Information processing method, device, storage medium and electronic device

Abstract

The embodiment of the present invention discloses an information processing method, device, storage medium and electronic device, the method comprising: obtaining historical search data of a user; analyzing the historical search data to determine commonly used search terms; and establishing customized search results corresponding to the commonly used search terms according to the types of the commonly used search terms. The embodiment of the present invention obtains the commonly used search terms of the user according to the analysis of the historical search data of the user, and establishes different customized search results according to different types of commonly used search terms, so as to present different search results to the user according to different commonly used search terms, thereby avoiding the user from searching multiple times or needing to click on a link to find the search results that the user cares about, and providing a better user experience.

Description

Technical Field

[0001] The present invention relates to the field of the Internet, and in particular to an information processing method, device, storage medium and electronic equipment. Background Art

[0002] The existing technology can only record and store each search behavior of the user, and when the user searches again, the user's previous search terms are displayed below the search box in the form of a history record.

[0003] In the process of implementing the present invention, the inventors found that the prior art has at least the following defects: the number of search terms that can be displayed in the history records of the prior art is limited, and only the search terms that the user has searched most recently can be displayed in chronological order. If the user focuses on searching for a certain aspect of content or repeatedly uses the same search term for a period of time, but searches for other search terms in the middle, the repeated use of the same search term will be squeezed out of the history record by other search terms that come later in time, resulting in the user needing to manually enter the search term again to search when searching for the focused content again, and it is impossible to complete the search by clicking the reused search term in the history record, resulting in a poor user experience. Summary of the invention

[0004] In view of this, an embodiment of the present invention proposes an information processing method, device, storage medium and electronic device to solve the following problems in the prior art: if a user repeatedly uses the same search term, it will be squeezed out of the historical record by other search terms that come later in time, resulting in the user needing to manually enter the search term again when searching for the preferred content again, and being unable to complete the search by clicking on the reused search term in the historical record.

[0005] On the one hand, an embodiment of the present invention proposes an information processing method, which includes: obtaining a user's historical search data; analyzing the historical search data to determine commonly used search terms; and establishing customized search results corresponding to the commonly used search terms based on the types of the commonly used search terms.

[0006] On the other hand, an embodiment of the present invention proposes an information processing device, including: an acquisition module for acquiring a user's historical search data; a determination module for analyzing the historical search data to determine commonly used search terms; and an establishment module for establishing customized search results corresponding to the commonly used search terms based on the types of the commonly used search terms.

[0007] On the other hand, an embodiment of the present invention provides a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method provided by any embodiment of the present invention.

[0008] On the other hand, an embodiment of the present invention provides an electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the method provided by any embodiment of the present invention when executing the computer program on the memory.

[0009] The embodiment of the present invention obtains the user's frequently used search terms based on the user's historical search data analysis, and establishes different customized search results according to the different types of frequently used search terms, so as to be able to present different search results to the user according to different frequently used search terms, thereby avoiding the user from searching multiple times or needing to click on a link to find the search result that the user is concerned about, and providing a better user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flowchart of an information processing method provided by a first embodiment of the present invention;

[0011] Figure 2 A schematic diagram of presenting a push window on a main page provided by the first embodiment of the present invention;

[0012] Figure 3 A schematic diagram of presenting a display window on a search result page provided by the first embodiment of the present invention;

[0013] Figure 4 A flowchart of an information processing method provided by a second embodiment of the present invention;

[0014] Figure 5 A schematic diagram of a display position provided for the second embodiment of the present invention;

[0015] Figure 6 A schematic diagram of the structure of an information processing device provided by a third embodiment of the present invention;

[0016] Figure 7 A schematic structural diagram of an electronic device provided in a fifth embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0019] In order to keep the following description of the embodiments of the present invention clear and concise, detailed descriptions of well-known functions and well-known components are omitted.

[0020] The first embodiment of the present invention provides an information processing method, the process of which is as follows: Figure 1 As shown, steps S101 to S103 are included:

[0021] S101, obtaining the user's historical search data.

[0022] The embodiment of the present invention is for each individual user. Different users pay attention to or like to search for different contents. The purpose of this embodiment is to identify the search needs or search intentions of users within a period of time based on the attention or search behaviors of different users, especially for repetitive search behaviors, and make targeted recommendations of search terms to users, and finally provide different personalized services for different users. Therefore, the implementation of the embodiment of the present invention is for a certain user, and what is obtained is the historical search data of each user.

[0023] Here, the meaning of historical search data is relatively broad, and may refer to data on user behavior of paying attention to certain search content, or may refer to data generated by user behavior of searching for certain search terms, among which data on user attention to certain search content may be data on operations such as user clicking a follow button; data on user search for search content may be behavior data on users manually entering search terms in a search box for active search, such as users actively entering “local weather” in the search box; or may be behavior data on users clicking on search terms in the search term association box for search, such as users entering “local” in the search box, and clicking on the pop-up “local weather” in the association box, thereby searching for local weather; of course, may also be behavior data on users finding search content of interest in the search results page and performing click operations for search, such as users obtaining a large number of search results by entering “local” in the search box, and clicking on content related to “local weather” in the search results, thereby searching for local weather, etc. User search data is not limited to the behavior data described above, and may also be other search behavior data, and the relevant data of these search behaviors will be recorded in historical search data.

