Data processing method, recommendation method, readable medium and electronic equipment

Abstract

The invention relates to the technical field of computers, and discloses a data processing method, a recommendation method, a readable medium and electronic equipment. According to the data processing method, the search contents of the user in the multiple application programs are obtained, the search features corresponding to the search contents are calculated, the search habits, preferences and the like of the user are determined more comprehensively, then the calculated search features or information related to the search features are shared to the multiple application programs, and the user experience is improved. Or based on the calculated search features or information related to the search features, better recommendation service is provided for the user. By acquiring the search content of the user in the multiple application programs and calculating the search features, the richness and integrity of the search features are improved, so that more accurate and more complete service content and / or search content can be recommended to the user.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a data processing method, a recommendation method, a readable medium and an electronic device. Background Art

[0002] As users' search needs become more diverse, applications usually determine users' preferences, habits, and other information based on their search history and generate corresponding tags, and recommend keywords to users based on their corresponding tags. For example, if a user has searched for electronic products many times in a shopping application, the shopping application will determine that the user's tag is electronic based on the user's search history, and will mainly recommend electronic products to the user to improve the user's experience.

[0003] However, the current processing of search records is usually applied to a certain application or some related applications, and the richness and completeness of the obtained tags are low. Summary of the invention

[0004] The purpose of this application is to provide a data processing method, a recommendation method, a readable medium and an electronic device.

[0005] The first aspect of the present application provides a data processing method, including: a first electronic device obtains multiple search contents input by a user on the first electronic device, wherein the multiple search contents come from multiple applications; the first electronic device generates search features for the multiple search contents, wherein the search features include: multiple categories corresponding to the search contents, category levels corresponding to the categories, and confidence levels, wherein the confidence level indicates the probability that the search contents belong to the categories; the first electronic device sends the search features of the multiple search contents to a second electronic device.

[0006] In the embodiment of the present application, the first electronic device here may be the electronic device 100, the second electronic device may be the data middle station, the search content may be the keyword input by the user, the search feature may be a tag, the category may be a tag field, and the category level may be a tag level. The electronic device 100 obtains the keywords input by the user in each application; generates corresponding tags, wherein the tags include: tag field, tag level and confidence, wherein the confidence is used to indicate the probability that the keyword input by the user belongs to the corresponding tag field; the electronic device 100 sends the obtained tags to the data middle station.

[0007] It can be understood that the data processing method provided in the present application improves the richness and completeness of search features by obtaining the user's search content in multiple applications and calculating the search features, so as to recommend more accurate and complete service content and / or search content to the user.

[0008] In a possible implementation of the first aspect above, the higher the category level corresponding to a category is, the smaller the scope represented by the category is.

[0009] In the embodiment of the present application, the larger the tag level, the smaller the range of the corresponding tag field.

[0010] In a possible implementation of the first aspect above, the category with the highest category level among the categories is the search content input by the user, or the category with the highest category level among the categories is the keyword of the search content.

[0011] In the embodiment of the present application, the search content input by the user here may be a keyword input by the user, and the keyword of the search content may be a sub-keyword obtained from the keyword input by the user. The tag field corresponding to the maximum tag level is the keyword input by the user or the sub-keyword obtained from the keyword input by the user.

[0012] In a possible implementation of the first aspect above, the multiple search contents include a first search content and a second search content; and the first electronic device obtains the multiple search contents input by the user on the first electronic device, including: detecting that the user inputs a first search content of a first application, and the first electronic device does not currently meet the trigger condition, storing the first search content, detecting that the user inputs a second search content of a second application, and the first electronic device does not currently meet the trigger condition, storing the second search content; and the first electronic device generates search features for the multiple search contents, including: detecting that the first electronic device meets the trigger condition, calculating the first search content and the second search content through a data model, and obtaining a first search feature of the first search content and a second search feature of the second search content, respectively.

[0013] In the embodiment of the present application, the first application and the second application here may be different applications in the electronic device 100, the first search content may be the search content entered by the user in the first application, the second search content may be the search content entered by the user in the second application, the first search feature may be the label corresponding to the search content entered by the user in the first application, and the second search feature may be the label corresponding to the search content entered by the user in the second application. The electronic device 100 obtains the search content entered by the user in different applications in response to the acquisition condition, and encrypts and stores the obtained search content in the local database; when the trigger condition is met, the electronic device 100 inputs the search content of each application stored in the search database into the data model, and obtains the labels corresponding to each search content of each application.

[0014] In a possible implementation of the first aspect above, the trigger condition includes at least one of the following: the first electronic device is powered on; the battery power of the first electronic device is greater than a power threshold; the battery temperature of the first electronic device is less than a temperature threshold; the time interval from the last time the trigger condition was met is greater than a time threshold.

[0015] In an embodiment of the present application, the trigger conditions may include: when the electronic device 100 is connected to a power source and the power level is greater than a power threshold (for example, 50%); and the temperature of the electronic device 100 is less than a temperature threshold (for example, 37 degrees Celsius); in some embodiments, when the above conditions are met, it can be calculated at most once within 24 hours, that is, the interval with the previous calculation time is greater than the time threshold.

[0016] In a possible implementation of the first aspect above, the data model includes at least one of the following models: a support vector machine model, a k-nearest neighbor algorithm model, a decision tree model, a naive Bayes model, a deep neural network model, a convolutional neural network model, and a recurrent neural network model.

[0017] In a possible implementation of the first aspect above, the first electronic device obtains multiple search contents input by the user on the first electronic device, including: storing a first application package name of a first application and a first timestamp corresponding to the input time of the first search content, a second application package name of a second application, and a second timestamp corresponding to the input time of the second search content.

[0018] In the embodiment of the present application, the electronic device 100 obtains the input time (timestamp) corresponding to the search content entered by the user in different applications and the package name of each application.

[0019] In a possible implementation of the first aspect, the method further includes: displaying first recommended content, wherein the first recommended content is generated based on a first search feature of the first search content and a second search feature of the second search content.

[0020] In the embodiment of the present application, the first recommended content here may be recommended service content and / or recommended search terms. The data center predicts the user behavior of each application based on the tags corresponding to the search content of each application obtained, and determines the recommended service content and / or recommended search terms; the electronic device 100 displays the recommended service content and / or recommended search terms based on the data processing results of the data center.

[0021] In a possible implementation of the first aspect above, it also includes: based on the first application package name and the first timestamp, determining that the first recommended content is a recommendation of the first application, and the display time of the first recommended content is a first time, wherein the first time is the time corresponding to the first timestamp.

[0022] In an embodiment of the present application, the data center determines that the recommended application is an application based on the package name of each application and the timestamp corresponding to the keyword input by the user of each application, and determines the display time of the recommended application to be the time corresponding to the timestamp.

[0023] In a possible implementation of the first aspect above, it also includes: based on the first application package name and the first timestamp, and the second application package name and the second timestamp, determining that the first recommended content is a recommendation of the first application and the second application, and the display time of the first recommended content is the second time, wherein the second time is the time corresponding to the first timestamp or the second timestamp.

