Information push method, device and electronic equipment

Abstract

This application discloses an information push method, device, and electronic device, relating to the field of Internet technology. The method comprises: obtaining information about a user's reading behavior when reading electronic documents; determining target geographic location information based on the reading behavior information; and pushing target information based on the target geographic location information. This solution enables the push of information of interest to users based on their personalized needs.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to an information push method, device, and electronic device. Background Art

[0002] Existing content recommendation methods include the following: the first is re-recommendation for the same author, the second is re-recommendation based on what users who have read similar books have also read, and the third is cross-type recommendation, that is, recommending e-books based on purchased paper books or recommending original works based on watching videos, etc. However, the above recommendation methods cannot meet the personalized needs of users. Summary of the Invention

[0003] The purpose of this application is to provide an information push method, device and electronic device, so as to solve the problem that the recommendation method in the prior art cannot meet the personalized needs of users.

[0004] In order to achieve the above-mentioned purpose, the present application provides an information push method, comprising:

[0005] Obtaining user reading behavior information of electronic documents;

[0006] determining target geographic location information based on the reading behavior information;

[0007] Target information is pushed according to the target geographic location information.

[0008] Optionally, before determining the current geographical location information based on the reading behavior information, the method further includes:

[0009] Identify the content in the electronic file based on a semantic recognition algorithm to obtain first content related to the geographic location;

[0010] Geographic location information is generated according to the first content, and the target geographic location information is one or more of the geographic location information.

[0011] Optionally, generating geographic location information according to the first content includes at least one of the following:

[0012] determining the first content as the geographic location information;

[0013] Determining the geographical location name corresponding to the first content as the geographical location information according to a pre-configured mapping relationship between geographical location-related content and geographical location names;

[0014] According to a pre-configured mapping relationship between geographic location-related content and geographic location levels, the geographic location level corresponding to the first content is determined as the geographic location information.

[0015] Optionally, determining target geographic location information based on the reading behavior information includes:

[0016] Determining a first portion of content based on the reading behavior information; the first portion of content is content in the electronic file whose reading parameters meet a first preset condition;

[0017] The target geographic location information is determined based on the first part of the content.

[0018] Optionally, determining the target geographic location information according to the first part of the content includes:

[0019] In the first part of the content, determining the frequency of occurrence of candidate geographic location information;

[0020] At least one piece of geographic location information in the candidate geographic location information whose occurrence frequency meets a second preset condition is determined as the target geographic location information.

[0021] Optionally, determining the target geographic location information according to the first part of the content includes:

[0022] Retrieving the occurrence frequency of second content in the first portion of content; wherein the second content corresponds to the first geographic location level;

[0023] If a third content is retrieved, the search for the occurrence frequency of the second content is stopped and the occurrence frequency of the third content is searched; wherein the third content corresponds to a second geographic location level, and the second geographic location level is higher than the first geographic location level; and the geographic location name corresponding to the third content is the same as the geographic location name corresponding to the second content;

[0024] The target geographic location information is determined according to the appearance frequency of the third content.

[0025] Optionally, determining the target geographic location information according to the appearance frequency of the third content includes:

[0026] If the occurrence frequency of the third content meets a third preset condition, determining the geographical location information corresponding to the third content as the target geographical location information;

[0027] If the occurrence frequency of the third content does not meet the third preset condition, resuming the search for the occurrence frequency of the second content;

[0028] The target geographic location information is determined according to the appearance frequency of the second content and the third content.

[0029] Optionally, determining the target geographic location information according to the occurrence frequency of the second content and the third content includes:

[0030] If the occurrence frequency of the second content meets a fourth preset condition, determining the geographical location information corresponding to the second content and the geographical location information corresponding to the third content as the target geographical location information;

[0031] The relevance of the geographical location information corresponding to the second content is higher than the relevance of the geographical location information corresponding to the third content, and different relevance levels correspond to different recommendation strategies.

[0032] Optionally, the method further includes:

[0033] Obtaining the location information of the user;

[0034] The pushing target information according to the target geographic location information includes:

[0035] Target information is pushed according to the location information of the user and the target geographical location information.

[0036] In a second aspect, in order to achieve the above-mentioned purpose, the embodiment of the present application further provides an information push device, comprising:

[0037] The first acquisition module is used to obtain the reading behavior information of the user reading the electronic file;

[0038] a determination module, configured to determine target geographic location information based on the reading behavior information;

[0039] The push module is used to push target information according to the target geographical location information.

