WO2022105775A1 - Search processing method and apparatus, model training method and apparatus, and medium and device - Google Patents

Abstract

The present disclosure relates to a search processing method and apparatus, a model training method and apparatus, and a medium and a device. The search processing method comprises: receiving target search information; and determining a target search result according to the target search information, and determining a target degree of relevance between the target search result and the target search information by means of a degree of relevance determination model. The degree of relevance determination model is obtained by means of training in the following manner: according to information of historical operation behavior implemented by a user on a plurality of historical search results, respectively determining a degree of relevance between each historical search result and historical search information, wherein a degree of relevance between a historical search result and historical search information that have identical target text digest information is set to be identical; and training a model by taking the historical search information and the historical search result as an input of the model and taking the degree of relevance between the historical search result and the historical search information as a target output of the model, so as to obtain the degree of relevance determination model. In this way, a determined target degree of relevance is more accurate.

Description

Search processing method, model training method, apparatus, medium and equipment

This application is based on the Chinese application with the application number of 202011303665.1 and the filing date of November 19, 2020, and claims its priority. The disclosure of the Chinese application is hereby incorporated into this application as a whole.

technical field

The present disclosure relates to the field of search technology, and in particular, to a search processing method, a model training method, an apparatus, a medium, a computer program product, and a device.

Background technique

In the field of search, a search is generally performed according to search information such as search words or search sentences input by a user, so as to obtain corresponding search results. The correlation between the search results and the search information input by the user can reflect whether the search results conform to the user's search intent. Wherein, the higher the correlation between the search result and the search information, it can be represented that the search result is more in line with the user's search intention.

SUMMARY OF THE INVENTION

This Summary is provided to introduce concepts in a simplified form that are described in detail in the Detailed Description section that follows. This summary section is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to be used to limit the scope of the claimed technical solution.

In a first aspect, the present disclosure provides a search processing method, the method includes: receiving target search information; determining a target search result according to the target search information, and determining the target search result and the target through a correlation determination model The target correlation between the search information; wherein, the correlation determination model is obtained by training in the following way: according to the historical operation behavior information performed by the user on a plurality of historical search results, respectively determine each historical search result and historical search information The correlation between the historical search results and the historical search information with the same target text summary information is set to be the same, and the historical search results are based on the historical search results input by the user. The search information is obtained by searching; the historical search information and the historical search results are used as the input of the model, and the correlation between the historical search results and the historical search information is used as the target output of the model. Training is performed to obtain the correlation determination model.

In a second aspect, the present disclosure provides a method for training a correlation determination model, the method comprising: determining the correlation between each historical search result and the historical search information according to historical operation behavior information performed by a user on a plurality of historical search results. The degree of correlation between the historical search results with the same target text summary information and the historical search information is set to be the same, and the historical search results are searched according to the historical search information input by the user Obtained; using the historical search information and the historical search results as the input of the model, and the correlation between the historical search results and the historical search information as the target output of the model, the model is trained to The correlation determination model is obtained.

In a third aspect, the present disclosure provides a search processing device, the device comprising: a receiving module for receiving target search information; a target relevance determination module for determining a target search result according to the target search information, and through correlation The degree determination model determines the target correlation between the target search result and the target search information; wherein, the correlation determination model is obtained by training in the following way: according to the historical operations performed by the user on a plurality of historical search results behavior information, respectively determining the correlation between each historical search result and historical search information, wherein the correlation between the historical search results and the historical search information with the same target text abstract information is set to be the same, The historical search result is obtained by searching according to the historical search information input by the user; the historical search information and the historical search result are used as the input of the model, and the relationship between the historical search result and the historical search information is obtained. The correlation degree is taken as the target output of the model, and the model is trained to obtain the correlation degree determination model.

In a fourth aspect, the present disclosure provides a correlation determination model training device, the device includes: a correlation determination module, configured to determine the correlation between each historical search result and each historical search result according to historical operation behavior information performed by a user on a plurality of historical search results. The correlation between historical search information, wherein the correlation between the historical search results with the same target text summary information and the historical search information is set to be the same, and the historical search results are based on user input The historical search information is obtained by searching; the training module is used to use the historical search information and the historical search results as the input of the model, and the correlation between the historical search results and the historical search information is used as the model The target output of the model is trained to obtain the correlation determination model.

In a fifth aspect, the present disclosure provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processing apparatus, implements the steps of the method provided in the first aspect of the present disclosure.

In a sixth aspect, the present disclosure provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processing apparatus, implements the steps of the method provided in the second aspect of the present disclosure.

In a seventh aspect, the present disclosure provides an electronic device, comprising: a storage device on which a computer program is stored; and a processing device for executing the computer program in the storage device, so as to implement the computer program provided in the first aspect of the present disclosure. the steps of the method.

In an eighth aspect, the present disclosure provides an electronic device, comprising: a storage device on which a computer program is stored; and a processing device for executing the computer program in the storage device, so as to implement the computer program provided in the second aspect of the present disclosure. the steps of the method.

In a ninth aspect, the present disclosure provides a computer program product comprising instructions that, when executed by a processing device, implement the steps of the method provided according to the first aspect of the present disclosure or the described methods provided according to the second aspect of the present disclosure. steps of the method.

Other features and advantages of the present disclosure will be described in detail in the detailed description that follows.

Description of drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent when taken in conjunction with the accompanying drawings and with reference to the following detailed description. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale. In the attached image:

Fig. 1 is a flow chart of a method for training a correlation determination model according to an exemplary embodiment.

Fig. 2 is a flow chart of a method for respectively determining the correlation between each historical search result and historical search information, according to an exemplary embodiment.

Fig. 3 is a flow chart of a method for determining target text summary information of historical search results according to an exemplary embodiment.

Fig. 4 is a flow chart of a method for determining the degree of relevancy between historical search results included in a search result group and historical search information, according to an exemplary embodiment.

Fig. 5 is a flowchart of a search processing method according to an exemplary embodiment.

Fig. 6 is a block diagram of a search processing apparatus according to an exemplary embodiment.

Fig. 7 is a block diagram of an apparatus for training a correlation determination model according to an exemplary embodiment.

FIG. 8 is a schematic structural diagram of an electronic device according to an exemplary embodiment.