[0024] In the process of obtaining the user's historical search data, it is necessary to first identify the user's search needs or search intentions. As mentioned above, the user can directly pay attention to certain search content to express the search needs or search intentions, and this attention behavior will be recorded; the user can also express the search needs or search intentions through search behavior. If the user is accustomed to obtaining relevant information through search, there will be more historical search data in a longer period of time. Therefore, a first cycle can be set to obtain historical search data according to the first cycle; in order to accurately count the user's search behavior, when the time set in the first cycle is short, a second cycle can be set. The second cycle includes multiple first cycles, and the number of searches in multiple first cycles is integrated through the second cycle. For example, the first cycle is 24 hours and the second cycle is 48 hours. The historical search data is counted once every 24 hours. After two statistics, the number of searches for each search term within 48 hours can be determined. This statistical method can reduce the processing load compared to the method of directly counting in a 48-hour cycle.

[0025] S102, analyzing historical search data to determine commonly used search terms.

[0026] After obtaining the user's historical search data, it can be found through analysis of the historical search data that some users pay attention to certain search content, or perform repeated searches for certain search terms within a certain period of time.

[0027] These users with fixed search needs or search intentions are taken as recommended users. In order to save the search costs of these recommended users and improve the search experience of these recommended users, this embodiment identifies the users' search needs or search intentions for certain search terms within a period of time, determines some commonly used search terms, and then recommends these commonly used search terms or their corresponding search results to the recommended users at a predetermined time, so that the recommended users can obtain relevant search terms or search results in a timely manner.

[0028] These recommended users have relatively clear search needs or search intentions for a period of time. Figure 1 Generally, it is directly associated with commonly used search terms. On the one hand, the search content that users pay attention to is generally the search term that users expect, and this search content is a commonly used search term; on the other hand, when searching, users may have repeated search needs for a certain search term within a period of time. For example, during a large-scale sports event, users will often search for content related to the large-scale sports event. During this period, the large-scale sports event may be a commonly used search term for users; for another example, users may have continuous or regular search needs for a certain time. For example, users may intend to search and learn about local weather conditions every day, so local weather is a commonly used search term that meets the user's search intention; for another example, users may intend to search and learn about lottery draws every week, so lottery draws are commonly used search terms that meet the user's search intention; for another example, users may often intend to search and learn about the column of a certain anchor or celebrity, and hope to get corresponding prompts when the column is updated for the first time, so the name of the anchor or celebrity's column is a commonly used search term that meets the user's search intention. In short, by obtaining the user's historical search data over a period of time, we can determine the common search terms that the user has repeated search needs for during this period. By determining the common search terms, we can prompt the user when he needs to search, which will improve the user's search experience and reduce the user's search cost.

[0029] S103: Creating customized search results corresponding to the commonly used search terms according to the types of the commonly used search terms.

[0030] There are many types of commonly used search terms, such as weather type, financial type, sports type, etc., but these types only represent the fields to which the commonly used search terms belong, and it is impossible to truly establish customized search results for commonly used search terms based on these fields. Therefore, in order to make the search results pushed to users more in line with search intent and more accurate, the types of commonly used search terms in an embodiment of the present invention can be divided according to whether they are time-sensitive types of commonly used search terms.

[0031] There are many kinds of time-sensitive commonly used search terms. For example, during a large-scale sports event, users will often search for content related to the large-scale sports event. During this period, the medal list of the large-scale sports event is a time-sensitive commonly used search term. However, if the large-scale sports event has ended for a while, users still often search for the medal list of the large-scale sports event, but at this time the medal list of the large-scale sports event is no longer a time-sensitive commonly used search term. For another example, users may search for local weather conditions at almost the same time period every day, then local weather is a time-sensitive commonly used search term. For another example, users may search for and learn about relevant information about the lottery draw every week, then lottery draw is a time-sensitive commonly used search term.

[0032] If the frequently used search terms are of non-time-sensitive type, then they are the user's personal preference, and customized search results can be established in a way that is convenient for users to find frequently used search terms; if the frequently used search terms are of time-sensitive type, then the frequently used search terms have a certain correlation with time, and customized search results need to be established with reference to time.

[0033] Preferably, when the type of commonly used search terms is a time-sensitive type, a push window of commonly used search results corresponding to the commonly used search terms is created on the main page when the time node corresponding to the commonly used search terms arrives; when the type of commonly used search terms is a non-time-sensitive type, a display window of commonly used search results corresponding to the commonly used search terms is created on the search results page.

[0034] For example, a user will check the local weather at around 6:30 every morning. The user will enter "weather" in the search box, and the user will click on the link corresponding to the local weather in the search results, then "local weather" will be determined as a common search term. For example, if the "local" located by the location permission is Beijing, then the common search term is "Beijing weather." Since the user checks the local weather at around 6:30 every morning, the type of common search terms is a time-sensitive type, and the customized search results that are created are common search results for common search terms that are pushed by the application in the push window on the main page at around 6:30 every day (for example, between 6:25 and 6:35). Figure 2 As shown in the figure, the weather content pushed to the main page when the user enters the application at around 6:30. This solution avoids the user from searching multiple times or clicking on a link to find the result the user is interested in, and provides a good user experience.

[0035] For another example, users often search for information related to "XX Finance" and often view articles published by "Financial Cai" at the bottom of the search results page. In this case, "XX Finance" is determined to be a common search term. Since the search time for "XX Finance" is irregular and the articles published by "Financial Cai" are also irregular, the common search term is a non-time-sensitive type. Figure 3As shown, when the user searches for relevant information about "XX Finance" again, the article published by "Finance Cai" originally at the bottom of the search results page will be adjusted to the display window at the top of the search results page.