[0040] In the third aspect, in order to achieve the above-mentioned purpose, an embodiment of the present application also provides an electronic device, including: a transceiver, a processor, a memory, and a computer program stored on the memory and runnable on the processor, wherein when the computer program is executed by the processor, the steps of the information push method described in the first aspect are implemented.

[0041] In a fourth aspect, in order to achieve the above-mentioned purpose, an embodiment of the present application further provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the information push method described in the first aspect are implemented.

[0042] The above technical solution of the present application has at least the following beneficial effects:

[0043] The information push method of the embodiment of the present application first obtains information about a user's reading behavior of an electronic document; secondly, based on the reading behavior information, it determines target geographic location information; the target geographic location is related to the user's reading behavior and, therefore, may be a place of interest to the user; finally, based on the target geographic location information, it pushes the target information. In this way, information of interest to the user is pushed based on the user's preferences, achieving the goal of pushing relevant information according to the user's personalized needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of the information push method according to an embodiment of the present application;

[0045] Figure 2 This is the second flow chart of the information push method according to an embodiment of the present application;

[0046] Figure 3 This is a structural diagram of an information push device according to an embodiment of the present application;

[0047] Figure 4 This is a schematic structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0049] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects and are not used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of this application can be implemented in an order other than those illustrated or described herein. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0050] The information push method, device and electronic device provided in the embodiments of the present application are described in detail below with reference to the accompanying drawings through specific embodiments and their application scenarios.

[0051] like Figure 1 FIG. 1 is a flow chart of an information push method according to an embodiment of the present application, and the method includes:

[0052] Step 101: Obtaining user's reading behavior information of electronic files;

[0053] It should be noted here that the electronic file refers to a file that is produced in a digital device and environment, stored in digital form on a carrier such as a tape, disk, or CD, read and processed by a digital device such as a computer, and can be transmitted over a communication network. For example, an electronic file can be an e-book, audio file, or video file.

[0054] The reading behavior information in this step can be one or more of reading time, reading frequency, and reading annotations, but is not limited to these. The reading time can be determined according to the length of time the same content is displayed on the screen of the electronic device, and the reading frequency can be determined according to the number of times the same content is displayed on the screen of the electronic device; reading annotations are annotations added by users when reading electronic files.

[0055] Step 102: determining target geographic location information based on the reading behavior information;

[0056] In this step, the target geographic location information determined based on the reading behavior information should be the geographic location that the user is interested in. For example, when the user reads the content currently displayed on the electronic device for more than a preset time, or the user reads the currently displayed content multiple times, or the user adds annotation information when reading the currently displayed content, it is inferred that the user is interested in the currently displayed content, and the currently displayed content should be related to the target geographic location. Therefore, the target geographic location information can be determined based on the reading behavior information.

[0057] Step 103: Push target information according to the target geographic location information.

[0058] In this step, the target information is information related to the target geographical location information. For example, if the target geographical location information is Beijing, the target information may be information related to Beijing such as scenic spots, food, and hotels.

[0059] The information push method of the embodiment of the present application first obtains information about a user's reading behavior of an electronic document; secondly, based on the reading behavior information, it determines target geographic location information; the target geographic location is related to the user's reading behavior and, therefore, may be a place of interest to the user; finally, based on the target geographic location information, it pushes the target information. In this way, information of interest to the user is pushed based on the user's preferences, achieving the goal of pushing relevant information according to the user's personalized needs.

[0060] Furthermore, as an optional implementation, before determining the current geographical location information based on the reading behavior information, the method further includes:

[0061] Identify the content in the electronic file based on a semantic recognition algorithm to obtain first content related to the geographic location;

[0062] It should be noted that when the electronic file is an image, audio, or video, the electronic file can first be recognized and converted into text. The text can then be meaningfully segmented to create a semantic set that potentially represents a geographic location. The elements in this semantic set comprise the first content. For example, the first content may include: author information, information containing geographic location names, images, audio, or video containing scenic spots, buildings, or latitude and longitude information, poetry and its annotations, and special scenes such as cruise ships and deserts.

[0063] Geographic location information is generated according to the first content, and the target geographic location information is one or more of the geographic location information.

[0064] In this step, the geographic location information is related to the first content. For example, if the first content is the delicacy "roast duck", the geographic location information can be Beijing, Nanjing and other geographic locations related to roast duck. If the first content is the author information, the geographic location information related to the first content can be related information about the author's hometown.