Detailed ways

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for the purpose of A more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes, and are not intended to limit the protection scope of the present disclosure.

It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and/or in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this regard.

As used herein, the term "including" and variations thereof are open-ended inclusions, ie, "including but not limited to". The term "based on" is "based at least in part on." The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions of other terms will be given in the description below.

It should be noted that concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or interdependence.

It should be noted that the modifications of "a" and "a plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless the context clearly indicates otherwise, they should be understood as "one or a plurality of". multiple".

The names of messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of these messages or information.

At present, the correlation between search results and search information is mainly determined by a model, and the training of the model depends on preset training data, which may include the correlation between the marked search results and search information. In related technologies, technicians generally manually mark the correlation between search results and search information. However, the amount of data required for training is large, and the manual labeling method is inefficient, and the correlation is manually marked. The annotation is affected by the subjective judgment of technicians and is not accurate enough.

First, the training method of the relevance determination model in the embodiment of the present disclosure is introduced, and the relevance determination model can be used to determine the relevance between the search result and the search information.

Fig. 1 is a flow chart of a method for training a correlation determination model according to an exemplary embodiment. The method can be applied to an electronic device with processing capability. As shown in Fig. 1 , the method can include S101 and S102.

In S101, the correlation between each historical search result and the historical search information is determined respectively according to the historical operation behavior information performed by the user on the plurality of historical search results.

The historical search result may be obtained by searching according to the historical search information input by the user. For example, the historical search information may include search information input by the user during a historical period (eg, the past week or the past month), and the historical search information may be search words or search sentences input by the user. Among them, a plurality of historical search results can be found according to the historical search information. For example, the historical search information input by the user is the name of a singer, and the plurality of historical search results can include a plurality of songs written by the singer.

Users can perform operations on historical search results that meet their own search intentions according to their needs. For example, the operations can include operations such as clicking, browsing, and sliding. In addition, when users search for media files such as music and videos, the operation can also include music or video. The playback operation of the video file. The historical operation behavior information performed by the user on the historical search results may include one or more of the following information items: user click behavior information, user browsing behavior information, user playing behavior information, and the like. The historical operation behavior information can be used to represent whether the user has performed an operation on the historical search result.

In one embodiment, the historical operation behavior information may include one of the above information items, for example, the user clicks on the historical search result, or the user browses the historical search result, and it is considered that the user has performed an operation on the historical search result. In another embodiment, the historical operation behavior information may include multiple items of the above information items, and whether the user has performed operations on the historical search results may be determined through the multiple items of information items. For example, only after the user clicks on the historical search result and browses the page corresponding to the historical search result for a first preset period of time, it is considered that the user has performed an operation on the historical search result. Alternatively, only after the user clicks on the historical search result and plays the music or video file corresponding to the historical search result for a second preset duration, it is considered that the user has performed an operation on the historical search result. The above-mentioned first preset duration and second preset duration may be pre-calibrated.

Among them, if the historical search results conform to the user's search intention, the user will perform operations on the historical search results. Therefore, the historical operation behavior information performed by the user on the historical search results can reflect the historical search results and historical search information to a certain extent. correlation between. The historical search results that the user performs more operations are more in line with the user's search intent, that is, the correlation with the historical search information is relatively higher. In the present disclosure, the correlation between each historical search result and the historical search information is determined respectively according to the historical operation behavior information performed by the user on the historical search results, and there is no need for technicians to manually mark the correlation.

However, the operation behavior performed by the user on the historical search results is affected by factors such as the display order of the historical search results. For example, the user is generally accustomed to clicking the historical search result with the previous display order, which makes the determination based on the historical operation behavior information. The correlation between historical search results and historical search information is easily affected by other factors such as display order, media file playback volume, and attention.

Illustratively, taking the search user name as an example, for example, the historical search information input by the user is aaa, and a plurality of historical search results are searched according to the historical search information, for example, including: user name: aaa1, degree of attention: 2000; user name aaa2, Attention: 200; Username: aaa3, Attention: 20. Since the user name aaa1 has a higher degree of attention and its display order is in the front, the click rate of the user named aaa1 is higher than the other two, and it will be considered that the historical search result with the user name aaa1 has a relationship between the historical search information and the historical search information. The correlation is the highest, the correlation between the historical search results with the user name aaa2 and the historical search information is second, and the correlation between the historical search results with the user name aaa3 and the historical search information is the lowest. However, from the perspective of text information, the three historical search results have the same degree of matching with the historical search information aaa.

As another example, taking the historical search information as the search information for media files as an example, the historical search information input by the user is word A, and word A is the name of a singer, and the singer has multiple musical works, such as music 1, music 2. When displaying historical search results to users, it is possible that Music 1 is displayed in the first order, and Music 2 is displayed in the last order. Usually, the user playback rate of Music 1 is higher, and the user playback rate of Music 2 is lower. However, the subject of the creator of both music 1 and music 2 is the singer, and the degree of matching between music 1 and word A is the same as the degree of matching between music 2 and word A.

In view of this, in order to reduce the influence of other factors such as presentation order, playback volume and other factors on user operation behavior, in the present disclosure, when determining the correlation between historical search results and historical search information, historical searches with the same target text summary information The degree of correlation between the result and the historical search information is set to be the same. Wherein, the target text summary information of the historical search result may be the text information of the part associated with the historical search information in the historical search result. If the target text summary information is the same, it can be represented that from the perspective of text, the matching degree between the historical search results and the historical search information is the same.

In S102, the historical search information and historical search results are used as the input of the model, the correlation between the historical search results and the historical search information is used as the target output of the model, and the model is trained to obtain a correlation determination model. The correlation determination model may be any network model, such as a neural network model, and the present disclosure does not specifically limit the form of the correlation determination model.

Through the above solution, if the historical search results conform to the user's search intention, the user will perform operations on the historical search results. Therefore, according to the historical operation behavior information performed by the user on multiple historical search results, each historical search result and historical search results are determined. The correlation between information, the correlation can be used as model training data, and the correlation is determined by training. In this way, the data required for model training can be quickly obtained without manual labeling of training data, and the problem of inaccurate correlation of manual labeling can be solved. Also, when determining the degree of relevancy between the historical search results and the historical search information, the degree of relevancy between the historical search results and the historical search information having the same target text summary information is set to be the same, and it is possible to reduce the order of presentation, etc. The influence of other factors on the user's operation behavior makes the model training data more accurate, so that the trained correlation determination model is more accurate.