[0036] The embodiment of the present invention obtains the user's frequently used search terms based on the user's historical search data analysis, and establishes different customized search results according to the different types of frequently used search terms, so as to be able to present different search results to the user according to different frequently used search terms, thereby avoiding the user from searching multiple times or needing to click on a link to find the search result that the user is concerned about, and providing a better user experience.

[0037] The second embodiment of the present invention provides an information processing method, the process of which is as follows: Figure 4 As shown, steps S401 to S405 are included:

[0038] S401, obtaining the user's historical search data.

[0039] The embodiment of the present invention is for each individual user. Different users pay attention to or like to search for different contents. The purpose of this embodiment is to identify the search needs or search intentions of users within a period of time based on the attention or search behaviors of different users, especially for repetitive search behaviors, and make targeted recommendations of search terms to users, and finally provide different personalized services for different users. Therefore, the implementation of the embodiment of the present invention is for a certain user, and what is obtained is the historical search data of each user.

[0040] Here, the meaning of historical search data is relatively broad, and may refer to data on user behavior of paying attention to certain search content, or may refer to data generated by user behavior of searching for certain search terms, among which data on user attention to certain search content may be data on operations such as user clicking a follow button; data on user search for search content may be behavior data on users manually entering search terms in a search box for active search, such as users actively entering “local weather” in the search box; or may be behavior data on users clicking on search terms in the search term association box for search, such as users entering “local” in the search box, and clicking on the pop-up “local weather” in the association box, thereby searching for local weather; of course, may also be behavior data on users finding search content of interest in the search results page and performing click operations for search, such as users obtaining a large number of search results by entering “local” in the search box, and clicking on content related to “local weather” in the search results, thereby searching for local weather, etc. User search data is not limited to the behavior data described above, and may also be other search behavior data, and the relevant data of these search behaviors will be recorded in historical search data.

[0041] In the process of obtaining the user's historical search data, it is necessary to first identify the user's search needs or search intentions. As mentioned above, the user can directly pay attention to certain search content to express the search needs or search intentions, and this attention behavior will be recorded; the user can also express the search needs or search intentions through search behavior. If the user is accustomed to obtaining relevant information through search, there will be more historical search data in a longer period of time. Therefore, a first cycle can be set to obtain historical search data according to the first cycle; in order to accurately count the user's search behavior, when the time set in the first cycle is short, a second cycle can be set. The second cycle includes multiple first cycles, and the number of searches in multiple first cycles is integrated through the second cycle. For example, the first cycle is 24 hours and the second cycle is 48 hours. The historical search data is counted once every 24 hours. After two statistics, the number of searches for each search term within 48 hours can be determined. This statistical method can reduce the processing load compared to the method of directly counting in a 48-hour cycle.

[0042] S402: Determine the user's search keywords based on historical search data.

[0043] When a user searches for data, the number of search terms is usually very large. In a large amount of historical search data, the number of times different search terms appear can be used as a way to divide the search keywords. For example, a search term that has been searched a predetermined number of times is determined as a search keyword. Of course, the above division method is only an example. Historical search data may include the user's continuous search process, so the search keyword can also be determined by the title of the search result in the clicked search result page. Specifically, keyword extraction is performed on the title content of the clicked search result.

[0044] The above method for determining the search keyword is only an example. Those skilled in the art may use more reasonable methods to determine the search keyword, which will not be described in detail here.

[0045] S403: Obtain the attribute score of the search keyword.

[0046] In this embodiment, the attribute score of the search keyword is obtained to determine whether the search keyword is a commonly used search term for the recommended user. Here, the attribute score represents the degree to which the search needs of the recommended user are met, which is represented by three dimensions, namely, the frequency of use of the search keyword by the user, the quality of the search keyword itself, and the user's feedback on the search results associated with the search keyword. Specifically, in order to facilitate the quantification of the user's demand level, the attribute score can be determined based on the following numerical quantifications: the number of searches for the search keyword, the quality score of the search keyword, and the quality score of the search results based on the search keyword.

[0047] Among them, the number of searches for the search keyword, this search behavior can be any form of search behavior involved in this embodiment; the quality score of the search keyword is mainly to filter out search terms that are not suitable for recommendation to users, and to reflect the health of the search keyword in the form of a quality score. For example, a black and white list mechanism can be used to judge the quality of the search keyword. Of course, the quality of the search keyword can also be scored according to other pre-set filtering mechanisms; the quality score of the search results based on the search keyword can be reflected in the health of the search results and the user's feedback behavior on the search results associated with the search keyword. For example, if the quality of the search results contains pornographic, violent and other content, the quality score is low. In addition, if the user does not click on the search results or does not browse them, it is identified as having a low quality score. The quality score of the search results can be scored in the form of a predetermined mechanism, and the dimensions involved in the search results can be quantified to ultimately obtain the quality score of the search results.

[0048] S404: When the attribute score is greater than a predetermined value, the search keyword is determined to be a commonly used search term.