[0065] Here, it should be noted that this optional implementation can be specifically implemented in the following centralized manner:

[0066] Method 1: After the author of an electronic file uploads the work, the electronic file is identified, first content is obtained, and the first content is marked. When a user reads the electronic file, one or more contents of interest to the user are determined from the marked first content based on the user's reading behavior information. Then, target geographic location information is determined based on the contents of interest to the user. The contents of interest to the user may include content that the user has read repeatedly, content that the user has read for a long time, or content that the user has annotated.

[0067] Method 2: After the author of the electronic file uploads the work, the electronic file is identified to obtain the first content, the geographic location information related to the first content is determined, and the first content is marked using the geographic location information related to the first content, that is, the geographic location information related to the first content is used as the marking information of the first content.

[0068] Method three: When a user reads an electronic file, the portion of the electronic file that the user is interested in is determined based on the user's reading behavior. Then, the portion of the electronic file that the user is interested in is identified to obtain first content, and geographic location information related to the first content is determined. The geographic location information related to the first content is used as tag information of the first content to mark the first content.

[0069] As a specific implementation, generating geographic location information according to the first content includes at least one of the following:

[0070] (1) determining the first content as the geographic location information;

[0071] For example, when the first content is a geographical location name, such as Chongqing, Beijing, etc., it is determined that the first content itself is the geographical location information related thereto.

[0072] (2) determining the geographical location name corresponding to the first content as the geographical location information according to a pre-configured mapping relationship between geographical location-related content and geographical location names;

[0073] For example, when the first content is a tourist attraction such as the Forbidden City, a delicacy such as roast duck, or a scenery such as maple leaves, the geographical location name corresponding to the first content is determined as the geographical location information of the first content according to the following mapping relationship table between geographical location-related content and geographical location names;

[0074] (3) According to a pre-configured mapping relationship between geographic location-related content and geographic location levels, the geographic location level corresponding to the first content is determined as the geographic location information.

[0075] Here, it should be noted that the geographic location level is related to the coverage of the geographic location, for example, based on the natural division of the location. In addition, the geographic location information may also include latitude and longitude information related to the first content.

[0076] The following is an example of the process of establishing each pre-configured mapping relationship in this specific implementation:

[0077] (1) Geographic location matching:

[0078] In map applications (such as Amap), basic place name matching is performed and the matched place names are marked as level 1 (provinces and cities), level 2 (scenic spots), and level 3 (streets) according to their scope.

[0079] Extract provinces, cities, districts, streets, and scenic spots from the map application, store their names, longitudes and latitudes, and range sizes in the backend data storage, and generate a geographic location matching table, as shown in Table 1 below:

[0080]

[0081] Table 1

[0082] (2) Geographic location and content matching:

[0083] Using the strong location information, place names and location level information (characterizing coverage) matched based on Table 1, a location association information table is matched and constructed. By inputting a place name, content information that is strongly correlated with the location is obtained.

[0084] That is, when the first content is a geographic location name, the geographic location information of the first content can be determined based on Table 1. For example, the geographic location information of the first content includes at least one of the first content itself, the longitude and latitude information corresponding to the first content, and the geographic location level corresponding to the first content.

[0085] Travel information matching:

[0086] Input information: the geographic location name obtained from Amap;

[0087] Processing: Enter the location name into the travel website database, search for relevant information about the location, and identify key content nouns through semantic recognition;

[0088] For example: Beijing: Search results include: Attractions: The Great Wall, Forbidden City; Food: Roast Duck, Qingfeng Baozi; Scenery: Maple Leaves, Snow;

[0089] Output: Input the obtained geographic locations one by one into the travel website for matching, and obtain a matching mapping table of geographic location and content information. The geographic location and content matching table is as follows:

[0090]

[0091] Table 2 (III) Special content matching table:

[0092]

[0093] Table 3

[0094] Therefore, in this specific implementation, when generating geographic location information based on the first content, the geographic location information (geographic location name, latitude and longitude information, geographic location level, etc.) corresponding to the first content can be obtained by looking up a table. The mapping relationship formed by the above table can be updated regularly.