[0024] In an embodiment of the present application, the data center determines that the recommended applications are multiple applications based on the package names of each application and the timestamps corresponding to the keywords input by the user of each application, and determines that the display time of the multiple recommended applications is the time corresponding to the timestamp of one of the applications.

[0025] The second aspect of the present application provides a recommendation method, including: a second electronic device receives search features of multiple search contents from a first electronic device, wherein the multiple search contents come from multiple applications of the first electronic device, and the search features include: multiple categories corresponding to the search contents, category levels corresponding to the categories, and confidence levels, wherein the confidence levels indicate the probability that the search contents belong to the categories; the second electronic device generates second recommended content corresponding to the first electronic device based on the search features of the multiple search contents; and the second electronic device sends the second recommended content to the first electronic device.

[0026] In a possible implementation of the second aspect above, the higher the category level corresponding to a category, the smaller the scope represented by the category; and the category with the highest category level among the categories is the search content entered by the user, or the category with the highest category level among the categories is the keyword of the search content.

[0027] In a possible implementation of the second aspect above, the multiple search contents include a first search content input by a user into a first application and a second search content input by a user into a second application; and the second electronic device receives search features of the multiple search contents from the first electronic device, including: obtaining a first application package name of the first application, and a first timestamp corresponding to the input time of the first search content, a second application package name of the second application, and a second timestamp corresponding to the input time of the second search content.

[0028] In a possible implementation of the second aspect above, the second electronic device generates second recommended content corresponding to the first electronic device based on the search features of multiple search contents, including: based on the first application package name and the first timestamp, determining that the second recommended content is a recommendation for the first application, and the display time of the second recommended content is a third time, wherein the third time is the time corresponding to the first timestamp; or based on the first application package name and the first timestamp, and the second application package name and the second timestamp, determining that the second recommended content is a recommendation for the first application and the second application, and the display time of the second recommended content is a fourth time, wherein the fourth time is the time corresponding to the first timestamp or the second timestamp.

[0029] In an embodiment of the present application, the data center determines that the recommended application is one application based on the package name of each application and the timestamp corresponding to the keyword input by the user of each application, and determines that the display time of the recommended application is the time corresponding to the timestamp. Alternatively, the data center determines that the recommended application is multiple applications based on the package name of each application and the timestamp corresponding to the keyword input by the user of each application, and determines that the display time of the multiple recommended applications is the time corresponding to the timestamp of one of the applications.

[0030] The third aspect of the present application provides a recommendation method, including: a third application of a first electronic device obtains search features of multiple search contents, wherein the multiple search contents come from multiple applications of the first electronic device, the multiple applications include a first application and a second application, and the search features include: multiple categories corresponding to the search contents, category levels corresponding to the categories, and confidence levels, wherein the confidence level indicates the probability that the search contents belong to the category; the third application displays recommended search terms in the search box of the third application based on the search features of the multiple search contents.

[0031] In a possible implementation of the third aspect above, the higher the category level corresponding to a category, the smaller the scope represented by the category; and the category with the highest category level among the categories is the search content entered by the user, or the category with the highest category level among the categories is the keyword of the search content.

[0032] In a possible implementation of the third aspect above, the third application displays recommended search terms in the search box of the third application based on the search features of multiple search contents, including at least one of the following: the third application displays recommended search terms after the user activates the search box of the third application; the third application displays recommended search terms in the search box of the third application after it is started; the third application displays recommended search terms below the search box of the third application when the user enters content in the search box of the third application.

[0033] In the embodiment of the present application, in response to the user activating the search box, such as the user clicking the search box, the application displays recommended search terms in the search box. In response to the user launching the application, such as clicking the application icon to enter the display interface of the application, the application displays recommended search terms in the search box. In response to the user inputting content in the search box of the application, the application displays recommended keywords in the area below the search box.

[0034] A fourth aspect of the present application provides a readable medium on which instructions are stored. When the instructions are executed on an electronic device, the electronic device executes any one of the methods in the first, second and third aspects above.

[0035] The fifth aspect of the present application provides an electronic device, comprising a memory for storing instructions executed by one or more processors of the electronic device, and a processor, which is one of the processors of the electronic device, for executing any one of the methods in the first, second and third aspects above. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A schematic diagram of a user interface of a shopping application is shown according to an embodiment of the present application;

[0038] Figure 2 According to an embodiment of the present application, a flow chart of a data processing method is shown;

[0039] Figure 3 A schematic diagram of a user interface is shown according to an embodiment of the present application;

[0040] Figure 4 A schematic diagram of a search interface is shown according to an embodiment of the present application;

[0041] Figure 5 According to an embodiment of the present application, a schematic diagram of an interactive process of a data processing method is shown;

[0042] Figure 6 According to an embodiment of the present application, a structural schematic diagram of an electronic device is shown;

[0043] Figure 7According to an embodiment of the present application, a schematic block diagram of a software system architecture of an electronic device is shown. DETAILED DESCRIPTION

[0044] The illustrative embodiments of the present application include, but are not limited to, a data processing method, a recommendation method, a readable medium, and an electronic device.

[0045] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and comprehensively described below in conjunction with the accompanying drawings.

[0046] As mentioned above, with the diversification of user search needs, applications usually determine user preferences, habits and other information based on the user's search history and generate corresponding tags, and recommend search content to users based on the user's corresponding tags. For example, if a user has searched for electronic products many times in a shopping application, the shopping application determines that the user's tag is electronic based on the user's search history, and mainly recommends electronic products to the user to improve the user's experience.

[0047] For example, refer to Figure 1 FIG. 1 is a schematic diagram of a user interface of a shopping application shown in FIG. 1 . In response to a user clicking on the search box interface of the shopping application, the mobile phone 10 displays the following Figure 1 The user interface shown in FIG. The user interface includes a search interface display area 101 of a shopping application and a display interface 102 of an input method application. The search interface display area 101 of the shopping application includes a search box 1011, a "historical search" area 1012, and a "guess what you want to search" area 1013. Figure 1 As shown, assuming that the user's historical search records include "summer clothes for women", "chiffon dresses", "short skirts", etc., the shopping application generates tags corresponding to the search records based on the user's search records, and recommends search content to the user in the search box 1011 and / or the "Guess what you want to search" area 1013, such as "dresses", "skirts", "denim skirts", etc.

[0048] However, current processing of search records is usually applied to an application, such as Figure 1 The shopping application shown in the figure has low richness and completeness of tags. For example, the electronic device cannot provide accurate recommended content to the user based on the user's search usage habits and search history. For another example, when the user changes to another shopping software that is not frequently used, it may not be possible to make appropriate search recommendations for the user based on the user's recent search history, thereby affecting the user's experience.