[0049] After the attribute scores of the search keywords are determined through the above steps, the attribute scores of each search keyword are judged. When the attribute score is greater than a predetermined value, the search keyword is determined to be a commonly used search term. This predetermined value is the standard for judging whether the search keyword can be recommended to the recommended user. As long as the attribute score of the search keyword is greater than the predetermined value for the recommended user, it is marked as a commonly used search term and recommended to the recommended user when necessary. Of course, the number of commonly used search terms can be adjusted according to the size of the predetermined value, and the predetermined value can be set.

[0050] S405: Creating customized search results corresponding to the commonly used search terms according to the types of the commonly used search terms.

[0051] There are many types of commonly used search terms, such as weather type, financial type, sports type, etc., but these types only represent the fields to which the commonly used search terms belong, and it is impossible to truly establish customized search results for commonly used search terms based on these fields. Therefore, in order to make the search results pushed to users more in line with search intent and more accurate, the types of commonly used search terms in the embodiments of the present invention can be divided according to whether they are time-sensitive commonly used search terms.

[0052] There are many kinds of time-sensitive commonly used search terms. For example, during a large-scale sports event, users will often search for content related to the large-scale sports event. During this period, the medal list of the large-scale sports event is a time-sensitive commonly used search term. However, if the large-scale sports event has ended for a while, users still often search for the medal list of the large-scale sports event, but at this time the medal list of the large-scale sports event is no longer a time-sensitive commonly used search term. For another example, users may search for local weather conditions at almost the same time period every day, then local weather is a time-sensitive commonly used search term. For another example, users may search for and learn about relevant information about the lottery draw every week, then lottery draw is a time-sensitive commonly used search term.

[0053] If the frequently used search terms are of non-time-sensitive type, then they are the user's personal preference, and customized search results can be established in a way that is convenient for users to find frequently used search terms; if the frequently used search terms are of time-sensitive type, then the frequently used search terms have a certain correlation with time, and customized search results need to be established with reference to time.

[0054] Preferably, when the type of commonly used search terms is a time-sensitive type, a push window of commonly used search results corresponding to the commonly used search terms is created on the main page when the time node corresponding to the commonly used search terms arrives; when the type of commonly used search terms is a non-time-sensitive type, a display window of commonly used search results corresponding to the commonly used search terms is created on the search results page.

[0055] Furthermore, when the type of commonly used search terms is a non-time-sensitive type, since commonly used search terms of the non-time-sensitive type will not be displayed in the push window and require user search, in order to facilitate user search, this embodiment sets a position on the search middle page where commonly used search terms can be displayed. The specific process is as follows: create a display position for commonly used search terms on the search middle page; sort the commonly used search terms based on the attribute scores; when there are N display positions, associate the first N commonly used search terms in the sorting results with a display position respectively, where N is an integer greater than or equal to 1.

[0056] Taking into account the limitation of display space on the interface of electronic devices and in order to provide users with a better user experience, it is necessary to display the commonly used search terms that users most expect or that best meet their search needs or search intentions. Therefore, it is necessary to sort the commonly used search terms according to the attribute scores, and the commonly used search terms with high attribute scores are the commonly used search terms that most need to be recommended to users.

[0057] In implementation, the above display position can be the area corresponding to the history record, or the search box area, or it can be a separately set area parallel to the area corresponding to the history record. There is no limitation here, as long as it can enable users to quickly find the location of commonly used search terms.

[0058] The number N of commonly used search terms displayed can be adjusted appropriately according to the display position. For example, when the display position is the area corresponding to the history records, since the number of search terms that can be displayed in the history records is fixed, the number of commonly used search terms that are fixedly displayed should be less than the number of search terms that can be displayed in the history records. Of course, displaying too many commonly used search terms may bring a bad user experience to the user, so in the specific implementation, only one or two commonly used search terms that are most desired to be recommended to the user can be displayed. Figure 5 The following is a schematic diagram showing the location, where "Beijing Weather * The position where " is located is the display position. In order to allow users to distinguish between commonly used search terms and terms in historical records, an "*" is added to the upper right corner of "Beijing Weather". Technical personnel in this field can make equivalent changes according to actual needs as long as the purpose of reminding users can be achieved.

[0059] The embodiment of the present invention obtains the user's frequently used search terms based on the user's historical search data analysis, and establishes different customized search results according to the different types of frequently used search terms, so as to present different search results to the user according to different frequently used search terms, thereby avoiding the user from searching multiple times or needing to click on a link to find the search result that the user is concerned about; further, the user's search needs or search intentions within a period of time can be identified, and the frequently used search terms can be seen in the display position in a timely manner, so that quick operations can be performed based on the frequently used search terms without manually entering the frequently used search terms again, and the user experience is better.

[0060] The third embodiment of the present invention provides an information processing device, the structure of which is shown in FIG. Figure 6 As shown, including:

[0061] The acquisition module 10 is used to obtain the user's historical search data; the determination module 20 is coupled with the acquisition module 10 and is used to analyze the historical search data and determine the commonly used search terms; the establishment module 30 is coupled with the determination module 20 and is used to establish customized search results corresponding to the commonly used search terms according to the types of the commonly used search terms.

[0062] The embodiment of the present invention is for each individual user. Different users pay attention to or like to search for different contents. The purpose of this embodiment is to identify the search needs or search intentions of users within a period of time based on the attention or search behaviors of different users, especially for repetitive search behaviors, and make targeted recommendations of search terms to users, and finally provide different personalized services for different users. Therefore, the implementation of the embodiment of the present invention is for a certain user, and what is obtained is the historical search data of each user.