[0095] As an optional implementation, determining target geographic location information based on the reading behavior information includes:

[0096] Determining a first portion of content based on the reading behavior information; the first portion of content is content in the electronic file whose reading parameters meet a first preset condition;

[0097] Here, it should be noted that the first part of the content is at least part of the content in the electronic file. Taking the electronic file as an e-book as an example, the first part can be one or more chapters in the e-book, wherein the multiple chapters can be continuous or discontinuous.

[0098] Here, it should be noted that, when the reading behavior information includes reading time, the first preset condition is a time threshold, such as 10 minutes. Taking an e-book as an example, if the user reads a chapter for 10 minutes, the chapter is determined to be the first part; when the reading behavior information includes the number of times of reading, the first preset condition is a number threshold, such as 3 times. Taking an e-book as an example, if the user reads a chapter 3 times, the chapter is determined to be the first part;

[0099] The target geographic location information is determined based on the first part of the content.

[0100] This step may specifically be determining the target geographic location information according to the pre-marked content in the first part.

[0101] As a specific implementation, determining the target geographic location information according to the first part of the content includes:

[0102] In the first part of the content, determining the frequency of occurrence of candidate geographic location information;

[0103] In this step, the first part of the content may be identified, and the content related to the geographic location may be determined based on the identification result. The content related to the geographic location / the geographic location name / the geographic location level related to the content may be considered as candidate geographic location information, and the occurrence frequency of each content may be counted.

[0104] At least one piece of geographic location information in the candidate geographic location information whose occurrence frequency meets a second preset condition is determined as the target geographic location information.

[0105] Here, it should be noted that the second preset condition may be a preset frequency, such as 10 times; that is, if the candidate geographic location information appears 10 times or more, the candidate geographic location information is the target geographic location information.

[0106] It should also be noted that the second preset condition can be determined based on the type / literary nature of the electronic file, for example, the electronic file / work / chapter can be rated according to the correlation between the electronic file type (or work type) and the place name, and the second preset condition is determined based on the rating of the electronic file. For example, the higher the rating, the smaller the second preset condition. The mapping relationship between work type and rating is shown in the following table:

[0107] Title Nature of the work Rating Cultural Journey Travel Notes 3 siege Life novels 2 Travel Magazine travel 4 Teaching Materials Teaching Materials 1

[0108] Table 4

[0109] As another specific implementation, determining the target geographic location information according to the first part of the content includes:

[0110] Retrieving the occurrence frequency of second content in the first portion of content; wherein the second content corresponds to the first geographic location level;

[0111] Here, it should be noted that the first geographical location level may be the level corresponding to the geographical location with the largest coverage, such as the geographical location level 1 in Table 1 above.

[0112] If a third content is retrieved, the search for the occurrence frequency of the second content is stopped and the occurrence frequency of the third content is searched; wherein the third content corresponds to a second geographic location level, and the second geographic location level is higher than the first geographic location level; and the geographic location name corresponding to the third content is the same as the geographic location name corresponding to the second content;

[0113] That is, when searching for the first part of the content, if the second content is retrieved first, then in a subsequent search, a third content related to the second content is retrieved, the user's possible interest can be narrowed down to the third content. At this point, the search for the second content can be stopped and the third content can be directly searched. For example, if the second content is about Beijing and the third content is about the Forbidden City, when the third content is retrieved, it is confirmed that the user may be interested in the Forbidden City, so the search for the Forbidden City is continued.

[0114] The target geographic location information is determined according to the appearance frequency of the third content.

[0115] As a more specific implementation, determining the target geographic location information according to the appearance frequency of the third content includes:

[0116] If the occurrence frequency of the third content meets a third preset condition, determining the geographical location information corresponding to the third content as the target geographical location information;

[0117] Here, it should be noted that when the frequency of occurrence of the third content meets the third preset condition, it is determined that the first part of the content is strongly correlated with the geographical location corresponding to the third content. Among them, when the geographical location information corresponding to the third content is determined to be the target geographical location information, the second content related to the third content and with a larger coverage should also be the target geographical location information.

[0118] If the occurrence frequency of the third content does not meet the third preset condition, resuming the search for the occurrence frequency of the second content;

[0119] The target geographic location information is determined according to the appearance frequency of the second content and the third content.

[0120] Specifically, determining the target geographic location information according to the occurrence frequency of the second content and the third content includes:

[0121] If the occurrence frequency of the second content meets a fourth preset condition, determining the geographical location information corresponding to the second content and the geographical location information corresponding to the third content as the target geographical location information;

[0122] The relevance of the geographical location information corresponding to the second content is higher than the relevance of the geographical location information corresponding to the third content, and different relevance levels correspond to different recommendation strategies.