Fig. 2 is a flowchart of a method for respectively determining the correlation between each historical search result and historical search information according to an exemplary embodiment. As shown in Fig. 2 , S101 may include S201-S203.

In S201, for each historical search result, target text summary information of the historical search result is determined.

In an embodiment, an exemplary implementation of this step S201 may be shown in FIG. 3 , including S2011 to S2014.

In S2011, text information belonging to a preset topic in the historical search results is acquired. The preset topic may be a preset tag used to describe historical search results from different dimensions.

For example, when the historical search information is search information for user names, the preset topics may include user ID, user name, degree of attention, user signature, and the like. For another example, in the case that the historical search information is the search information for the document material, the preset subject may include the title of the document material, the author of the document material, the content of the document material, and the like. For another example, when the historical search information is search information for media files, the preset theme may include the name of the media file, the creator of the media file, the lyrics of the media file, the album to which the media file belongs, and the style of the media file. ,and many more. It is worth noting that, in the following introduction of the present disclosure, historical search information is used as an example for the search information for media files for illustration, but this does not constitute a limitation on the implementation of the present disclosure.

Wherein, the text information belonging to the preset theme in the acquired historical search results may include all or part of the theme content under the preset theme, and if the text information includes part of the theme content under the preset theme, it belongs to the preset theme. The text information of the preset theme is multiple.

Taking the historical search information as the search information for media files as an example, for example, for the preset theme of the name of the media file, the theme content under the preset theme is generally shorter, usually the song name of the song, so it belongs to the preset theme. It is assumed that the text information of a topic may include all topic contents under the preset topic. In addition, the acquired text information of the creator of the media file, the album to which the media file belongs, and the style of the media file, such as preset themes, may also include all the themes under the preset theme. For the preset theme of the lyrics of the media file, since the content of the lyrics is usually large, the text information belonging to the preset theme may include part of the theme content under the preset theme, and the part of the theme content may be, for example, the content of the lyrics in the lyrics. In a word. In this way, there are multiple pieces of text information belonging to the preset theme, and each sentence in the lyrics can be regarded as the text information belonging to the preset theme.

In S2012, candidate text summary information is determined. The candidate text summary information may include text information belonging to each preset topic, and text combination information of the text information.

When the user enters the historical search information, he or she may input content of various preset themes. For example, the user searches by adding a song title by a singer. Therefore, the candidate text summary information may include the text combination information of the text information, in which different preset themes can be selected. Assuming that the text information of the topics is combined, it can cover the situation that the user inputs the contents of multiple preset topics, so that the candidate text summary information is more comprehensive. The present disclosure does not specifically limit the manner of text combination, for example, text information may be combined in pairs.

In S2013, the matching degree between each candidate text summary information and the historical search information is determined respectively.

For example, the matching degree between the candidate text summary information and the historical search information may be determined by the number of characters matched between the two, wherein the matching may refer to the same or the same. For example, the matching degree between the candidate text summary information and the historical search information can be determined by the following formula (1):

Among them, M represents the matching degree between the candidate text summary information and the historical search information, hit_terms represents the number of characters matched between the candidate text abstract information and the historical search information, query_length represents the number of characters of the historical search information, and doc_length represents the candidate text abstract The number of characters of the message.

In S2014, the candidate text summary information with the highest matching degree with the historical search information is determined as the target text summary information.

In S202, the historical search results with the same target text summary information are aggregated into a search result group.

After the target text abstract information of each historical search result is determined, the historical search results with the same target text abstract information can be determined. For example, if historical search result 1 and historical search result 2 have the same target text summary information, they can be aggregated into a search result group. It should be noted that the present disclosure does not specifically limit the number of historical search results included in the search result group, and the above examples are only for explanation.

In S203, the correlation between the historical search results included in the search result group and the historical search information is determined according to the historical operation behavior information performed by the user on the historical search results included in the search result group.

In one embodiment, the correlation between the historical search results and the historical search information may be determined from a historical search behavior performed by the user according to the historical search information. However, the correlation degree is only determined by one historical search behavior of the user, the reference data is small, and effective data support cannot be provided, which may make the determined correlation degree inaccurate. The present disclosure provides another preferred embodiment of determining the correlation between historical search results and historical search information through multiple historical search behaviors performed by the user according to historical search information. This embodiment may be shown in FIG. 4 , and may include S2031 ~S2033.

In S2031, for each historical search behavior in the multiple historical search behaviors performed by the user according to the historical search information, according to the historical search behavior performed by the user on the historical search results included in the search result group in this historical search behavior The historical operation behavior information is to determine the target historical operation behavior information performed by the user on the search result group in this historical search behavior.

The multiple historical search behaviors may be initiated by different users. The target historical operation behavior information can be used to represent whether the user has performed an operation on the search result group. For example, in a user's historical search behavior, as long as the user performs an operation on any historical search result in the search result group, the target historical operation behavior information corresponding to the search result group may be recorded as 1.

In S2032, according to the target historical operation behavior information respectively performed by the user on the search result group in the multiple historical search behaviors, the feature information of the historical operation behavior performed by the user on the search result group is determined.

The historical operation behavior feature information may represent the historical click-through rate, historical playback rate, historical browsing rate, etc. of the search result group. Illustratively, for example, the data of X times of historical search behaviors performed by the user according to the historical search information are counted, and the target historical operation behavior information is Y, and Y is less than or equal to X, then the historical operation behavior feature information can be represented by the ratio of Y to X. .

In S2033, the correlation between the historical search results included in the search result group and the historical search information is determined according to the historical operation behavior feature information.

For example, the historical operation behavior feature information can be directly used as the correlation between the historical search results included in the search result group and the historical search information. Alternatively, the correlation may also be determined according to the correspondence between the pre-quantized historical operation behavior feature information and the correlation.

In the above solution, the correlation between the historical search results and the historical search information can be accurately determined through multiple historical search behaviors performed by the user according to the historical search information. In addition, the historical search results with the same target text abstract information are aggregated into a search result group, and the correlation between the historical search results included in the search result group and the historical search information is the same, which can reduce other factors such as the display order. The influence of factors on the user's operation behavior makes the model training data more accurate, so that the trained correlation determination model is more accurate.