[0063] Here, the meaning of historical search data is relatively broad, and may refer to data on user behavior of paying attention to certain search content, or may refer to data generated by user behavior of searching for certain search terms, among which data on user attention to certain search content may be data on operations such as user clicking a follow button; data on user search for search content may be behavior data on users manually entering search terms in a search box for active search, such as users actively entering “local weather” in the search box; or may be behavior data on users clicking on search terms in the search term association box for search, such as users entering “local” in the search box, and clicking on the pop-up “local weather” in the association box, thereby searching for local weather; of course, may also be behavior data on users finding search content of interest in the search results page and performing click operations for search, such as users obtaining a large number of search results by entering “local” in the search box, and clicking on content related to “local weather” in the search results, thereby searching for local weather, etc. User search data is not limited to the behavior data described above, and may also be other search behavior data, and the relevant data of these search behaviors will be recorded in historical search data.

[0064] In the process of obtaining the user's historical search data, it is necessary to first identify the user's search needs or search intentions. As mentioned above, the user can directly pay attention to certain search content to express the search needs or search intentions, and this attention behavior will be recorded; the user can also express the search needs or search intentions through search behavior. If the user is accustomed to obtaining relevant information through search, there will be more historical search data in a longer period of time. Therefore, a first cycle can be set to obtain historical search data according to the first cycle; in order to accurately count the user's search behavior, when the time set in the first cycle is short, a second cycle can be set. The second cycle includes multiple first cycles, and the number of searches in multiple first cycles is integrated through the second cycle. For example, the first cycle is 24 hours and the second cycle is 48 hours. The historical search data is counted once every 24 hours. After two statistics, the number of searches for each search term within 48 hours can be determined. This statistical method can reduce the processing load compared to the method of directly counting in a 48-hour cycle.

[0065] After obtaining the user's historical search data, it can be found through analysis of the historical search data that some users pay attention to certain search content, or search for certain search terms within a certain period of time.

[0066] These users with fixed search needs or search intentions are taken as recommended users. In order to save the search costs of these recommended users and improve the search experience of these recommended users, this embodiment identifies the users' search needs or search intentions for certain search terms within a period of time, obtains some commonly used search terms, and then recommends these commonly used search terms or their corresponding search results to the recommended users at a predetermined time, so that the recommended users can obtain relevant search terms or search results in a timely manner.

[0067] These recommended users have relatively clear search needs or search intentions for a period of time. Figure 1 Generally, it is associated with commonly used search terms. On the one hand, the search content that users pay attention to is generally the search term that users expect, and this search content is a commonly used search term; on the other hand, when searching, users may have repeated search needs for a certain search term within a period of time. For example, during a large-scale sports event, users will often search for content related to the large-scale sports event. During this period, the large-scale sports event may be a commonly used search term for users; for another example, users may have continuous or regular search needs for a certain time. For example, users may intend to search and learn about local weather conditions every day, so local weather is a commonly used search term that meets the user's search intention; for another example, users may intend to search and learn about lottery draws every week, so lottery draws are commonly used search terms that meet the user's search intention; for another example, users may often intend to search and learn about the column of a certain anchor or celebrity, and hope to get corresponding prompts when the column is updated for the first time, so the name of the anchor or celebrity's column is a commonly used search term that meets the user's search intention. In short, by obtaining the user's historical search data over a period of time, we can determine the common search terms that the user has repeated search needs for during this period. By determining the common search terms, we can prompt the user when he needs to search, which will improve the user's search experience and reduce the user's search cost.

[0068] There are many types of commonly used search terms, such as weather type, financial type, sports type, etc., but these types only represent the fields to which the commonly used search terms belong, and it is impossible to truly establish customized search results for commonly used search terms based on these fields. Therefore, in order to make the search results pushed to users more in line with search intent and more accurate, the types of commonly used search terms in the embodiments of the present invention can be divided according to whether they are time-sensitive commonly used search terms.

[0069] There are many kinds of time-sensitive commonly used search terms. For example, during a large-scale sports event, users will often search for content related to the large-scale sports event. During this period, the medal list of the large-scale sports event is a time-sensitive commonly used search term. However, if the large-scale sports event has ended for a while, users still often search for the medal list of the large-scale sports event, but at this time the medal list of the large-scale sports event is no longer a time-sensitive commonly used search term. For another example, users may search for local weather conditions at almost the same time period every day, then local weather is a time-sensitive commonly used search term. For another example, users may search for and learn about relevant information about the lottery draw every week, then lottery draw is a time-sensitive commonly used search term.

[0070] If the commonly used search terms are of non-time-sensitive type, then they are the user's personal preferences, and customized search results can be established in a way that is convenient for users to find commonly used search terms; if the commonly used search terms are of time-sensitive type, then the commonly used search terms have a certain correlation with time, and it is necessary to refer to time to establish customized search results. Therefore, the above-mentioned establishment module can be specifically used for: when the type of commonly used search terms is of time-sensitive type, when the time node corresponding to the commonly used search terms arrives, a push window for commonly used search results corresponding to the commonly used search terms is created on the main page; when the type of commonly used search terms is of non-time-sensitive type, a display window for commonly used search results corresponding to the commonly used search terms is created on the search results page.

[0071] The above-mentioned determination module specifically includes a determination unit and an acquisition unit coupled to each other, wherein the determination unit is used to determine the user's search keyword based on historical search data; the acquisition unit is used to obtain the attribute score of the search keyword; the determination unit is also used to determine that the search keyword is a commonly used search term when the attribute score is greater than a predetermined value.