[0123] That is, when the occurrence frequency of the second content meets the fourth preset condition and the occurrence frequency of the third content does not meet the third preset condition, it is determined that the target geographic location includes the second content and the third content, and the first part of the content is strongly correlated with the second content and weakly correlated with the third content.

[0124] Here, it should be noted that the third content in the embodiment of the present application can be a geographical location noun or content such as food, scenery, etc. that represents the geographical location.

[0125] The following describes the process of determining the target geographic location information, with respect to the second content being location content or thing content:

[0126] The second content is the position content, such as the position noun:

[0127] Step 1: When the second content is location content, searching the first portion of content for the second content and third content related to the second content (location content and / or thing content) based on the second content and its tag information (geographic location information corresponding to the second content);

[0128] Step 2: Determine the target object and the association relationship between the target object and the first portion of content based on at least one of a first weight determined by the number of times the second content is retrieved and a weight determined by the number of times the third content is retrieved.

[0129] Specifically, step one includes:

[0130] If the third content is not retrieved, or if the corresponding weight does not reach the corresponding threshold when the retrieval of the third content is completed, continue to retrieve the second content;

[0131] After the third content is retrieved for the first time and before the weight corresponding to the third content reaches a corresponding threshold, the third content is retrieved from the first part of content.

[0132] Specifically, step two includes:

[0133] If the first weight reaches a first threshold, determining that the target geographic location information includes the first content and the geographic location information corresponding to the retrieved third content, and that the first portion of content is strongly correlated with the second content and weakly correlated with the third content;

[0134] When the weight corresponding to the third content reaches the corresponding threshold, it is determined that the target geographic location information includes geographic location information corresponding to the second content and the third content, and the first portion of content is strongly correlated with each of the target geographic locations.

[0135] The second content is the content of things, such as food, scenery and other nouns:

[0136] Step 1: In the first part of the content, search for the frequency of occurrence of the second content, as well as the frequency of occurrence of the location content and / or thing content corresponding to the geographic location information of the second content. For example, if the second content is roast duck and the geographic location information corresponding to the second content is Beijing / Nanjing, then location information related to Beijing / Nanjing, such as the Great Wall, the Forbidden City, etc., and / or thing information, such as Qingfeng steamed buns, etc., can be searched.

[0137] Step 2: Determine the target object and the association relationship between the target object and the first portion of content based on at least one of a first weight determined by the number of times the second content is retrieved and a weight determined by the number of times the third content is retrieved.

[0138] Next, combine Figure 2 The implementation process of this specific implementation method is described as follows:

[0139] Part 1: Extracting geographic location and related content information from the full text through geographic location and context relevance:

[0140] Input: Parse the geographic location from the article using the aforementioned identification method, obtain the first and second level location names with fixed location information, and then use the three-layer model shown above to determine the relevance information contained in the context.

[0141] (1) Judgment method: If the input is a level 1 location, then determine whether the context (a certain chapter) has relevant, level 1, level 2, or content information. If so, weight it and enter the level 2 address or content judgment logic;

[0142] If there is no secondary geographic location or content information, but the primary address information appears multiple times, the weight is increased by one each time it appears. When the weight reaches the threshold, the content of this paragraph is output as being related to this primary geographic location.

[0143] If there is a secondary geographic location or content related to the primary geographic location, then enter the corresponding secondary geographic location judgment model or content judgment model

[0144] If the threshold is reached after the weighting of the secondary geographic location level, it is concluded that the segment of content is strongly correlated with both the primary and secondary geographic locations; if the threshold is reached after the weighting of the content level, it is concluded that the segment of content is strongly correlated with both the primary location and the content. If neither the secondary geographic location level nor the content level reaches the corresponding threshold, then the primary model is returned and weighted. After the weighting reaches the threshold, it is concluded that the segment of content is strongly correlated with one primary geographic location information and weakly correlated with several secondary geographic location information or content information.

[0145] (2) If the input is a secondary geographic location, the process directly enters the secondary geographic location judgment. When the same secondary location information appears again, the secondary location information is weighted and the context is continued to be retrieved;

[0146] If no relevant content appears but the secondary location information appears repeatedly and reaches the weighted threshold, a strongly relevant secondary geographic location is finally obtained;

[0147] If relevant content appears, it enters the content judgment level. If the relevant content ultimately does not reach the threshold, it returns to the secondary model and weights the secondary location to finally output that the segment of content has a strong correlation with a secondary geographic location and a weak correlation with several contents. If the repeated weighting at the content level exceeds the threshold, it outputs that the segment of content has a strong correlation with a secondary geographic location and a content.