The present disclosure also provides a search processing method. FIG. 5 is a flowchart of a search processing method according to an exemplary embodiment. The method can be applied to an electronic device with processing capability, such as a terminal or a server, as shown in FIG. As shown in 5, the method may include S501 and S502.

In S501, target search information is received.

The target search information may be information such as search words, search sentences, etc. input by the user. The user and the user who input the historical search information may be the same or different. The target search information may be the same or different from the above-mentioned historical search information. There are no specific restrictions on disclosure.

In S502, the target search result is determined according to the target search information, and the target correlation degree between the target search result and the target search information is determined by the correlation determination model.

The target search results and target search information may be input into the pre-trained correlation determination model to obtain the target correlation between the target search results and the target search information output by the correlation determination model.

The correlation determination model may be obtained by training in the following way: according to the historical operation behavior information performed by the user on a plurality of historical search results, the correlation between each historical search result and the historical search information is determined respectively, and the correlation between each historical search result and the historical search information is determined respectively, wherein the target text has the same target text. The correlation between the historical search results of the abstract information and the historical search information is set to be the same, and the historical search results are obtained by searching based on the historical search information input by the user; taking the historical search information and historical search results as the input of the model, The correlation between historical search results and historical search information is used as the target output of the model, and the model is trained to obtain a correlation determination model.

The training process of the correlation determination model has been described in detail above, and will not be repeated here.

Through the above technical solution, the target search result is determined according to the target search information, and the target correlation between the target search result and the target search information is determined by the correlation determination model. In the training phase of the correlation determination model, if the historical search results conform to the user's search intent, the user will perform operations on the historical search results. The correlation between the historical search results and the historical search information, the correlation can be used as model training data, and the correlation determination model is obtained by training. In this way, the data required for model training can be quickly obtained without manual labeling of training data, and the problem of inaccurate correlation of manual labeling can be solved. Also, when determining the degree of relevancy between the historical search results and the historical search information, the degree of relevancy between the historical search results and the historical search information having the same target text summary information is set to be the same, and it is possible to reduce the order of presentation, etc. The influence of other factors on the user's operation behavior makes the model training data and the trained correlation determination model more accurate, so that the correlation between the target search results determined by the correlation determination model and the target search information is more accurate. It provides an accurate basis for judging whether the target search result conforms to the user's search intent.

Optionally, determining the correlation between each historical search result and the historical search information according to the historical operation behavior information performed by the user on the plurality of historical search results, includes: for each historical search result, determining all the historical search results. The target text summary information of the historical search results; the historical search results with the same target text abstract information are aggregated into a search result group; according to the user's implementation of the historical search results included in the search result group the historical operation behavior information, and determine the correlation between the historical search results included in the search result group and the historical search information.

Optionally, according to the historical operation behavior information performed by the user on the historical search results included in the search result group, it is determined that the historical search results included in the search result group are the same as the historical search results included in the search result group. The correlation between the historical search information includes: for each historical search behavior in the multiple historical search behaviors performed by the user according to the historical search information, according to the user's search result group in this historical search behavior, The historical operation behavior information implemented by the historical search results included in the , determine the target historical operation behavior information performed by the user on the search result group in this historical search behavior; The target historical operation behavior information implemented on the search result group respectively, determine the historical operation behavior characteristic information implemented by the user on the search result group; according to the historical operation behavior characteristic information, determine the search result group the correlation between the historical search results and the historical search information included in .

Optionally, the determining the target text summary information of the historical search results includes: acquiring text information belonging to a preset topic in the historical search results, wherein the text information includes information under the preset topic. All or part of the subject content, in the case that the text information includes part of the subject content under the preset subject, there are multiple text information belonging to the preset subject; determine candidate text summary information, wherein, The candidate text summary information includes the text information belonging to each of the preset topics and the text combination information of the text information; respectively determine the relationship between each of the candidate text summary information and the historical search information. Matching degree: Determine the candidate text summary information with the highest matching degree with the historical search information as the target text summary information.

The specific implementation of the above steps has been described in detail in the above-mentioned training method for determining the correlation degree.

The search processing method provided by the present disclosure may further include: determining the display order of the target search results according to the target relevance between the target search results and the target search information.

Under normal circumstances, multiple target search results can be searched according to the target search information, and the relevancy degrees between the multiple target search results and the target search information may be different from each other. Wherein, for example, the display order of the target search results with a high degree of relevance to the target search information may be arranged before the display order of the target search results with a low degree of relevance to the target search information. In this way, the user can first browse to the search result more relevant to the target search information input by the user, thereby improving the user experience.

Based on the same inventive concept, the present disclosure also provides a search processing apparatus. FIG. 6 is a block diagram of a search processing apparatus according to an exemplary embodiment. The apparatus 600 may include:

a receiving module 601, configured to receive target search information;

A target relevance determination module 602, configured to determine a target search result according to the target search information, and determine the target relevance between the target search result and the target search information through a relevance determination model;

Wherein, the correlation determination model is obtained by training in the following way: according to the historical operation behavior information performed by the user on multiple historical search results, the correlation between each historical search result and the historical search information is determined respectively, wherein there are The correlation between the historical search results of the same target text abstract information and the historical search information is set to be the same, and the historical search results are obtained by searching according to the historical search information input by the user; The historical search information and the historical search results are used as the input of the model, the correlation between the historical search results and the historical search information is used as the target output of the model, and the model is trained to obtain the correlation Determine the model.

Optionally, the apparatus 600 may further include: a display order determination module, configured to determine the display order of the target search results according to the target relevance between the target search results and the target search information.

Regarding the apparatus in the above-mentioned embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments of the related method, and will not be described in detail here.

The present disclosure also provides a correlation determination model training apparatus. FIG. 7 is a block diagram of a correlation determination model training apparatus according to an exemplary embodiment. The apparatus 700 may include:

Relevance determination module 701 is used to determine the correlation between each historical search result and historical search information according to the historical operation behavior information performed by the user on a plurality of historical search results, wherein the The correlation between the historical search result and the historical search information is set to be the same, and the historical search result is obtained by searching according to the historical search information input by the user;

The training module 702 is used for taking the historical search information and the historical search results as the input of the model, and the correlation between the historical search results and the historical search information as the target output of the model, and performing the training on the model. training to obtain the correlation determination model.