[0072] When a user searches for data, the number of search terms is usually very large. In a large amount of historical search data, the number of times different search terms appear can be used as a way to divide the search keywords. For example, a search term that has been searched a predetermined number of times is determined as a search keyword. Of course, the above division method is only an example. Historical search data may include the user's continuous search process, so the search keyword can also be determined by the title of the search result in the clicked search result page. Specifically, keyword extraction is performed on the title content of the clicked search result.

[0073] The above method for determining the search keyword is only an example. Those skilled in the art may use more reasonable methods to determine the search keyword, which will not be described in detail here.

[0074] In this embodiment, the attribute score of the search keyword is obtained to determine whether the search keyword is a commonly used search term for the recommended user. Here, the attribute score represents the degree to which the search needs of the recommended user are met, which is represented by three dimensions, namely, the frequency of use of the search keyword by the user, the quality of the search keyword itself, and the user's feedback on the search results associated with the search keyword. Specifically, in order to facilitate the quantification of the user's demand level, the above-mentioned determination module may also include a calculation unit for determining the attribute score of the search keyword based on at least one of predetermined values, and the predetermined values ​​include: the number of searches for the search keyword; the quality score of the search keyword; the quality score of the search results based on the search keyword.

[0075] Among them, the number of searches for the search keyword, this search behavior can be any form of search behavior involved in this embodiment; the quality score of the search keyword is mainly to filter out search terms that are not suitable for recommendation to users, and to reflect the health of the search keyword in the form of a quality score. For example, a black and white list mechanism can be used to judge the quality of the search keyword. Of course, the quality of the search keyword can also be scored according to other pre-set filtering mechanisms; the quality score of the search results based on the search keyword can be reflected in the health of the search results and the user's feedback behavior on the search results associated with the search keyword. For example, if the quality of the search results contains pornographic, violent and other content, the quality score is low. In addition, if the user does not click on the search results or does not browse them, it is identified as having a low quality score. The quality score of the search results can be scored in the form of a predetermined mechanism, and the dimensions involved in the search results can be quantified to ultimately obtain the quality score of the search results.

[0076] After determining the attribute score of the search keyword, the attribute score of each search keyword is judged. When the attribute score is greater than a predetermined value, the search keyword is determined to be a commonly used search term. This predetermined value is the standard for judging whether the search keyword can be recommended to the recommended user. As long as the attribute score of the search keyword is greater than the predetermined value for the recommended user, it is marked as a commonly used search term and recommended to the recommended user when necessary. Of course, the number of commonly used search terms can be adjusted according to the size of the predetermined value, and the predetermined value can be set.

[0077] In order to allow users to perform quick operations based on commonly used search terms, the establishment module also includes a display unit, which is used to create display positions for commonly used search terms in the search middle page; sort the commonly used search terms based on attribute scores; when there are N display positions, the first N commonly used search terms in the sorting results are respectively associated with a display position, where N is an integer greater than or equal to 1.

[0078] Taking into account the limitation of display space on the interface of electronic devices and in order to provide users with a better user experience, it is necessary to display the commonly used search terms that users most expect or that best meet their search needs or search intentions. Therefore, it is necessary to sort the commonly used search terms according to the attribute scores, and the commonly used search terms with high attribute scores are the commonly used search terms that most need to be recommended to users.

[0079] In implementation, the above display position can be the area corresponding to the history record, or the search box area, or it can be a separately set area parallel to the area corresponding to the history record. There is no limitation here, as long as it can enable users to quickly find the location of commonly used search terms.

[0080] The number N of commonly used search terms displayed can be adjusted appropriately according to different display positions. For example, when the display position is the area corresponding to the history records, since the number of search terms that can be displayed in the history records is fixed, the number of commonly used search terms that are fixedly displayed should be less than the number of search terms that can be displayed in the history records. Of course, displaying too many commonly used search terms may bring a bad user experience to the user, so in the specific implementation, only one or two commonly used search terms that are most desired to be recommended to the user can be displayed.

[0081] If the user is not satisfied with the displayed common search words or does not want to display the common search words, the user can cancel the common search words displayed at the display position through a predetermined operation.

[0082] The embodiment of the present invention obtains the user's frequently used search terms based on the user's historical search data analysis, and establishes different customized search results according to the different types of frequently used search terms, so as to present different search results to the user according to different frequently used search terms, thereby avoiding the user from searching multiple times or needing to click on a link to find the search result that the user is concerned about; further, the user's search needs or search intentions within a period of time can be identified, and the frequently used search terms can be seen in the display position in a timely manner, so that quick operations can be performed based on the frequently used search terms without manually entering the frequently used search terms again, and the user experience is better.

[0083] A fourth embodiment of the present invention provides a storage medium storing a computer program. When the computer program is executed by a processor, the method provided by any embodiment of the present invention is implemented. Exemplarily, the method includes the following steps S1 to S3:

[0084] S1, obtain the user's historical search data;

[0085] S2, analyze historical search data to determine commonly used search terms;

[0086] S3, according to the types of the commonly used search terms, establishing customized search results corresponding to the commonly used search terms.