[0049] In view of this, an embodiment of the present application provides a data processing method, which obtains the search content of the user in multiple applications and calculates the search features corresponding to the search content to more comprehensively determine the user's search habits, preferences, etc., and then shares the calculated search features or information related to the search features with multiple applications, or provides better recommendation services for users based on the calculated search features or information related to the search features. For example, the search features may include features such as the category to which the search content belongs, the level of the category to which the search content belongs, and the confidence level of the category to which the search content belongs.

[0050] It can be understood that in some embodiments of the present application, the application may be an application that includes a search box and is authorized by the user.

[0051] In some embodiments, the service content recommended based on the search feature includes: recommended applications and recommended content. For example, if the recommended application is a system application of the electronic device, the system service of the electronic device determines the recommended content based on the search feature or information related to the search feature. If the recommended application is a third-party application, the third-party application obtains the search feature through the data interface and determines the recommended content based on the search feature. Among them, the recommended application can be a different application authorized by the user. For example, based on the user's usage habits: the electronic device recommends the user to open the news application in the morning and recommends financial news reading; recommends the user to open the music software and recommends pop music during the user's commuting time; recommends the user to open the sports software at noon and recommends the dynamics of the user's favorite team; recommends the user to open the shopping application in the evening and recommends the user's favorite products; recommends the user to open the video software and recommend the user's favorite videos before the user goes to bed, so as to improve the user's usage experience.

[0052] In other embodiments, a user's search operation in a certain application is detected, and a recommended search term can be determined based on the search feature. For example, assuming that the user has searched for camping sites multiple times in a map application, a corresponding tag (search feature) is generated based on the user's search history. When the user opens a shopping application and clicks on the search control, the search content of camping equipment products can be recommended to the user in the input method recommended search area to improve the user's experience.

[0053] It can be understood that the data processing method provided in the embodiment of the present application improves the richness and completeness of search features by obtaining the user's search content in multiple applications and calculating the search features, so as to recommend more accurate and complete service content and / or search content to the user.

[0054] In some embodiments, the search feature or information related to the search feature is calculated by a data model, and the output data of the data model includes the following fields: the version number (version) of the input method, the timestamp (timestamp), the package name (pkgName) of the application, and the tag list (tagList) obtained by calculating the keyword entered by the user through the data model. Among them, the tag list tagList includes tags; each tag tag includes a tag field (key), a tag level (level), and a confidence (score). It can be understood that the timestamp represents a time period, that is, the time period from when the input method is started to when the user clicks the search / confirm control. The tag field indicates the category to which the keyword entered by the user belongs. The tag level may include N, and the larger the tag level, the smaller the range of the corresponding tag field, and the tag field corresponding to the maximum tag level is the keyword entered by the user or a sub-keyword obtained based on the keyword entered by the user. The confidence level indicates the degree of match between the keyword entered by the user and the corresponding tag field, that is, the probability that the keyword entered by the user belongs to the corresponding tag field.

[0055] It can be understood that the data processing method provided in the embodiment of the present application can be executed by an input method application or by a system service of an electronic device.

[0056] It is understood that the data processing method provided in the embodiments of the present application can be applied to any electronic device such as a mobile phone, a smart screen, a tablet computer, a laptop computer, a netbook, a personal digital assistant (PDA), etc. The exemplary embodiments of the electronic device include but are not limited to a device equipped with Or electronic devices with other operating systems. The embodiments of the present application do not impose any restrictions on the specific types of electronic devices.

[0057] In order to make the technical solution of this application clearer, Figure 2 The flowchart shown provides a clear and detailed description of the technical solution in the embodiments of the present application.

[0058] Figure 2 According to an embodiment of the present application, a flow chart of a data processing method is shown. It can be understood that Figure 2 Each step of the process shown in the figure is performed by the electronic device 100. Figure 2 The execution entities of each step will not be described repeatedly in the steps of the process shown. Figure 2 As shown, the process includes but is not limited to the following steps:

[0059] S201: Obtain the user's search content and store it in the local database.

[0060] In some embodiments, the electronic device 100 obtains search content input by the user in different applications in response to the acquisition conditions, and encrypts and stores the obtained search content in a local database.

[0061] The acquisition condition may be that the user clicks a search control in the application, or that the user clicks a confirmation / search control in the input method display interface, or that the user clicks an enter control in the input method display interface. This application does not impose any specific restrictions on this.

[0062] In some embodiments, the electronic device 100 obtains the input time (timestamp) corresponding to the search content entered by the user in different applications and the package name of each application. It can be understood that the data stored in the local database mainly includes the following fields: the version number (version) of the input method, the timestamp (timestamp), the package name (packagename) of the application, and the keyword (query) entered by the user. It can be understood that the keyword entered by the user is the search content.

[0063] For example, in response to a user clicking on Figure 1 The electronic device obtains the version number of the input method application, the current system time, the package name of the current application, and Figure 1 The search interface of the shopping application shown shows keywords input by the user in the search box 1011 of area 101 (search content input by the user).

[0064] S202: When a trigger condition is met, the tags of the stored search content are calculated.

[0065] In some embodiments, when the trigger condition is met, the electronic device 100 inputs the search content of each application stored in the search database into the data model, obtains the label corresponding to each search content of each application, and outputs the output data of the data model.

[0066] Among them, the trigger conditions may include: when the electronic device 100 is connected to a power source and the power level is greater than a power threshold (for example, 50%); and the temperature of the electronic device 100 is less than a temperature threshold (for example, 37 degrees Celsius); in some embodiments, when the above conditions are met, it can be calculated at most once within 24 hours, that is, the interval with the previous calculation time is greater than the time threshold.

[0067] For example, assuming that at 8 o'clock today, the electronic device 100 is connected to a power source and the power is greater than 50%, and the temperature of the electronic device 100 is less than 37 degrees Celsius, the electronic device 100 inputs the search content stored in the search database into the data model for calculation once. If at 8 o'clock tomorrow, the electronic device 100 is connected to a power source and the power is greater than 50%, and the temperature of the electronic device 100 is greater than 37 degrees Celsius, because the temperature of the electronic device 100 does not meet the condition of being less than the temperature threshold, no calculation is performed until all trigger conditions are met, and then calculation is performed.

[0068] In some embodiments, the data model may use a method combining keyword matching and classification model. For example, semantic segmentation and other operations are performed on the keyword input by the user to obtain sub-keywords, and the sub-keywords are matched with words in the vocabulary preset for each label field (category). If the sub-keywords are successfully matched with the words in the vocabulary, the keyword currently calculated by the user is judged to be the label field corresponding to the vocabulary; if the sub-keywords are not successfully matched with the words in the vocabulary, the classification model is used to classify the keyword input by the user.

[0069] It can be understood that the classification model includes but is not limited to a support vector machine model, a k-nearest neighbor algorithm model, a decision tree model, a naive Bayes model, a deep neural network model, a convolutional neural network model, a recurrent neural network model, and various variants and combinations thereof, etc., and the present application does not impose any restrictions on this.

[0070] In some embodiments, the output data of the output data model is a file in json format and includes the following fields: version number of the input method, timestamp, package name of the application, and tag list tagList calculated by the data model based on the keyword input by the user. The tag list tagList includes tags; each tag tag includes a tag field key, a tag level, and a confidence score.