Optionally, the relevancy determination module 701 includes: a target text summary information determination submodule for determining the target text summary information of the historical search result for each historical search result; an aggregation submodule , used for aggregating the historical search results with the same target text summary information into a search result group; a first correlation determination sub-module is used for the historical search results included in the search result group according to the user's The implemented historical operation behavior information determines the degree of relevancy between the historical search results included in the search result group and the historical search information.

Optionally, the first relevancy determination sub-module includes: a behavior information determination sub-module, which is used for each historical search behavior in the multiple historical search behaviors performed by the user according to the historical search information, according to the In this historical search behavior, the historical operation behavior information performed by the user on the historical search results included in the search result group determines the target history performed by the user on the search result group in this historical search behavior Operation behavior information; a behavior feature information determination sub-module, configured to determine that the user has performed the search result group according to the target historical operation behavior information respectively performed by the user on the search result group in multiple historical search behaviors the historical operation behavior feature information; the second correlation determination sub-module is used to determine the relationship between the historical search results included in the search result group and the historical search information according to the historical operation behavior feature information the correlation.

Optionally, the target text summary information determination sub-module includes: a text information acquisition sub-module for acquiring text information belonging to preset topics in the historical search results, wherein the text information includes the preset All or part of the theme content under the theme, in the case that the text information includes part of the theme content under the preset theme, there are multiple pieces of text information belonging to the preset theme; module for determining candidate text summary information, wherein the candidate text summary information includes the text information belonging to each of the preset topics and the text combination information of the text information; the matching degree determination sub-module, using for determining the matching degree between each of the candidate text abstract information and the historical search information respectively; the abstract information determination sub-module is used to determine the candidate text abstract with the highest matching degree with the historical search information information, which is determined as the target text summary information.

Through the above technical solution, the target search result is determined according to the target search information, and the target correlation between the target search result and the target search information is determined by the correlation determination model. In the training phase of the correlation determination model, if the historical search results conform to the user's search intent, the user will perform operations on the historical search results. The correlation between the historical search results and the historical search information, the correlation can be used as model training data, and the correlation determination model is obtained by training. In this way, the data required for model training can be quickly obtained without manual labeling of training data, and the problem of inaccurate correlation of manual labeling can be solved. Also, when determining the degree of relevancy between the historical search results and the historical search information, the degree of relevancy between the historical search results and the historical search information having the same target text summary information is set to be the same, and it is possible to reduce the order of presentation, etc. The influence of other factors on the user's operation behavior makes the model training data and the trained correlation determination model more accurate, so that the correlation between the target search results determined by the correlation determination model and the target search information is more accurate. It provides an accurate basis for judging whether the target search result conforms to the user's search intent.

Regarding the apparatus in the above-mentioned embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments of the related method, and will not be described in detail here. It should be noted that the division of the above-mentioned modules does not limit the specific implementation manner, and the above-mentioned various modules may be implemented by, for example, software, hardware, or a combination of software and hardware. In actual implementation, the above-mentioned modules may be implemented as independent physical entities, or may also be implemented by a single entity (eg, a processor (CPU or DSP, etc.), an integrated circuit, etc.). It should be noted that although the respective modules are shown as separate modules in the figures, one or more of these modules may also be combined into one module or split into multiple modules.

Referring next to FIG. 8 , it shows a schematic structural diagram of an electronic device 800 suitable for implementing an embodiment of the present disclosure. Terminal devices in the embodiments of the present disclosure may include, but are not limited to, such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (eg, mobile terminals such as in-vehicle navigation terminals), etc., and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in FIG. 8 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.

As shown in FIG. 8 , an electronic device 800 may include a processing device (eg, a central processing unit, a graphics processor, etc.) 801 that may be loaded into random access according to a program stored in a read only memory (ROM) 802 or from a storage device 808 Various appropriate actions and processes are executed by the programs in the memory (RAM) 803 . In the RAM 803, various programs and data required for the operation of the electronic device 800 are also stored. The processing device 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input/output (I/O) interface 805 is also connected to bus 804 .

Typically, the following devices may be connected to the I/O interface 805: input devices 806 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration An output device 807 of a computer, etc.; a storage device 808 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 809. Communication means 809 may allow electronic device 800 to communicate wirelessly or by wire with other devices to exchange data. While FIG. 8 shows an electronic device 800 having various means, it should be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.

In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. Embodiments of the present disclosure also include a computer program product, comprising: instructions that, when executed by a processing device, implement the steps of the search processing method of the embodiments of the present disclosure or the steps of the relevance determination model training method of the embodiments of the present disclosure . For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network via the communication device 809, or from the storage device 808, or from the ROM 802. When the computer program is executed by the processing device 801, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.

It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In this disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device . Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, electrical wire, optical fiber cable, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the client and server can use any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol) to communicate, and can communicate with digital data in any form or medium Communication (eg, a communication network) interconnects. Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (eg, the Internet), and peer-to-peer networks (eg, ad hoc peer-to-peer networks), as well as any currently known or future development network of.

The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or may exist alone without being assembled into the electronic device.

The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: receives target search information; determines a target search result according to the target search information, and passes The relevance determination model determines the target relevance between the target search result and the target search information; wherein, the relevance determination model is obtained by training in the following manner: according to the history of the user's implementation of multiple historical search results Operating behavior information, respectively determining the correlation between each historical search result and historical search information, wherein the correlation between the historical search results and the historical search information with the same target text abstract information is set to be the same , the historical search result is obtained by searching according to the historical search information input by the user; the historical search information and the historical search result are used as the input of the model, and the difference between the historical search result and the historical search information The correlation between the two is used as the target output of the model, and the model is trained to obtain the correlation determination model.

Alternatively, the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: according to the historical operation behavior information performed by the user on multiple historical search results, respectively determining the degree of relevance between each historical search result and historical search information, wherein the degree of relevancy between the historical search results and the historical search information having the same target text summary information is set to be the same, the historical search The result is obtained by searching according to the historical search information input by the user; the historical search information and the historical search results are taken as the input of the model, and the correlation between the historical search results and the historical search information is taken as The target output of the model, and the model is trained to obtain the correlation determination model.