[0087] When the computer program is executed by the processor to analyze the historical search data and determine the commonly used search terms, the processor specifically executes the following steps: determining the user's search keyword based on the historical search data; obtaining the attribute score of the search keyword; when the attribute score is greater than a predetermined value, determining that the search keyword is a commonly used search term. The attribute score of the search keyword is determined based on at least one of the following values: the number of searches for the search keyword; the quality score of the search keyword; the quality score of the search results based on the search keyword.

[0088] When the computer program is executed by the processor to establish customized search results corresponding to the commonly used search terms according to the types of the commonly used search terms, the processor specifically executes the following steps: when the type of the commonly used search terms is a time-sensitive type, a push window of the commonly used search results corresponding to the commonly used search terms is created on the main page when the time node corresponding to the commonly used search terms arrives; when the type of the commonly used search terms is a non-time-sensitive type, a display window of the commonly used search results corresponding to the commonly used search terms is created on the search results page.

[0089] The computer program is also executed by the processor to perform the following steps: create a display position for commonly used search terms in the search middle page; sort the commonly used search terms based on the attribute scores; when there are N display positions, associate the first N commonly used search terms in the sorting results with a display position respectively, where N is an integer greater than or equal to 1.

[0090] The computer program is further executed by the processor as follows: in response to an operation of canceling the display of the common search word at the display position, deleting the common search word from the display position.

[0091] The embodiment of the present invention obtains the user's frequently used search terms based on the user's historical search data analysis, and establishes different customized search results according to the different types of frequently used search terms, so as to present different search results to the user according to different frequently used search terms, thereby avoiding the user from searching multiple times or needing to click on a link to find the search result that the user is concerned about; further, the user's search needs or search intentions within a period of time can be identified, and the frequently used search terms can be seen in the display position in a timely manner, so that quick operations can be performed based on the frequently used search terms without manually entering the frequently used search terms again, and the user experience is better.

[0092] Optionally, in this embodiment, the above-mentioned storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk. Optionally, in this embodiment, the processor executes the method steps recorded in the above-mentioned embodiment according to the program code stored in the storage medium. Optionally, the specific examples in this embodiment can refer to the examples described in the above-mentioned embodiment and the optional implementation mode, and this embodiment will not be repeated here. Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented with a general computing device, which can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices. Optionally, they can be implemented with executable program codes of computing devices, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that here, or they can be made into individual integrated circuit modules respectively, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present invention is not limited to any specific combination of hardware and software.

[0093] A fifth embodiment of the present invention provides an electronic device, such as Figure 7 As shown, the electronic device at least includes a memory 901 and a processor 902. The memory 901 stores a computer program. The processor 902 implements the method provided by any embodiment of the present invention when executing the computer program on the memory 901. Exemplarily, the computer program steps are as follows S11 to S13:

[0094] S11, obtaining the user's historical search data;

[0095] S12, analyzing historical search data to determine commonly used search terms;

[0096] S13, creating customized search results corresponding to the commonly used search terms according to the types of the commonly used search terms.

[0097] When the processor 902 executes the computer program stored in the memory 901 for analyzing the historical search data and determining the commonly used search terms, the processor 902 specifically executes the following computer program: determining the user's search keyword based on the historical search data; obtaining the attribute score of the search keyword; when the attribute score is greater than a predetermined value, determining that the search keyword is a commonly used search term. The attribute score of the search keyword is determined based on at least one of the following values: the number of searches for the search keyword; the quality score of the search keyword; the quality score of the search results based on the search keyword.

[0098] When processor 902 executes a computer program stored in memory 901 for establishing customized search results corresponding to commonly used search terms based on the types of commonly used search terms, the computer program specifically executes the following: when the type of commonly used search terms is a time-sensitive type, a push window of commonly used search results corresponding to the commonly used search terms is created on the main page when the time node corresponding to the commonly used search terms arrives; when the type of commonly used search terms is a non-time-sensitive type, a display window of commonly used search results corresponding to the commonly used search terms is created on the search results page.

[0099] Processor 902 can also execute the following computer program stored in memory 901: create a display position for commonly used search terms in the search middle page; sort the commonly used search terms based on attribute scores; when there are N display positions, associate the first N commonly used search terms in the sorting results with a display position respectively, where N is an integer greater than or equal to 1.

[0100] The processor 902 may also execute the following computer program stored in the memory 901: in response to an operation of canceling the display of the common search word at the display position, the common search word is deleted from the display position.

[0101] The embodiment of the present invention obtains the user's frequently used search terms based on the user's historical search data analysis, and establishes different customized search results according to the different types of frequently used search terms, so as to present different search results to the user according to different frequently used search terms, thereby avoiding the user from searching multiple times or needing to click on a link to find the search result that the user is concerned about; further, the user's search needs or search intentions within a period of time can be identified, and the frequently used search terms can be seen in the display position in a timely manner, so that quick operations can be performed based on the frequently used search terms without manually entering the frequently used search terms again, and the user experience is better.

[0102] In addition, although exemplary embodiments have been described herein, the scope includes any and all embodiments based on the present invention with equivalent elements, modifications, omissions, combinations (e.g., various embodiments intersecting schemes), adaptations or changes. The elements in the claims will be interpreted broadly based on the language adopted in the claims, and are not limited to the examples described in this specification or during the implementation of this application, and the examples will be interpreted as non-exclusive. Therefore, this specification and examples are intended to be considered as examples only, and the true scope and spirit are indicated by the following claims and the full scope of their equivalents.