[0071] It can be understood that the timestamp represents a time period, that is, the time period from when the input method is started to when the user clicks the search / confirm control. The tag field indicates the category to which the keyword entered by the user belongs. The tag level may include N, and the larger the tag level, the smaller the range of the corresponding tag field, and the tag field corresponding to the largest tag level is the keyword entered by the user or a sub-keyword obtained based on the keyword entered by the user. The confidence level indicates the matching degree between the keyword entered by the user and the corresponding tag field, that is, the probability that the keyword entered by the user belongs to the corresponding tag field.

[0072] For example, assuming that the keyword input by the user acquired by the electronic device 100 is "baby leggings summer", the output data of the data model can be expressed as:

[0073]

[0074]

[0075] It can be understood that the results calculated for the keyword "baby leggings summer" input by the user are: the tag field "shopping" with a tag level of 1, the confidence is 0.9; the tag field "mother and baby" with a tag level of 2, the confidence is 0.8; the tag field "baby clothes" with a tag level of 3, the confidence is 0.8; the tag field "leggings" with a tag level of 4, the confidence is 0.8; the tag field "baby" with a tag level of 4, the confidence is 0.8. It can be understood that the tag fields with tag levels of 1, 2, and 3 are the categories of the keywords input by the user, and the tag field with a tag level of 4 (i.e., the last tag field) is the sub-keyword obtained according to the keyword input by the user.

[0076] It can be understood that in the above embodiments, only a keyword input by a user corresponding to a timestamp in an application is used as an example to illustrate the format of the output data of the data model. In other embodiments, the output data of the data model includes keywords input by the user corresponding to multiple timestamps of multiple applications (applications authorized by all users in the electronic device 100), and the tag list corresponding to each timestamp may include multiple tags.

[0077] It can be understood that the data processing method provided in the embodiment of the present application improves the richness and completeness of the tags by acquiring the search content of each application in the electronic device 100 and calculating the corresponding tags.

[0078] In some embodiments, the tag field is in a format pre-agreed with the data middle station (data processing tool), for example, refer to Table 1.

[0079] Table 1 Label field table

[0080]

[0081] Among them, the first-level tags for local life searches - map applications and local life applications include: "Food Preferences" and "Entertainment Preferences"; the second-level tags corresponding to the first-level tag "Food Preferences" include: "Internet celebrity restaurants", "Hot pot", "Barbecue (including barbecue and fish)"; the second-level tags corresponding to the first-level tag "Entertainment Preferences" include: "Movies", "Performances", and "Competitions".

[0082] Online travel agency (OTA) searches - the first-level tags for map apps and itinerary apps include: "travel preferences"; the second-level tags for the first-level tag "travel preferences" include: "natural landscapes", "beach", "zoo and botanical gardens". Information, short video, and live broadcast searches - the first-level tags for short video apps and news apps include: "content preferences"; the second-level tags for the first-level tag "content preferences" include: "finance", "society", "international", and "entertainment".

[0083] Video search - The first-level tags of video applications include: "Movie Preference", "TV Preference" and "Variety Show Preference"; the second-level tags corresponding to the first-level tag "Movie Preference" include: "Drama", "Comedy", "Action", "Romance"; the second-level tags corresponding to the first-level tag "TV Preference" include: "Idol Romance", "Ancient Costume History", "Fantasy History"; the second-level tags corresponding to the first-level tag "Variety Show Preference" include: "Game", "Music", "Cultivation".

[0084] The first-level tags for entertainment application searches include: "Entertainment star preference"; the second-level tags corresponding to the first-level tag "Entertainment star preference" include: "Star name".

[0085] Sports search - The first-level tags of sports applications include: "Sports Preference"; the second-level tags corresponding to the first-level tag "Sports Preference" include: "NBA (National Basketball League)", "CBA (Chinese Basketball Association)", and "Chinese Super League".

[0086] Product search - The first-level tags of shopping applications include: "Product Preferences"; the second-level tags corresponding to the first-level tag "Product Preferences" include: "Women's clothing", "Home decoration", "Electrical appliances", "Mother and baby", etc.; the third-level tags corresponding to the second-level tag "Mother and baby" include: "Children's toys, children's clothing", etc.

[0087] It can be understood that the content of Table 1 is only an example of the tag field, and in other embodiments, the tag field may also be other content, which is not limited in the present application.

[0088] S203: Donate the label to the data center.

[0089] In some embodiments, the electronic device 100 donates (sends) the output data of the data model to the data middle platform, which performs further data processing.

[0090] S204: The data center predicts user behavior based on tags.

[0091] In some embodiments, the data center predicts user behavior of each application based on the tags corresponding to the search content of each application obtained, and determines recommended service content and / or recommended search terms.

[0092] It is understandable that the data middle station may be located in the electronic device 100 or may be another electronic device, and this application does not impose any limitation on this.

[0093] In some embodiments, the electronic device 100 displays recommended service content and / or recommended search terms based on the data processing results of the data center.

[0094] It can be understood that the recommended service content includes recommended applications and recommended content.

[0095] In some embodiments, the data center determines that the recommended application is an application based on the package name of each application and the timestamp corresponding to the keyword input by the user of each application, and determines the display time of the recommended application to be the time corresponding to the timestamp. At the same time, the recommended content is determined based on the tag of the application.

[0096] In other embodiments, the data center determines that the recommended application is a plurality of applications based on the package names of the respective applications and the timestamps corresponding to the keywords input by the users of the respective applications, and determines that the display time of the plurality of recommended applications is the time corresponding to the timestamp of one of the applications. At the same time, the recommended content is determined based on the tags of the respective applications.

[0097] In some embodiments, the electronic device 100 displays the corresponding recommended applications and recommended content in the service card according to the data processing results of the data middle station. For example, based on the user's usage habits: the electronic device 100 recommends the user to open the news application in the morning and recommends financial news reading; recommends the user to open the music software and recommends pop music during the user's commuting time; recommends the user to open the sports software and recommends the dynamics of the user's favorite team at noon; recommends the user to open the shopping application and recommends the user's favorite products in the evening; recommends the user to open the video software and recommends the user's favorite videos before the user goes to bed, so as to improve the user's usage experience.

[0098] It can be understood that the recommended service content is the content in the service card. The service card can be a service card in the main interface of the electronic device 100, or a service card in the negative one screen display area of ​​the electronic device 100. This application does not impose any restrictions on this.

[0099] For example, refer to Figure 3 FIG. 1 is a schematic diagram of a user interface of a mobile phone 10 shown in FIG. Figure 3As shown, the user interface 301 is the main interface of the mobile phone 10, and the interface 301 includes a "YOLO Suggestion" service card 3011 and icons of multiple application programs. Among them, the recommended application corresponding to the "YOLO Suggestion" service card 3011 is a music application, and the recommended content is "Popular Music A".