[0148] Part 2: By inputting content (information about things, such as food, scenery, etc.), reversely judge whether the paragraph is strongly related to a certain geographical location information:

[0149] 1) When content is input, the content location matching table is used to determine the primary or secondary geographic location information that may be related to the content, and ultimately multiple primary and secondary geographic location information that may be related is obtained.

[0150] 2) This primary and secondary location information is fed into the model for contextual retrieval: secondary location information and content related to primary location information, and content related to secondary location information. This primary and secondary location information is fed into the model for reverse comparison. If no obvious location information appears throughout the entire text, but the content associated with the corresponding location information appears multiple times, then the multi-content weighting will still reach the threshold at the primary or secondary location layer. In this case, even if the content does not appear in the context, it can still be determined that the text is strongly related to a specific or secondary location.

[0151] Here, based on the above implementations, the process of pushing target information according to the target geographic location information includes:

[0152] (1) Based on the output of the content processing model, a decision tree model is used to dynamically determine the weight of the recommendation results;

[0153] (2) The semantic vector extracted from the user's reading content and the weighted weight determined in (1) are input into the expert scoring, neural network and other recommendation models to determine the recommended content.

[0154] Furthermore, as an optional implementation, the method further includes:

[0155] Obtaining the location information of the user;

[0156] The pushing target information according to the target geographic location information includes:

[0157] Target information is pushed according to the location information of the user and the target geographical location information.

[0158] That is to say, in this optional implementation, after determining the recommended information based on the target geographic location information, the recommended information can also be determined based on the user's location information. Finally, the overlap between the recommended content and the recommended content obtained through the user's real-time location information is calculated using models such as logistic regression analysis, linear regression analysis, and cluster analysis, and the content with the greatest overlap is used as the final recommended content.

[0159] The information push method of the embodiment of the present application monitors user reading behavior, records the user's reading behavior of content with basic tags during the user's reading process, and uses real-time parsing rules to derive location information data of interest to the user based on the basic tagged content and tagged information. In this way, the user's preferences are judged based on the frequency and duration of the user's reading of content related to the corresponding latitude and longitude and scenic spots. Based on the user's preference for location, recommended content is selected for the user from the recommended content library and displayed in the front-end e-book or video. The recommended content may include travel information, such as scenic spots, hotel information, books, etc.

[0160] In short, the information push method of the embodiment of the present application, on the one hand, obtains the content related to the geographic location in the electronic file by identifying the content of the electronic file, and automatically adds a mark to the content; on the other hand, extracts the geographic location information in the electronic file, specifically, divides the content in the electronic file through a semantic recognition algorithm, identifies the location information corresponding to the e-book content, grades the obtained geographic location, and inputs the graded geographic location into the content processing model to obtain the strong and weak correlation between the content of the electronic file and each geographic location; thereby recommending relevant information to the user based on the strong and weak correlation between the content of the electronic file and each geographic location, specifically, based on the strong and weak correlation between the content of the electronic file and each geographic location, a decision tree model is used to determine the weighted weight of the recommendation result, the semantic vector and weighted weight of each geographic location are input into the neural network model, and the recommended content corresponding to each geographic location is output, and then a model such as logistic regression analysis is used to calculate the overlap between the recommended content and the recommended content obtained through the user's real-time location information, and the content with the largest overlap is used as the final recommended content.

[0161] It should be noted that the information push method provided in the embodiments of the present application can be executed by an information push device or a control module in the information push device for executing the loading information push method. In the embodiments of the present application, the information push method provided in the embodiments of the present application is described by taking the information push device executing the loading information push method as an example.

[0162] like Figure 3 As shown, the embodiment of the present application further provides an information push device, including:

[0163] The first acquisition module 301 is used to acquire the reading behavior information of the user reading the electronic file;

[0164] A determination module 302 is configured to determine target geographic location information based on the reading behavior information;

[0165] The push module 303 is configured to push target information according to the target geographic location information.

