Further, the memory 1109 may include volatile memory or nonvolatile memory, or the memory 1109 may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM), static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (ddr SDRAM), enhanced SDRAM (Enhanced SDRAM), synchronous DRAM (SLDRAM), and Direct RAM (DRRAM). Memory 1109 in embodiments in accordance with the present application includes, but is not limited to, these and any other suitable types of memory.

Processor 1110 may include one or more processing units; optionally, processor 1110 integrates an application processor that primarily processes operations involving an operating system, user interface, application programs, and the like, and a modem processor that primarily processes wireless communication signals, such as a baseband processor. It will be appreciated that the modem processor described above may not be integrated into the processor 1110.

According to the embodiment of the application, a readable storage medium is further provided, and a program or an instruction is stored on the readable storage medium, and when the program or the instruction is executed by a processor, the program or the instruction realizes each process of the method for constructing the search library or the embodiment of the search method, and the same technical effect can be achieved, so that repetition is avoided, and no redundant description is provided herein.

The processor is a processor in the electronic device in the above embodiment. Readable storage media include computer readable storage media such as computer readable memory ROM, random access memory RAM, magnetic or optical disks, and the like.

According to the embodiment of the application, a chip is further provided, the chip includes a processor and a communication interface, the communication interface is coupled with the processor, the processor is used for running a program or instructions, the above-mentioned search library construction method or each process of the search method embodiment can be realized, and the same technical effects can be achieved, so that repetition is avoided, and the description is omitted here.

It should be understood that chips mentioned according to embodiments of the present application may also be referred to as system-on-chip, chip system, or system-on-chip chips, etc.

According to an embodiment of the present application, there is provided a computer program product stored in a storage medium, where the program product is executed by at least one processor to implement the above-mentioned method for constructing a search library or each process of the search method embodiment, and achieve the same technical effects, and for avoiding repetition, a description is omitted herein.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solutions of the present application may be embodied essentially or in a part contributing to the prior art in the form of a computer software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods of the embodiments of the present application.

The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those of ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are also within the protection of the present application.

Claims (15)

1. A method for constructing a search library, comprising:

identifying, in a full-scale search library, first music information used in the media content;

identifying second music information newly added in the first time period in the full search library;

and constructing a target retrieval library based on the first music information and the second music information.

2. The method of constructing a search pool according to claim 1, wherein constructing a target search pool based on the first music information and the second music information, comprises:

identifying third music information which does not meet target requirements in the first music information and the second music information;

and deleting the third music information from the first music information and the second music information to construct the target retrieval library.

3. The method of constructing a search pool according to claim 1, wherein constructing a target search pool based on the first music information and the second music information, further comprises:

identifying blank segment proportion in the audio corresponding to the first music information and the second music information;

acquiring fourth music information of which the blank segment proportion does not meet the preset proportion requirement;

And deleting the fourth music information from the first music information and the second music information to construct the target retrieval library.

4. The method for constructing a search pool according to claim 1, further comprising:

every second time interval, obtaining fifth music information which is newly added in the second time interval by the full-quantity search library;

and updating the target retrieval library based on the fifth music information.

5. The method for constructing a search pool according to claim 1, further comprising:

identifying, in the target search pool, sixth music information that has not been used by the media content for a third period of time;

and deleting the sixth music information from the target retrieval library.

6. The method for constructing a search pool according to claim 1, further comprising:

and updating the target retrieval library based on the seventh music information when the audio corresponding to the media content retrieves the seventh music information in the full-scale retrieval library.

7. The method for constructing a search pool according to any one of claims 1 to 6, further comprising:

And constructing, deleting or updating the full-volume search library or the target search library through a service and an interface.

8. A retrieval method, comprising:

acquiring audio based on the media content;

based on the audio frequency, carrying out real-time retrieval in a target retrieval library;

and under the condition that a result is retrieved, obtaining the music information corresponding to the audio.

9. The retrieval method as recited in claim 8, further comprising:

under the condition that a result is not retrieved, acquiring a first data index corresponding to the audio frequency in a first time dimension;

and searching in a full-scale search library under the condition that the first data index meets the first requirement.

10. The search method according to claim 9, wherein, in the case where the first data index meets a first requirement, searching in a full-scale search library includes:

acquiring a retrieval tag of the audio under the condition that the first data index meets a first requirement;

and searching in the full-volume search library when the full-volume search library search label is not included in the search label.

11. The retrieval method according to any one of claims 8 to 10, further comprising:

Under the condition that no result is retrieved, acquiring a second data index corresponding to the audio frequency in a second time dimension;

searching in the target search library under the condition that the second data index meets a second requirement;

and searching in a full-scale search library under the condition that the target search library does not search the result.

12. A search library constructing apparatus comprising:

a first identifying module for identifying, in the full search library, first music information used in the media content;

the second identification module is used for identifying second music information newly added in the first time period in the full search library;

and the construction module is used for constructing a target retrieval library based on the first music information and the second music information.

13. A search device, comprising:

the first acquisition module is used for acquiring audio based on the media content;

the retrieval module is used for carrying out real-time retrieval in a target retrieval library based on the audio;

and the second acquisition module is used for obtaining the music information corresponding to the audio under the condition that the result is retrieved.

14. An electronic device, comprising:

A memory having stored thereon programs or instructions;

a processor for implementing the steps of the construction method of the search pool according to any one of claims 1 to 7 or the steps of the search method according to any one of claims 8 to 11 when executing the program or instructions.

15. A readable storage medium having stored thereon a program or instructions, which when executed by a processor, realizes the steps of the construction method of the search pool according to any one of claims 1 to 7 or the steps of the search method according to any one of claims 8 to 11.