[0100] In some embodiments, if the recommended application is a system application of the electronic device 100 , the system service of the electronic device 100 determines the recommended content based on the tag.

[0101] In other embodiments, if the recommended application is a third-party application, the third-party application obtains the tag through the data interface of the electronic device 100 and determines the recommended content based on the tag.

[0102] In some embodiments, the application in the electronic device 100 obtains the tags calculated by the data model from the data center, determines the recommended search terms based on the obtained tags, and displays the recommended search terms in the search box. It can be understood that the application can be any application in the electronic device 100 that contains a search box and is authorized by the user.

[0103] For example, in some embodiments, in response to a user activating a search box, such as a user clicking on the search box, the application displays recommended search terms in the search box.

[0104] Or for example, in some embodiments, in response to a user operation of launching an application, such as clicking an application icon to enter a display interface of the application, the application displays recommended search terms in a search box.

[0105] Or for example, in some embodiments, in response to a user inputting content into a search box of an application, the application displays recommended keywords in an area below the search box.

[0106] In some embodiments, if the user activates / starts / inputs content and other operations corresponding to an input method application, the input method application obtains labels corresponding to the keywords input by the user of each application, determines recommended search terms based on the obtained labels, and displays the recommended search terms in the recommendation display area of ​​the input method application.

[0107] For example, assuming that a user has searched for camping sites multiple times in a map application, corresponding tags are generated based on the user's search history. When the user opens a shopping application and clicks the search box of the shopping application, recommended keywords for camping equipment products can be recommended to the user in the search box of the shopping application or in the recommendation display area of ​​the input method application to improve the user's experience.

[0108] For example, reference Figure 4 Schematic diagram of the search interface of the mobile phone 10 shown in FIG. Figure 4 As shown, in response to the user clicking on the search box interface of the shopping application, the mobile phone 10 displays the following Figure 4 The user interface shown in FIG. 4 includes a search interface display area 401 of a shopping application and a display interface 402 of an input method application. The search interface display area 401 of the shopping application includes a search box 4011, a "historical search" area 4012, and a "guess what you want to search" area 4013. The display interface 402 of the input method application includes a recommendation display area 4021 and a key area 4022, and the recommendation display area 4021 includes recommended keywords such as "tent", "camping equipment", and "barbecue grill".

[0109] It can be understood that in other embodiments, according to actual needs, the above Figure 2 The steps shown can be combined, deleted or replaced with other steps that are conducive to achieving the purpose of this application. For example, the above-mentioned step S203 and step S204 can be combined into one step, and this application does not limit this.

[0110] To make the technical solution of this application clearer, the following takes a shopping application as an example. Figure 3 The interaction diagram shown provides a clear and detailed description of the technical solutions in the embodiments of the present application.

[0111] Figure 5 According to an embodiment of the present application, a schematic diagram of an interactive process of a data processing method is shown. Figure 5 As shown, the interaction process includes but is not limited to the following steps:

[0112] S501: A user opens a shopping application.

[0113] S502: The user clicks on the search box of a shopping application.

[0114] S503: The shopping application invokes the input method application.

[0115] In some embodiments, in response to the user clicking on the search box of the shopping application, the electronic device 100 displays the search interface of the shopping application and starts the input method application. Figure 1 FIG. 1 is a schematic diagram of a user interface of a shopping application shown in FIG. 1 . In response to a user clicking on the search box interface of the shopping application, the mobile phone 10 displays the following Figure 1 The user interface shown in FIG. The user interface includes a search interface display area 101 of a shopping application and a display interface 102 of an input method application. The search interface display area 101 of the shopping application includes a search box 1011, a "historical search" area 1012, and a "guess what you want to search" area 1013. Figure 1As shown, assuming that the user's historical search records include "summer clothes for women", "chiffon dresses", "short skirts", etc., the shopping application generates tags corresponding to the search records based on the user's search records, and recommends search content to the user in the search box 1011 and / or the "Guess what you want to search" area 1013, such as "dresses", "skirts", "denim skirts", etc.

[0116] S504: The user inputs search content through the input method application.

[0117] In some embodiments, the user clicks on the display panel (eg, Figure 1 The text content to be searched is input by using the numbers and / or letters in the display interface 102 of the input method application shown in the figure.

[0118] S505: The input method application displays the text on the screen of the shopping application.

[0119] In some embodiments, the input method application displays the text content input by the user on the display screen of the electronic device 100 in response to the user's input operation, and the corresponding display position is the search box of the shopping application (for example, Figure 1 In the search box 1011 shown.

[0120] S506: The user clicks the search control of the input method panel.

[0121] S507: The input method application responds to the search and sends the search results to the local database.

[0122] In some embodiments, in response to a user clicking on a search control of the input method panel, the input method application sends the search content input by the user to a local database, so that the local database stores the search content.

[0123] S508: The user clicks on the search control of the shopping application.

[0124] S509: The shopping application responds to the search and sends the search results to the local database.

[0125] In some embodiments, in response to a user clicking on a search control of a shopping application, the shopping application sends the search content input by the user to a local database, so that the local database stores the search content.

[0126] S510: The local database stores the search record.

[0127] In some embodiments, after receiving the search content input by the user, the local database stores the search content in encrypted form.

[0128] In some embodiments, the search content stored in the local database mainly includes the following fields: version number of the input method, timestamp, package name of the application, and keyword query input by the user.

[0129] S511: In response to a trigger condition, the local database sends the search record to the input method application.

[0130] In some embodiments, in response to a trigger condition, the local database sends the search content to the input method application. The trigger condition may include: when the electronic device 100 is connected to a power source and the power is greater than a power threshold (e.g., 50%); and the temperature of the electronic device 100 is less than a temperature threshold (e.g., 37 degrees Celsius); when the above conditions are met, the calculation is performed at most once within 24 hours, that is, the interval with the previous calculation time is greater than or equal to 24 hours.

[0131] S512: Calculate a label of the data model of the input method application.

[0132] In some embodiments, the input method application inputs the search content stored in the present search database into the data model, obtains a label corresponding to the search content, and outputs output data of the data model.

[0133] In some embodiments, the data model may use a method combining keyword matching and classification model. For example, semantic segmentation and other operations are performed on the keyword input by the user to obtain sub-keywords, and the sub-keywords are matched with words in the vocabulary preset for each label field (category). If the sub-keywords are successfully matched with the words in the vocabulary, the keyword currently calculated by the user is judged to be the label field corresponding to the vocabulary; if the sub-keywords are not successfully matched with the words in the vocabulary, the classification model is used to classify the keyword input by the user.

[0134] It can be understood that the classification model includes but is not limited to a support vector machine model, a k-nearest neighbor algorithm model, a decision tree model, a naive Bayes model, a deep neural network model, a convolutional neural network model, a recurrent neural network model, and various variants and combinations thereof, etc., and the present application does not impose any restrictions on this.

[0135] In some embodiments, the output data of the output data model is a file in json format and includes the following fields: version number of the input method, timestamp, package name of the application, and tag list tagList calculated by the data model based on the keyword input by the user. The tag list tagList includes tags; each tag tag includes a tag field key, a tag level, and a confidence score.