Computer program code for performing operations of the present disclosure may be written in one or more programming languages, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and This includes conventional procedural programming languages - such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider to via Internet connection).

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.

The modules involved in the embodiments of the present disclosure may be implemented in software or hardware. Wherein, the name of the module does not constitute a limitation of the module itself under certain circumstances, for example, the receiving module may also be described as a "target search information receiving module".

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), Systems on Chips (SOCs), Complex Programmable Logical Devices (CPLDs) and more.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.

According to one or more embodiments of the present disclosure, exemplary embodiment 1 provides a search processing method, the method includes: receiving target search information; determining a target search result according to the target search information, and determining by correlation The model determines the target correlation between the target search result and the target search information; wherein, the correlation determination model is obtained by training in the following way: according to the historical operation behavior information performed by the user on a plurality of historical search results , respectively determine the correlation between each historical search result and historical search information, wherein the correlation between the historical search results with the same target text abstract information and the historical search information is set to be the same, the The historical search results are obtained by searching according to the historical search information input by the user; the historical search information and the historical search results are used as the input of the model, and the correlation between the historical search results and the historical search information The degree is used as the target output of the model, and the model is trained to obtain the correlation determination model.

According to one or more embodiments of the present disclosure, the exemplary embodiment 2 provides the method of the exemplary embodiment 1, wherein according to the historical operation behavior information performed by the user on the multiple historical search results, the relationship between each historical search result and each historical search result is determined respectively. The correlation between historical search information includes: for each historical search result, determining the target text summary information of the historical search result; aggregating the historical search results with the same target text abstract information as A search result group; according to the historical operation behavior information performed by the user on the historical search results included in the search result group, determine the historical search results included in the search result group and the historical search results correlation between information.

According to one or more embodiments of the present disclosure, exemplary embodiment 3 provides the method of exemplary embodiment 2 according to the history performed by the user on the historical search results included in the search result group Operation behavior information, determining the correlation between the historical search results included in the search result group and the historical search information, including: for the user according to the historical search information for multiple historical search behaviors. For each historical search behavior, according to the historical operation behavior information performed by the user on the historical search results included in the search result group in the historical search behavior, determine the user's interest in the historical search behavior in this historical search behavior. The target historical operation behavior information implemented by the search result group; according to the target historical operation behavior information respectively implemented by the user on the search result group in multiple historical search behaviors, it is determined that the user implements the search result group. The historical operation behavior feature information; according to the historical operation behavior feature information, determine the correlation between the historical search results included in the search result group and the historical search information.

According to one or more embodiments of the present disclosure, Exemplary Embodiment 4 provides the method of Exemplary Embodiment 2, and the determining the target text summary information of the historical search result includes: acquiring the historical search result The text information belonging to the preset theme in the text information, wherein the text information includes all the theme content or part of the theme content under the preset theme, in the case that the text information includes part of the theme content under the preset theme , there are multiple pieces of text information belonging to the preset theme; and candidate text summary information is determined, wherein the candidate text summary information includes the text information belonging to each preset theme and the text of the text information combination information; determine the degree of matching between each candidate text summary information and the historical search information respectively; determine the candidate text abstract information with the highest matching degree with the historical search information as the Target text summary information.

According to one or more embodiments of the present disclosure, exemplary embodiment 5 provides the method of exemplary embodiment 4, the historical search information is search information for media files, and accordingly, the preset theme includes media files name of the media file, the creator of the media file, the lyrics of the media file, the album to which the media file belongs, and the style of the media file.

According to one or more embodiments of the present disclosure, Exemplary Embodiment 6 provides the method of any one of Exemplary Embodiments 1 to 5, the method further comprising: searching according to the target The target relevance between the results and the target search information determines the display order of the target search results.

According to one or more embodiments of the present disclosure, exemplary embodiment 7 provides a method for training a relevance determination model, the method comprising: according to historical operation behavior information performed by a user on a plurality of historical search results, respectively determining The correlation between historical search results and historical search information, wherein the correlation between the historical search results and the historical search information with the same target text summary information is set to be the same, and the historical search results are Obtained by searching according to the historical search information input by the user; using the historical search information and the historical search results as the input of the model, and the correlation between the historical search results and the historical search information as the model's target output, the model is trained to obtain the correlation determination model.

According to one or more embodiments of the present disclosure, the exemplary embodiment 8 provides the method of the exemplary embodiment 7, wherein according to the historical operation behavior information performed by the user on the multiple historical search results, the relationship between each historical search result and each historical search result is determined respectively. The correlation between historical search information includes: for each historical search result, determining the target text summary information of the historical search result; aggregating the historical search results with the same target text abstract information as A search result group; according to the historical operation behavior information performed by the user on the historical search results included in the search result group, determine the historical search results included in the search result group and the historical search results correlation between information.

According to one or more embodiments of the present disclosure, Exemplary Embodiment 9 provides the method of Exemplary Embodiment 8 according to the history performed by the user on the historical search results included in the set of search results Operation behavior information, determining the correlation between the historical search results included in the search result group and the historical search information, including: for the user according to the historical search information for multiple historical search behaviors. For each historical search behavior, according to the historical operation behavior information performed by the user on the historical search results included in the search result group in the historical search behavior, determine the user's interest in the historical search behavior in this historical search behavior. The target historical operation behavior information implemented by the search result group; according to the target historical operation behavior information respectively implemented by the user on the search result group in multiple historical search behaviors, it is determined that the user implements the search result group. The historical operation behavior feature information; according to the historical operation behavior feature information, determine the correlation between the historical search results included in the search result group and the historical search information.

According to one or more embodiments of the present disclosure, Exemplary Embodiment 10 provides the method of Exemplary Embodiment 8, wherein the determining the target text summary information of the historical search result includes: acquiring the historical search result The text information belonging to the preset theme in the text information, wherein the text information includes all the theme content or part of the theme content under the preset theme, in the case that the text information includes part of the theme content under the preset theme , there are multiple pieces of text information belonging to the preset theme; and candidate text summary information is determined, wherein the candidate text summary information includes the text information belonging to each preset theme and the text of the text information combination information; determine the degree of matching between each candidate text summary information and the historical search information respectively; determine the candidate text abstract information with the highest matching degree with the historical search information as the Target text summary information.