[0166] In the information push device of the embodiment of the present application, first, the first acquisition module 301 acquires information about a user's reading behavior when reading electronic documents. Second, the determination module 302 determines target geographic location information based on the reading behavior information. The target geographic location is related to the user's reading behavior and is therefore likely a location of interest to the user. Finally, the push module 303 pushes target information based on the target geographic location information. In this way, information of interest to the user is pushed based on the user's preferences, achieving personalized information push based on the user's needs.

[0167] Optionally, the device further comprises:

[0168] an identification module, configured to identify the content in the electronic file based on a semantic recognition algorithm to obtain first content related to the geographic location;

[0169] The generating module is configured to generate geographic location information according to the first content, wherein the target geographic location information is one or more of the geographic location information.

[0170] Optionally, the generating module is configured to perform at least one of the following:

[0171] determining the first content as the geographic location information;

[0172] Determining the geographical location name corresponding to the first content as the geographical location information according to a pre-configured mapping relationship between geographical location-related content and geographical location names;

[0173] According to a pre-configured mapping relationship between geographic location-related content and geographic location levels, the geographic location level corresponding to the first content is determined as the geographic location information.

[0174] Optionally, the determining module includes:

[0175] A first determining submodule is configured to determine a first portion of content based on the reading behavior information; the first portion of content is content in the electronic file whose reading parameters meet a first preset condition;

[0176] The second determining submodule is configured to determine the target geographic location information according to the first portion of content.

[0177] Optionally, the second determining submodule includes:

[0178] a first determining unit, configured to determine an occurrence frequency of candidate geographic location information in the first portion of content;

[0179] The second determining unit is configured to determine at least one piece of geographic location information in the candidate geographic location information whose occurrence frequency satisfies a second preset condition as the target geographic location information.

[0180] Optionally, the second determining submodule includes:

[0181] A first retrieval unit is configured to retrieve the occurrence frequency of second content in the first portion of content, wherein the second content corresponds to a first geographic location level;

[0182] a second retrieval unit configured to, if a third content is retrieved, stop searching for the occurrence frequency of the second content and search for the occurrence frequency of the third content; wherein the third content corresponds to a second geographic location level, and the second geographic location level is higher than the first geographic location level; and the geographic location name corresponding to the third content is the same as the geographic location name corresponding to the second content;

[0183] The third determining unit is configured to determine the target geographic location information according to the appearance frequency of the third content.

[0184] Optionally, the determining unit includes:

[0185] a first determining subunit, configured to determine the geographical location information corresponding to the third content as the target geographical location information if the occurrence frequency of the third content satisfies a third preset condition;

[0186] a second determining subunit, configured to resume searching for the occurrence frequency of the second content if the occurrence frequency of the third content does not satisfy the third preset condition;

[0187] The third determining subunit is configured to determine the target geographic location information according to the occurrence frequency of the second content and the third content.

[0188] Optionally, the third determining subunit is specifically configured to:

[0189] If the occurrence frequency of the second content meets a fourth preset condition, determining the geographical location information corresponding to the second content and the geographical location information corresponding to the third content as the target geographical location information;

[0190] The relevance of the geographical location information corresponding to the second content is higher than the relevance of the geographical location information corresponding to the third content, and different relevance levels correspond to different recommendation strategies.

[0191] Optionally, the device further comprises:

[0192] A second acquisition module is used to obtain the location information of the user;

[0193] Optionally, the push module is specifically configured to:

[0194] Target information is pushed according to the location information of the user and the target geographical location information.

[0195] like Figure 4As shown, an embodiment of the present application also provides an electronic device, including: a transceiver 410, a processor 400, a memory 420, and a program or instruction stored on the memory 420 and executable on the processor 400; when the processor executes the program or instruction, each process of the information push method embodiment as described above is implemented, and the same technical effect can be achieved. In order to avoid repetition, it will not be described here.

[0196] The transceiver 410 is configured to receive and send data under the control of the processor 400 .

[0197] Among them, Figure 4 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically connecting various circuits of one or more processors represented by processor 400 and memory represented by memory 420. The bus architecture may also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 410 may be a plurality of components, i.e., a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. For different terminal devices, the user interface 430 may also be an interface capable of connecting external or internal devices as required, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, etc.

[0198] The processor 400 is responsible for managing the bus architecture and general processing, and the memory 420 can store data used by the processor 400 when performing operations.