[0136] It can be understood that the timestamp represents a time period, that is, the time period from when the input method is started to when the user clicks the search / confirm control. The tag field indicates the category to which the keyword entered by the user belongs. The tag level may include N, and the smaller the tag level, the larger the range of the corresponding tag field, and the tag field corresponding to the largest tag level is the keyword entered by the user or a sub-keyword obtained based on the keyword entered by the user. The confidence level indicates the matching degree between the keyword entered by the user and the corresponding tag field, that is, the probability that the keyword entered by the user belongs to the corresponding tag field.

[0137] S513: The input method application donates output data to the data center.

[0138] In some embodiments, the input method application donates (sends) the output data of the data model to the data center, which performs further data processing. For example, the data center predicts the user behavior of each application based on the acquired tags and determines the recommended service content and / or recommended search terms.

[0139] It can be understood that the above interaction diagram only uses shopping applications as examples of applications and input method applications as examples of the execution subject of steps such as calculating tags. In other embodiments, the application may also be other applications including input boxes such as map applications and video applications; the execution subject of steps such as calculating tags may also be the corresponding module of the electronic device 100.

[0140] In summary, the data processing method provided in the embodiment of the present application improves the richness and completeness of tags by obtaining the search content of users in various applications and calculating tags.

[0141] An embodiment of the present application also provides a search method, including: a data center receives tags corresponding to search contents of various applications from an electronic device 100, determines recommended contents based on the tags corresponding to the search contents of various applications, and sends the obtained recommended contents to the electronic device 100.

[0142] The tag includes: tag field, tag level and confidence. The larger the tag level, the smaller the range of the corresponding tag field; and the tag field corresponding to the largest tag level is the keyword entered by the user or the sub-keyword obtained based on the keyword entered by the user. The confidence indicates the probability that the keyword entered by the user belongs to the corresponding tag field.

[0143] In some embodiments, the data center obtains the input time (timestamp) corresponding to the search content entered by the user in different applications and the package name of each application.

[0144] In some embodiments, the data center determines that the recommended application is an application based on the package name of each application and the timestamp corresponding to the keyword input by the user of each application, and determines the display time of the recommended application to be the time corresponding to the timestamp.

[0145] In other embodiments, the data center determines that the recommended applications are multiple applications based on the package names of each application and the timestamps corresponding to the keywords input by the user of each application, and determines the display time of the multiple recommended applications to be the time corresponding to the timestamp of one of the applications.

[0146] For example, based on the user's usage habits: the electronic device 100 recommends the user to open news applications and recommends financial news reading in the morning; recommends the user to open music software and recommends pop music during the user's commuting time; recommends the user to open sports software and recommends the user's favorite team's updates at noon; recommends the user to open shopping applications and recommends the user's favorite products in the evening; recommends the user to open video software and recommends the user's favorite videos before the user goes to bed, so as to improve the user's usage experience.

[0147] An embodiment of the present application also provides another search method, including: an application in the electronic device 100 obtains tags corresponding to the search content of each application from the data center, determines recommended search terms based on the obtained tags, and displays the recommended search terms in the search box.

[0148] Among them, the tag includes: tag field, tag level and confidence. The larger the tag level, the smaller the range of the corresponding tag field; and the tag field corresponding to the maximum tag level is the keyword entered by the user or the sub-keyword obtained according to the keyword entered by the user. The confidence indicates the probability that the keyword entered by the user belongs to the corresponding tag field. It can be understood that the application can be any application in the electronic device 100 that contains a search box and is authorized by the user.

[0149] In some embodiments, in response to a user activating a search box, such as a user clicking on the search box, the application displays recommended search terms in the search box.

[0150] In some embodiments, in response to a user's operation of launching an application, such as clicking an application icon to enter a display interface of the application, the application displays recommended search terms in a search box.

[0151] In some embodiments, in response to a user inputting content into a search box of an application, the application displays recommended keywords in an area below the search box.

[0152] In some embodiments, if the user activates / starts / inputs content and other operations corresponding to an input method application, the input method application obtains labels corresponding to the keywords input by the user of each application, determines recommended search terms based on the obtained labels, and displays the recommended search terms in the recommendation display area of ​​the input method application.

[0153] For example, assuming that a user has searched for camping sites multiple times in a map application, corresponding tags are generated based on the user's search history. When the user opens a shopping application and clicks the search box of the shopping application, recommended keywords for camping equipment products can be recommended to the user in the search box of the shopping application or in the recommendation display area of ​​the input method application to improve the user's experience.

[0154] In order to better understand the technical solutions of the embodiments of the present application, the structure of the equipment involved in the present application is introduced below with reference to the accompanying drawings.

[0155] For example, Figure 6 According to an embodiment of the present application, a structural schematic diagram of an electronic device 100 is shown.

[0156] like Figure 6 As shown, the electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, an interface module 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0157] It is to be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0158] The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0159] The controller can generate operation control signals according to the instruction operation code and timing signal to complete the control of instruction fetching and execution.

[0160] The processor 110 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may store instructions or data that the processor 110 has just used or cyclically used. If the processor 110 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0161] In some embodiments, the processor 110 may include one or more interfaces. The interface may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0162] The charging management module 140 is used to receive charging input from a charger. The charger can be a wireless charger or a wired charger. While the charging management module 140 charges the battery 142, it can also power the electronic device through the power management module 141.

[0163] The power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140, and supplies power to the processor 110, the internal memory 121, the display screen 194, the camera 193, and the wireless communication module 160. The power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle number, battery health status (leakage, impedance), etc. In some other embodiments, the power management module 141 can also be set in the processor 110. In other embodiments, the power management module 141 and the charging management module 140 can also be set in the same device. In some embodiments, the power management module 141 is used to detect the power connection status and the power level of the electronic device 100.

[0164] The electronic device 100 implements the display function through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, which connects the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or change display information.

[0165] The display screen 194 is used to display images, videos, etc. The display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light emitting diode or an active-matrix organic light emitting diode (AMOLED), a flexible light-emitting diode (FLED), Mini-Led, Micro-Led, Micro-oLed, quantum dot light-emitting diodes (QLED), etc. In some embodiments, the electronic device 100 may include 1 or N display screens 194, where N is a positive integer greater than 1. In some embodiments, the display screen 194 displays the user interface of each application of the electronic device 100.

[0166] The electronic device 100 can realize the shooting function through ISP, camera 193, video codec, GPU, display screen 194 and application processor.

[0167] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external memory interface 120 to implement a data storage function, such as storing music, video and other files in the external memory card.

[0168] The internal memory 121 can be used to store computer executable program codes, which include instructions. The internal memory 121 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data created during the use of the electronic device 100 (such as audio data, a phone book, etc.), etc. In addition, the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc. The processor 110 executes various functional applications and data processing of the electronic device 100 by running instructions stored in the internal memory 121, and / or instructions stored in a memory provided in the processor.