According to one or more embodiments of the present disclosure, Exemplary Embodiment 11 provides the method of Exemplary Embodiment 10, the historical search information is search information for media files, and accordingly, the preset theme includes media files name of the media file, the creator of the media file, the lyrics of the media file, the album to which the media file belongs, and the style of the media file.

According to one or more embodiments of the present disclosure, exemplary embodiment 12 provides a search processing apparatus, the apparatus includes: a receiving module for receiving target search information; The target search information determines the target search result, and the target correlation between the target search result and the target search information is determined by a correlation determination model; wherein, the correlation determination model is obtained by training in the following manner: The historical operation behavior information performed by the user on a plurality of historical search results respectively determines the correlation between each historical search result and the historical search information, wherein the historical search results with the same target text summary information and the historical search information The correlations are set to be the same, and the historical search results are obtained by searching according to the historical search information input by the user; taking the historical search information and the historical search results as the input of the model, the The correlation between the historical search results and the historical search information is used as the target output of the model, and the model is trained to obtain the correlation determination model.

According to one or more embodiments of the present disclosure, exemplary embodiment 13 provides an apparatus for training a relevance determination model, the apparatus comprising: a relevance determination module configured to implement a history of a plurality of historical search results according to a user Operating behavior information, respectively determining the correlation between each historical search result and historical search information, wherein the correlation between the historical search results and the historical search information with the same target text abstract information is set to be the same , the historical search results are obtained by searching according to the historical search information input by the user; the training module is used to use the historical search information and the historical search results as the input of the model, and the historical search results are the same as the historical search results. The correlation between the historical search information is used as the target output of the model, and the model is trained to obtain the correlation determination model.

According to one or more embodiments of the present disclosure, Exemplary Embodiment 14 provides a computer-readable medium having stored thereon a computer program that, when executed by a processing apparatus, implements Exemplary Embodiment 1 - Exemplary Embodiment The steps of any one of the methods in 6.

According to one or more embodiments of the present disclosure, Exemplary Embodiment 15 provides a computer-readable medium having stored thereon a computer program that, when executed by a processing apparatus, implements Exemplary Embodiment 7 - Exemplary Embodiment The steps of any one of 11.

According to one or more embodiments of the present disclosure, exemplary embodiment 16 provides an electronic device, comprising: a storage device on which a computer program is stored; and a processing device for executing the computer in the storage device A program to implement the steps of the method of any one of Exemplary Embodiment 1 - Exemplary Embodiment 6.

According to one or more embodiments of the present disclosure, exemplary embodiment 17 provides an electronic device, comprising: a storage device on which a computer program is stored; and a processing device for executing the computer in the storage device A program to implement the steps of the method of any of Exemplary Embodiment 7-Example Embodiment 11.

The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, and should also cover, without departing from the above-mentioned disclosed concept, the technical solutions formed by the above-mentioned technical features or Other technical solutions formed by any combination of its equivalent features. For example, a technical solution is formed by replacing the above features with the technical features disclosed in the present disclosure (but not limited to) with similar functions.

Additionally, although operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although the above discussion contains several implementation-specific details, these should not be construed as limitations on the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or logical acts of method, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims. Regarding the apparatus in the above-mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be described in detail here.

Claims (25)

1. A search processing method, the method comprising:

   receive target search information;

   Determine the target search result according to the target search information, and determine the target correlation between the target search result and the target search information through a correlation determination model;

   Wherein, the correlation determination model is obtained by training in the following manner:

   According to the historical operation behavior information performed by the user on multiple historical search results, the correlation between each historical search result and the historical search information is respectively determined, wherein the historical search results with the same target text summary information are the same as the historical search results. The correlation between the information is set to be the same, and the historical search result is obtained by searching according to the historical search information input by the user;

   The historical search information and the historical search results are used as the input of the model, and the correlation between the historical search results and the historical search information is used as the target output of the model, and the model is trained to obtain the Correlation determines the model.
2. The method according to claim 1, wherein determining the correlation between each historical search result and the historical search information according to the historical operation behavior information performed by the user on a plurality of historical search results, comprising:

   For each of the historical search results, determining the target text summary information of the historical search results;

   Aggregating the historical search results with the same summary information of the target text into a search result group;

   Determine the relationship between the historical search results included in the search result group and the historical search information according to the historical operation behavior information performed by the user on the historical search results included in the search result group relativity.
3. The method according to claim 2, wherein, according to the historical operation behavior information performed by the user on the historical search results included in the search result group, the determination of the information included in the search result group The correlation between the historical search results and the historical search information, including:

   For each historical search behavior among the multiple historical search behaviors performed by the user according to the historical search information, according to the historical search behavior performed by the user on the historical search results included in the search result group in this historical search behavior For the historical operation behavior information, determine the target historical operation behavior information performed by the user on the search result group in this historical search behavior;

   According to the target historical operation behavior information respectively performed by the user on the search result group in multiple historical search behaviors, determine the historical operation behavior feature information performed by the user on the search result group;

   The degree of correlation between the historical search results included in the search result group and the historical search information is determined according to the historical operation behavior feature information.
4. The method according to claim 2, wherein the determining the target text summary information of the historical search result comprises:

   Acquiring text information belonging to a preset theme in the historical search results, wherein the text information includes all or part of the theme content under the preset theme;

   determining candidate text summary information, wherein the candidate text summary information includes the text information belonging to each of the preset topics and text combination information of the text information;

   respectively determining the degree of matching between each of the candidate text abstract information and the historical search information;

   The candidate text summary information with the highest matching degree with the historical search information is determined as the target text summary information.
5. The method according to claim 4, wherein, when the text information includes part of the subject content under the preset subject, there are multiple text information belonging to the preset subject.
6. The method according to any one of claims 1-5, wherein the historical search information is search information for media files, and correspondingly, the preset theme includes the name of the media file, the creator of the media file, The lyrics of the media file, the album to which the media file belongs, and the style of the media file.
7. The method of any one of claims 1-6, further comprising:

   The display order of the target search results is determined according to the target relevance between the target search results and the target search information.
8. A method for training a correlation determination model, the method comprising:

   According to the historical operation behavior information performed by the user on multiple historical search results, the correlation between each historical search result and the historical search information is respectively determined, wherein the historical search results with the same target text summary information are the same as the historical search results. The correlation between the information is set to be the same, and the historical search result is obtained by searching according to the historical search information input by the user;