[0103] The above description is intended to be illustrative rather than restrictive. For example, the above examples (or one or more of them) can be used in combination with each other. For example, a person of ordinary skill in the art can use other embodiments when reading the above description. In addition, in the above-mentioned specific embodiments, various features can be grouped together to simplify the present invention. This should not be interpreted as an intention that a disclosed feature that is not required to be protected is necessary for any claim. On the contrary, the subject matter of the present invention may be less than all the features of a specific disclosed embodiment. Thus, the following claims are incorporated into the specific embodiments as examples or embodiments, wherein each claim is independently used as a separate embodiment, and it is considered that these embodiments can be combined with each other in various combinations or arrangements. The scope of the present invention should be determined with reference to the attached claims and the full scope of equivalent forms granted by these claims.

[0104] A number of embodiments of the present invention have been described in detail above, but the present invention is not limited to these specific embodiments. Those skilled in the art can make various variations and modifications to the embodiments based on the concept of the present invention, and these variations and modifications should all fall within the scope of protection claimed by the present invention.

Claims

1. An information processing method, characterized in that: The method comprises: Get the user's historical search data; Analyze the historical search data to determine commonly used search terms; According to the type of the commonly used search terms, creating customized search results corresponding to the commonly used search terms; The commonly used search terms are search terms with repeated search requirements; the types include: time-effective type and non-time-effective type; the commonly used search terms of the time-effective type include: commonly used search terms with periodic search time, or commonly used search terms related to current events and whose search time is within the time range of current events; the commonly used search terms of the non-time-effective type include: commonly used search terms with non-periodic search time, or commonly used search terms related to current events but whose search time is not within the time range of current events; The step of establishing customized search results corresponding to the commonly used search terms according to the types of the commonly used search terms includes: When the type of the commonly used search term is a time-effective type, a push window of commonly used search results corresponding to the commonly used search term is established on the main page when the time node corresponding to the commonly used search term arrives; When the type of the commonly used search term is a non-time-effective type, a display window of commonly used search results corresponding to the commonly used search term is established on the search result page for display; The method further comprises: When the type of the commonly used search words is a non-time-effective type, a display position of the commonly used search words is created in the search intermediate page to display the non-time-effective type commonly used search words, and the display position includes: a history record corresponding area.

2. The information processing method according to claim 1, characterized in that: The analyzing the historical search data to determine the commonly used search terms includes: Determining the user's search keywords according to the historical search data; Obtaining the attribute score of the search keyword; When the attribute score is greater than a predetermined value, the search keyword is determined to be the commonly used search term.

3. The information processing method according to claim 2, characterized in that: The attribute score of the search keyword is determined based on at least one of the following values: the number of searches for the search keyword; The quality score of the search keyword; A quality score of the search results based on the search keyword.

4. The information processing method according to claim 2, characterized in that: The step of creating a display position for commonly used search terms on the search intermediate page to display the commonly used search terms of the non-time-effective type includes: Creating a display position for the commonly used search terms on the search intermediate page; sorting the commonly used search terms based on the attribute scores; When there are N display positions, the first N commonly used search terms in the sorted results are respectively associated with one display position, wherein N is an integer greater than or equal to 1.

5. An information processing device, characterized in that: include: The acquisition module is used to obtain the user's historical search data; A determination module, used to analyze the historical search data and determine commonly used search terms; An establishing module, used to establish customized search results corresponding to the commonly used search terms according to the types of the commonly used search terms; The commonly used search terms are search terms with repeated search requirements; the types include: time-effective type and non-time-effective type; the commonly used search terms of the time-effective type include: commonly used search terms with periodic search time, or commonly used search terms related to current events and whose search time is within the time range of current events; the commonly used search terms of the non-time-effective type include: commonly used search terms with non-periodic search time, or commonly used search terms related to current events but whose search time is not within the time range of current events; The establishment module is specifically used for: When the type of the commonly used search term is a time-effective type, a push window of commonly used search results corresponding to the commonly used search term is established on the main page when the time node corresponding to the commonly used search term arrives; When the type of the commonly used search term is a non-time-effective type, a display window of commonly used search results corresponding to the commonly used search term is established on the search result page for display; The establishment module also includes: The display unit is used to create a display position of the commonly used search term in the search middle page when the type of the commonly used search term is a non-time-effective type, so as to display the commonly used search term of the non-time-effective type, and the display position includes: a history record corresponding area.

6. The information processing device according to claim 5, characterized in that The determination module comprises: A determination unit, configured to determine a search keyword of the user according to the historical search data; An acquisition unit, used to acquire the attribute score of the search keyword; The determining unit is further configured to determine that the search keyword is the commonly used search term when the attribute score is greater than a predetermined value.

7. The information processing device according to claim 6, wherein: The module also includes: A calculation unit is used to determine the attribute score of the search keyword based on at least one of predetermined values, wherein the predetermined value includes: the number of searches for the search keyword; the quality score of the search keyword; and the quality score of the search results based on the search keyword.

8. The information processing device according to any one of claims 6 to 7, characterized in that: The display unit is specifically used to: create a display position for the commonly used search terms in the search middle page; sort the commonly used search terms based on the attribute scores; when there are N display positions, associate the first N commonly used search terms in the sorting results with one of the display positions respectively, where N is an integer greater than or equal to 1.

9. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

10. An electronic device, comprising at least a memory and a processor, wherein a computer program is stored in the memory, wherein: The processor implements the steps of the method of any one of claims 1 to 4 when executing the computer program on the memory.

Images