[0169] The electronic device 100 can implement audio functions through the audio module 170, such as music playing, recording, etc.

[0170] The pressure sensor 180A is used to sense the pressure signal and can convert the pressure signal into an electrical signal. In some embodiments, the pressure sensor 180A can be set on the display screen 194. There are many types of pressure sensors 180A, such as resistive pressure sensors, inductive pressure sensors, capacitive pressure sensors, etc. A capacitive pressure sensor can be a parallel plate including at least two conductive materials. When a force acts on the pressure sensor 180A, the capacitance between the electrodes changes. The electronic device 100 determines the intensity of the pressure based on the change in capacitance. When a touch operation acts on the display screen 194, the electronic device 100 detects the intensity of the touch operation according to the pressure sensor 180A. The electronic device 100 can also calculate the position of the touch based on the detection signal of the pressure sensor 180A. In some embodiments, touch operations acting on the same touch position but with different touch operation intensities can correspond to different operation instructions.

[0171] The temperature sensor 180J is used to detect temperature. In some embodiments, the electronic device 100 detects the battery temperature of the electronic device 100 using the temperature sensor 180J.

[0172] The touch sensor 180K is also called a "touch control device". The touch sensor 180K can be set on the display screen 194. The touch sensor 180K and the display screen 194 form a touch screen, also called a "touch control screen". The touch sensor 180K is used to detect touch operations acting on or near it. The touch sensor can pass the detected touch operation to the application processor to determine the type of touch event. Visual output related to the touch operation can be provided through the display screen 194. In other embodiments, the touch sensor 180K can also be set on the surface of the electronic device 100, which is different from the position of the display screen 194.

[0173] The key 190 includes a power key, a volume key, etc. The key 190 may be a mechanical key or a touch key. The electronic device 100 may receive key input and generate key signal input related to user settings and function control of the electronic device 100.

[0174] Motor 191 can generate vibration prompts. Motor 191 can be used for incoming call vibration prompts, and can also be used for touch vibration feedback. For example, touch operations acting on different applications (such as taking pictures, audio playback, etc.) can correspond to different vibration feedback effects. For touch operations acting on different areas of the display screen 194, motor 191 can also correspond to different vibration feedback effects. Different application scenarios (for example: time reminders, receiving messages, alarm clocks, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also support customization.

[0175] Indicator 192 may be an indicator light, which may be used to indicate charging status, power changes, messages, missed calls, notifications, etc.

[0176] For example, Figure 7 According to an embodiment of the present application, a schematic block diagram of a software system architecture of an electronic device 100 is shown.

[0177] The software system architecture of the electronic device 100 may adopt a layered architecture, an event-driven architecture, a micro-core architecture, a micro-service architecture, or a cloud architecture. The embodiment of the present application takes the Android system of the layered architecture as an example to exemplify the software structure of the electronic device 100.

[0178] Figure 7The layered architecture of the electronic device 100 shown divides the software into several layers, each layer has a clear role and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the Android system is divided into four layers, from top to bottom, namely, the application layer, the application framework layer, the Android runtime (Android runtime) and the system library, and the kernel layer.

[0179] like Figure 7 As shown, the application layer may include a series of application packages, which may include camera, shopping, calendar, call, map, navigation, WLAN, input method, music, short message and other applications.

[0180] like Figure 7 As shown, the application framework layer may include a window manager, a content provider, a view system, a phone manager, a resource manager, a notification manager, and the like.

[0181] The window manager is used to manage window programs. The window manager can obtain the display screen size, determine whether there is a status bar, lock the screen, capture the screen, etc.

[0182] Content providers are used to store and retrieve data and make it accessible to applications. This data can include search content, videos, images, audio, calls made and received, browsing history and bookmarks, phone books, etc.

[0183] The view system includes visual controls, such as controls for displaying text and controls for displaying images. The view system can be used to build applications. The display interface can be composed of one or more views. For example, the user interface of each application can include a view for displaying text and a view for displaying images.

[0184] The phone manager is used to provide the communication function of the electronic device 100 .

[0185] The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, and so on.

[0186] The notification manager enables applications to display notification information in the status bar. It can be used to convey notification-type messages and can disappear automatically after a short stay without user interaction. For example, the notification manager is used to notify download completion, message reminders, etc. The notification manager can also be a notification that appears in the system top status bar in the form of a chart or scroll bar text, such as notifications of applications running in the background, or a notification that appears on the screen in the form of a dialog window. For example, a text message is displayed in the status bar, a prompt sound is emitted, an electronic device vibrates, an indicator light flashes, etc.

[0187] Android runtime includes core libraries and virtual machines. Android runtime is responsible for scheduling and management of the Android system.

[0188] The core library consists of two parts: one is the function that needs to be called by the Java language, and the other is the Android core library.

[0189] The application layer and the application framework layer run in a virtual machine. The virtual machine executes the Java files of the application layer and the application framework layer as binary files. The virtual machine is used to perform functions such as object life cycle management, stack management, thread management, security and exception management, and garbage collection.

[0190] The kernel layer is the layer between hardware and software. The kernel layer contains at least display driver, camera driver, audio driver, and sensor driver.

[0191] The system library may include multiple functional modules, such as surface manager (SM), media libraries (ML), 3D graphics processing library (such as OpenGL ES), 2D graphics engine (such as SGL), etc.

[0192] The media library supports playback and recording of a variety of commonly used audio and video formats, as well as static image files, etc. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

[0193] The various embodiments of the mechanism disclosed in the present application can be implemented in hardware, software, firmware or a combination of these implementation methods. The embodiments of the present application can be implemented as a computer program or program code executed on a programmable system, which includes at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device and at least one output device.

[0194] Program code may be applied to input instructions to perform the functions described herein and to generate output information. The output information may be applied to one or more output devices in a known manner. For purposes of this application, a processing system includes any system having a processor such as, for example, a digital signal processor (DSP), a microcontroller, an application specific integrated circuit (ASIC), or a microprocessor.

[0195] Program code can be implemented with high-level programming language or object-oriented programming language to communicate with the processing system. When necessary, program code can also be implemented with assembly language or machine language. In fact, the mechanism described in this application is not limited to the scope of any specific programming language. In either case, the language can be a compiled language or an interpreted language.

[0196] In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried or stored on one or more temporary or non-temporary machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, instructions may be distributed over a network or through other computer-readable media. Therefore, machine-readable media may include any mechanism for storing or transmitting information in a machine (e.g., computer) readable form, including, but not limited to, floppy disks, optical disks, optical disks, read-only memories (CD-ROMs), magneto-optical disks, read-only memories (ROMs), random access memories (RAMs), erasable programmable read-only memories (EPROMs), electrically erasable programmable read-only memories (EEPROMs), magnetic or optical cards, flash memory, or tangible machine-readable memories for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using the Internet in electrical, optical, acoustic, or other forms of propagation signals. Accordingly, machine-readable media include any type of machine-readable media suitable for storing or transmitting electronic instructions or information in a form readable by a machine (eg, a computer).