[0199] The present application also provides a readable storage medium having a program stored thereon. When the program is executed by a processor, the various processes of the information push method embodiment are implemented and can achieve the same technical effects. To avoid repetition, the details are not described here. The readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0200] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0201] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles described in the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An information push method, characterized in that: include: Acquiring reading behavior information of a user reading an electronic document; wherein the reading behavior information includes one or more of reading time, reading frequency, and reading annotations; Determining target geographic location information based on the reading behavior information; wherein the target geographic location information is a geographic location of interest to the user; Pushing target information according to the target geographic location information; wherein the target information is information related to the target geographic location and of interest to the user; The step of determining target geographic location information based on the reading behavior information includes: Determining a first portion of content based on the reading behavior information; the first portion of content is content in the electronic file whose reading parameters meet a first preset condition; Determining the target geographic location information based on the first part of the content; Determining the target geographic location information according to the first part of the content includes: Retrieving the occurrence frequency of second content in the first portion of content; wherein the second content corresponds to the first geographic location level; If a third content is retrieved, the search for the occurrence frequency of the second content is stopped and the occurrence frequency of the third content is searched; wherein the third content corresponds to a second geographic location level, and the second geographic location level is higher than the first geographic location level; and the geographic location name corresponding to the third content is the same as the geographic location name corresponding to the second content; The target geographic location information is determined according to the appearance frequency of the third content.

2. The method according to claim 1, characterized in that Before determining the current geographical location information based on the reading behavior information, the method further includes: Identify the content in the electronic file based on a semantic recognition algorithm to obtain first content related to the geographic location; Geographic location information is generated according to the first content, and the target geographic location information is one or more of the geographic location information.

3. The method according to claim 2, characterized in that Generating geographic location information according to the first content includes at least one of the following: determining the first content as the geographic location information; Determining the geographical location name corresponding to the first content as the geographical location information according to a pre-configured mapping relationship between geographical location-related content and geographical location names; According to a pre-configured mapping relationship between geographic location-related content and geographic location levels, the geographic location level corresponding to the first content is determined as the geographic location information.

4. The method according to claim 1, wherein The determining the target geographic location information according to the appearance frequency of the third content includes: If the occurrence frequency of the third content meets a third preset condition, determining the geographical location information corresponding to the third content as the target geographical location information; If the occurrence frequency of the third content does not meet the third preset condition, resuming the search for the occurrence frequency of the second content; The target geographic location information is determined according to the appearance frequency of the second content and the third content.

5. The method according to claim 4, characterized in that The determining the target geographic location information according to the occurrence frequency of the second content and the third content includes: If the occurrence frequency of the second content meets a fourth preset condition, determining the geographical location information corresponding to the second content and the geographical location information corresponding to the third content as the target geographical location information; The relevance of the geographical location information corresponding to the second content is higher than the relevance of the geographical location information corresponding to the third content, and different relevance levels correspond to different recommendation strategies.

6. The method according to claim 1, wherein The method further comprises: Obtaining the location information of the user; The pushing target information according to the target geographic location information includes: Target information is pushed according to the location information of the user and the target geographical location information.

7. An information push device, characterized in that: include: A first acquisition module is configured to acquire reading behavior information of a user when reading an electronic document; wherein the reading behavior information includes one or more of reading time, reading frequency, and reading annotations; a determination module, configured to determine target geographic location information based on the reading behavior information; wherein the target geographic location information is a geographic location of interest to the user; a push module, configured to push target information according to the target geographic location information, wherein the target information is information related to the target geographic location and of interest to the user; Wherein, the determination module includes: A first determining submodule is configured to determine a first portion of content based on the reading behavior information; the first portion of content is content in the electronic file whose reading parameters meet a first preset condition; A second determining submodule is configured to determine the target geographic location information based on the first portion of content; The second determining submodule includes: A first retrieval unit is configured to retrieve the occurrence frequency of second content in the first portion of content, wherein the second content corresponds to a first geographic location level; a second retrieval unit configured to, if a third content is retrieved, stop searching for the occurrence frequency of the second content and search for the occurrence frequency of the third content; wherein the third content corresponds to a second geographic location level, and the second geographic location level is higher than the first geographic location level; and the geographic location name corresponding to the third content is the same as the geographic location name corresponding to the second content; The third determining unit is configured to determine the target geographic location information according to the appearance frequency of the third content.

8. An electronic device comprising: A transceiver, a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the information push method according to any one of claims 1 to 6 are implemented.

9. A readable storage medium, characterized in that The readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the information push method according to any one of claims 1 to 6.

Images