   The historical search information and the historical search results are used as the input of the model, and the correlation between the historical search results and the historical search information is used as the target output of the model, and the model is trained to obtain the Correlation determines the model.
9. The method according to claim 8, wherein determining the correlation between each historical search result and the historical search information according to the historical operation behavior information performed by the user on a plurality of historical search results, comprising:

   For each of the historical search results, determining the target text summary information of the historical search results;

   Aggregating the historical search results with the same summary information of the target text into a search result group;

   Determine the relationship between the historical search results included in the search result group and the historical search information according to the historical operation behavior information performed by the user on the historical search results included in the search result group relativity.
10. The method according to claim 9, wherein, according to the historical operation behavior information performed by the user on the historical search results included in the search result group, the determination of the information included in the search result group The correlation between the historical search results and the historical search information, including:

    For each historical search behavior among the multiple historical search behaviors performed by the user according to the historical search information, according to the historical search behavior performed by the user on the historical search results included in the search result group in this historical search behavior For the historical operation behavior information, determine the target historical operation behavior information performed by the user on the search result group in this historical search behavior;

    According to the target historical operation behavior information respectively performed by the user on the search result group in multiple historical search behaviors, determine the historical operation behavior feature information performed by the user on the search result group;

    The degree of correlation between the historical search results included in the search result group and the historical search information is determined according to the historical operation behavior feature information.
11. The method according to claim 9, wherein the determining the target text summary information of the historical search result comprises:

    Acquiring text information belonging to a preset theme in the historical search results, wherein the text information includes all or part of the theme content under the preset theme;

    determining candidate text summary information, wherein the candidate text summary information includes the text information belonging to each of the preset topics and text combination information of the text information;

    respectively determining the degree of matching between each of the candidate text abstract information and the historical search information;

    The candidate text summary information with the highest matching degree with the historical search information is determined as the target text summary information.
12. The method according to claim 11, wherein, when the text information includes part of the subject content under the preset subject, there are multiple text information belonging to the preset subject.
13. The method according to any one of claims 8-12, wherein the historical search information is search information for media files, and correspondingly, the preset theme includes the name of the media file, the creator of the media file, The lyrics of the media file, the album to which the media file belongs, and the style of the media file.
14. A search processing device, the device comprising:

    a receiving module for receiving target search information;

    a target relevance determination module, configured to determine a target search result according to the target search information, and determine the target relevance between the target search result and the target search information through a relevance determination model;

    Wherein, the correlation determination model is obtained by training in the following manner:

    According to the historical operation behavior information performed by the user on multiple historical search results, the correlation between each historical search result and the historical search information is respectively determined, wherein the historical search results with the same target text summary information are the same as the historical search results. The correlation between the information is set to be the same, and the historical search result is obtained by searching according to the historical search information input by the user;

    The historical search information and the historical search results are used as the input of the model, and the correlation between the historical search results and the historical search information is used as the target output of the model, and the model is trained to obtain the Correlation determines the model.
15. The apparatus of claim 14, further comprising:

    The display order determination module is configured to determine the display order of the target search results according to the target relevance between the target search results and the target search information.
16. A correlation determination model training device, the device comprising:

    The correlation determination module is used to determine the correlation between each historical search result and the historical search information according to the historical operation behavior information implemented by the user on a plurality of historical search results, wherein the historical information with the same target text summary information The correlation between the search result and the historical search information is set to be the same, and the historical search result is obtained by searching according to the historical search information input by the user;

    A training module is used to use the historical search information and the historical search results as the input of the model, the correlation between the historical search results and the historical search information as the target output of the model, and train the model , to obtain the correlation determination model.
17. The apparatus of claim 16, wherein the correlation determination module comprises:

    a target text summary information determination submodule, configured to determine the target text summary information of the historical search result for each of the historical search results;

    an aggregation submodule for aggregating the historical search results with the same target text summary information into a search result group;

    A first relevance determination submodule, configured to determine the historical search included in the search result group according to the historical operation behavior information performed by the user on the historical search results included in the search result group The correlation between the result and the historical search information.
18. The apparatus according to claim 17, wherein the first correlation determination sub-module comprises:

    The behavior information determination sub-module is used for each historical search behavior in the multiple historical search behaviors performed by the user according to the historical search information. The historical operation behavior information implemented by the historical search results, determine the target historical operation behavior information implemented by the user on the search result group in this historical search behavior;

    The behavior feature information determination submodule is used to determine the historical operation behaviors performed by the user on the search result group according to the target historical operation behavior information performed by the user on the search result group in multiple historical search behaviors. characteristic information;

    The second correlation degree determination submodule is configured to determine the degree of correlation between the historical search results included in the search result group and the historical search information according to the historical operation behavior feature information.
19. The apparatus according to claim 17, wherein the target text summary information determination submodule comprises:

    a text information acquisition sub-module, configured to acquire text information belonging to a preset theme in the historical search results, wherein the text information includes all or part of the theme content under the preset theme;

    a candidate text summary information determination submodule, configured to determine candidate text summary information, wherein the candidate text summary information includes the text information belonging to each of the preset topics and text combination information of the text information;

    a matching degree determination sub-module, used for respectively determining the matching degree between each of the candidate text abstract information and the historical search information;

    The summary information determination submodule is configured to determine the candidate text summary information with the highest matching degree with the historical search information as the target text summary information.
20. The apparatus according to claim 19, wherein in the case that the text information includes part of the subject content under the preset subject, there are multiple text information belonging to the preset subject.
21. A computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processing device, implements the steps of the method of any one of claims 1-7.
22. A computer-readable medium having stored thereon a computer program, wherein the program, when executed by a processing device, implements the steps of the method of any one of claims 8-13.
23. An electronic device comprising:

    a storage device on which a computer program is stored;

    A processing device, configured to execute the computer program in the storage device, to implement the steps of the method of any one of claims 1-7.
24. An electronic device comprising:

    a storage device on which a computer program is stored;

    A processing device, configured to execute the computer program in the storage device, to implement the steps of the method of any one of claims 8-13.
25. A computer program product comprising: instructions,

    The instructions, when executed by the processing device, implement the steps of the search processing method according to any one of claims 1-7 or the steps of the correlation determination model training method according to any one of claims 8-13.

Images