[0197] In the accompanying drawings, some structural or method features may be shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not be required. Instead, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. In addition, the inclusion of structural or method features in a particular figure does not mean that such features are required in all embodiments, and in some embodiments, these features may not be included or may be combined with other features.

[0198] It should be noted that the units / modules mentioned in the various device embodiments of the present application are all logical units / modules. Physically, a logical unit / module can be a physical unit / module, or a part of a physical unit / module, or can be implemented as a combination of multiple physical units / modules. The physical implementation method of these logical units / modules themselves is not the most important. The combination of functions implemented by these logical units / modules is the key to solving the technical problems proposed by the present application. In addition, in order to highlight the innovative part of the present application, the above-mentioned device embodiments of the present application do not introduce units / modules that are not closely related to solving the technical problems proposed by the present application, which does not mean that there are no other units / modules in the above-mentioned device embodiments.

[0199] It should be noted that in the examples and description of this patent, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one" do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0200] Although the present application has been illustrated and described with reference to certain preferred embodiments thereof, it will be apparent to those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present application.

Claims

1. A data processing method, characterized in that: include: The first electronic device acquires a plurality of search contents input by a user on the first electronic device, wherein the plurality of search contents are from a plurality of applications; The first electronic device generates search features of the multiple search contents, wherein the search features include: multiple categories corresponding to the search contents, category levels corresponding to the categories, and confidences, wherein the confidences represent the probability that the search contents belong to the categories; The first electronic device sends the search features of the plurality of search contents to the second electronic device.

2. The method according to claim 1, characterized in that The higher the category level corresponding to the category is, the smaller the scope represented by the category is.

3. The method according to claim 2, characterized in that The category with the highest category level among the categories is the search content input by the user, or The category with the highest category level among the categories is the keyword of the search content.

4. The method according to claim 2, characterized in that: The plurality of search contents include a first search content and a second search content; and The first electronic device acquires a plurality of search contents input by a user on the first electronic device, including: detecting that a user inputs a first search content of a first application, and the first electronic device currently does not meet a trigger condition, storing the first search content, Detecting that the user inputs a second search content of the second application, and the first electronic device currently does not meet the trigger condition, storing the second search content; and The first electronic device generates search features of the plurality of search contents, including: It is detected that the first electronic device meets the trigger condition, and the first search content and the second search content are calculated through a data model to obtain a first search feature of the first search content and a second search feature of the second search content respectively.

5. The method according to claim 4, characterized in that The trigger condition includes at least one of the following: The first electronic device is powered on; The battery power of the first electronic device is greater than a power threshold; The battery temperature of the first electronic device is less than a temperature threshold; The time interval from the last time the trigger condition was met is greater than the time threshold.

6. The method according to claim 4, characterized in that The data model includes at least one of the following models: Support vector machine model, k-nearest neighbor algorithm model, decision tree model, naive Bayes model, deep neural network model, convolutional neural network model, and recurrent neural network model.

7. The method according to claim 4, characterized in that The first electronic device acquires a plurality of search contents input by a user on the first electronic device, including: The first application package name of the first application and a first timestamp corresponding to the input time of the first search content, the second application package name of the second application and a second timestamp corresponding to the input time of the second search content are stored.

8. The method according to claim 7, characterized in that Also includes: First recommended content is displayed, wherein the first recommended content is generated based on a first search feature of the first search content and a second search feature of the second search content.

9. The method according to claim 8, characterized in that Also includes: Based on the first application package name and the first timestamp, it is determined that the first recommended content is a recommendation of the first application, and the display time of the first recommended content is a first time, wherein the first time is a time corresponding to the first timestamp.

10. The method according to claim 8, characterized in that Also includes: Based on the first application package name and the first timestamp, and the second application package name and the second timestamp, it is determined that the first recommended content is a recommendation of the first application and the second application, and the display time of the first recommended content is a second time, wherein the second time is a time corresponding to the first timestamp or the second timestamp.

11. A recommendation method, characterized in that: include: The second electronic device receives search features of multiple search contents from the first electronic device, wherein the multiple search contents are from multiple applications of the first electronic device, and the search features include: multiple categories corresponding to the search contents, category levels corresponding to the categories, and confidences, wherein the confidences represent the probability that the search contents belong to the categories; The second electronic device generates second recommended content corresponding to the first electronic device based on the search features of the multiple search contents; The second electronic device sends the second recommended content to the first electronic device.

12. The method according to claim 11, characterized in that The higher the category level corresponding to the category, the smaller the scope represented by the category; and The category with the highest category level among the categories is the search content input by the user, or The category with the highest category level among the categories is the keyword of the search content.

13. The method according to claim 12, characterized in that The multiple search contents include a first search content input by a user into a first application and a second search content input by a user into a second application; and The second electronic device receives a plurality of search features of search contents from the first electronic device, including: A first application package name of the first application and a first timestamp corresponding to the first search content input time, a second application package name of the second application and a second timestamp corresponding to the second search content input time are obtained.

14. The method according to claim 13, characterized in that The second electronic device generates second recommended content corresponding to the first electronic device based on the search features of the plurality of search contents, including: Based on the first application package name and the first timestamp, determine that the second recommended content is a recommendation of the first application, and the display time of the second recommended content is a third time, wherein the third time is a time corresponding to the first timestamp; or Based on the first application package name and the first timestamp, and the second application package name and the second timestamp, determine that the second recommended content is a recommendation of the first application and the second application, and the display time of the second recommended content is a fourth time, wherein the fourth time is a time corresponding to the first timestamp or the second timestamp.

15. A recommendation method, characterized in that: include: The third application of the first electronic device obtains search features of multiple search contents, wherein the multiple search contents are from multiple applications of the first electronic device, the multiple applications include a first application and a second application, and the search features include: multiple categories corresponding to the search contents, category levels corresponding to the categories, and confidences, wherein the confidences represent the probability that the search contents belong to the categories; The third application displays recommended search terms in a search box of the third application based on search features of the plurality of search contents.

16. The method according to claim 15, characterized in that The higher the category level corresponding to the category, the smaller the scope represented by the category; and The category with the highest category level among the categories is the search content input by the user, or The category with the highest category level among the categories is the keyword of the search content.

17. The method according to claim 16, characterized in that The third application displays recommended search terms in the search box of the third application based on the search features of the plurality of search contents, including at least one of the following: The third application displays the recommended search terms after the user activates the search box of the third application; After the third application is started, the recommended search term is displayed in the search box of the third application; When a user enters content in the search box of the third application, the third application displays the recommended search terms below the search box of the third application.

18. A readable medium, characterized in that The readable medium stores instructions, which, when executed on an electronic device, enable the electronic device to execute the method according to any one of claims 1 to 17.

19. An electronic device, characterized in that: include: a memory for storing instructions to be executed by one or more processors of the electronic device, and The processor is one of the processors of an electronic device, and is used to execute the method according to any one of claims 1 to 17.

Images